System

Abstract

To provide a system.SOLUTION: The system includes: means for determining, by AI, the delivery route of the day in question when the probability of re-delivery is reduced by using traffic information data, record data of re-delivery or absence of a resident, delivery package information of the day, electric meter information, and feature data of a route in the view of a local delivery; means for linking the route determined by the AI with a vehicle navigation system; means for collecting emotion data including voice, texts, facial expressions, and body actions through the interaction with the user; and means for analyzing the collected emotion data and re-optimizing the delivery route on the basis of the result of analysis.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional delivery route determination methods had the problem of not being able to fully consider the possibility of redelivery and being prone to variations depending on the driver's experience. [Means for solving the problem]

[0005] This invention utilizes traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers to determine a delivery route using AI that reduces the possibility of redelivery each day.Furthermore, by linking the route determined by AI with the car navigation system, it becomes possible to maintain the same level of delivery quality regardless of whether the driver is a veteran or a novice. [Brief explanation of the drawings]

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

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

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

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

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

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

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

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

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

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

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

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0027] "Example 1"

[0028] One aspect of the present invention is a delivery route determination system. This system collects traffic information data, data on resident absences / redelivery attempts, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and AI determines the optimal delivery route based on this data. Specifically, the AI ​​determines the delivery route taking into account resident absence times and redelivery attempt history data in order to reduce the possibility of redelivery.

[0029] "Example 2"

[0030] Furthermore, the route determined by AI is displayed in conjunction with the car navigation system. This allows the driver to make deliveries by following the optimal route determined by AI. Specifically, the route determined by AI is displayed on the car navigation screen, and the driver delivers by following that route. This makes it possible to maintain delivery standards regardless of whether the driver is a veteran or a novice.

[0031] "Example 3"

[0032] As a concrete example, a driver in charge of deliveries in a certain area inputs information about the day's deliveries and data on residents' absences / re-deliveries into the system. The system uses this information, traffic information data, electricity meter information, and route characteristics data from the area driver's perspective to determine the optimal delivery route using AI. This route is displayed on the car navigation system, and the driver follows it to make the delivery. This reduces the possibility of re-delivery and makes it possible to maintain delivery standards.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The delivery route determination system collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[0036] Step 2: Based on the collected data, the AI ​​determines the optimal delivery route. Specifically, to reduce the possibility of redelivery, the AI ​​determines the delivery route by taking into account the time when residents are absent and past redelivery data.

[0037] "Example 2"

[0038] Step 1: The route determined by the AI ​​is displayed in conjunction with the car navigation system.

[0039] Step 2: The driver follows the instructions on the car navigation system to make the delivery. This allows the delivery level to be maintained regardless of whether the driver is a veteran or a novice.

[0040] "Example 3"

[0041] Step 1: A driver in charge of deliveries in a certain area enters the delivery package information for the day and the actual data on residents' absence / re-delivery into the system.

[0042] Step 2: The system uses this information, traffic data, electricity meter information, and route characteristics data from the perspective of area drivers to determine the optimal delivery route using AI.

[0043] Step 3: This route is displayed on the car navigation system and the driver follows it to make the delivery, reducing the chance of redelivery and maintaining delivery levels.

[0044] Example 1

[0045] Next, a description will be given of 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."

[0046] Conventional delivery route determination systems had a high probability of redelivery, making efficient delivery difficult. Furthermore, they were unable to determine the optimal route taking into account traffic information and whether residents were at home, resulting in poor delivery efficiency. Another issue was the discrepancy in delivery quality between veteran and novice drivers.

[0047] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0048] In this invention, the server includes means for collecting traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers, means for preprocessing the collected data, means for training a machine learning model based on the preprocessed data, means for receiving delivery requests from users, means for calculating an optimal delivery route using the trained machine learning model, means for transmitting the calculated optimal route to a terminal, and means for displaying the route information received by the terminal to the user. This reduces the possibility of redelivery and enables efficient delivery route determination. It also allows for the maintenance of delivery quality between veteran and novice drivers.

[0049] "Traffic information data" refers to data that indicates real-time traffic conditions and road congestion.

[0050] "Resident absence / redelivery performance data" is data that indicates the time when residents were absent during past deliveries and the history of redeliveries.

[0051] "Today's delivery parcel information" is data showing detailed information about parcels to be delivered on the same day.

[0052] "Electricity meter information" is data on electricity usage that is used to estimate whether residents are at home.

[0053] "Route characteristics data from the perspective of area drivers" is data on route characteristics based on feedback from drivers.

[0054] "Means of collection" refers to the methods and devices used to obtain the required data.

[0055] "Preprocessing means" refers to methods or devices used to convert collected data into a form suitable for analysis or model training.

[0056] "Means for training a machine learning model" refers to a method or apparatus for training a machine learning algorithm using collected and pre-processed data.

[0057] "Means for receiving a delivery request" refers to a method or device for receiving a delivery request from a user.

[0058] "Means for calculating optimal delivery routes" refers to a method or apparatus for using a trained machine learning model to calculate the most efficient delivery route.

[0059] "Means for transmitting to the terminal" refers to a method or device for transmitting the calculated delivery route to the user's terminal.

[0060] The term "means for displaying the route information received by the terminal to the user" refers to a method or device for visually presenting the delivery route information received by the terminal to the user.

[0061] This invention relates to a delivery route determination system that determines the optimal delivery route by utilizing traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristic data from the perspective of area drivers.

[0062] Generating a Program

[0063] The system's programs are generated using Python, with key libraries including requests for data collection, pandas for data processing, and scikit-learn and TENSORFLOW (registered trademark) for building machine learning models.

[0064] Program processing explanation

[0065] The server collects the following data:

[0066] Traffic data: Use common map APIs to get real-time traffic information.

[0067] Resident absence / redelivery performance data: Obtain past delivery performance data from the delivery company database.

[0068] Today's delivery package information: Obtain today's delivery list from the delivery management system.

[0069] Electricity meter information: Use the smart meter API to obtain electricity usage data to infer whether residents are at home.

[0070] Route characteristics data from the perspective of area drivers: Feedback from drivers is collected and route characteristics are stored in a database.

[0071] After collecting this data, the server uses pandas to preprocess the data, specifically by filling in missing values ​​and normalizing the data.

[0072] The server then uses scikit-learn and TensorFlow to build a machine learning model that optimizes delivery routes by taking into account the time residents are away and past redelivery attempts to reduce the likelihood of redelivery.

[0073] After the model is trained, the server calculates the optimal delivery route and sends it to the device each time a new delivery request comes in.

[0074] Examples and prompts

[0075] As a concrete example, consider the following scenario:

[0076] The user inputs a new delivery request into the system. For example, the user might input "Make 10 deliveries within Tokyo on October 10, 2023." Based on this information, the server calculates the optimal delivery route and sends it to the device.

[0077] Example prompts to input to a generative AI model:

[0078] "I plan to make 10 deliveries within Tokyo on October 10, 2023. Please calculate the optimal delivery route taking into account traffic information data, data on residents' absence / redelivery attempts, information on the delivery packages for that day, electricity meter information, and route characteristics data from the perspective of area drivers."

[0079] By inputting this prompt into the generative AI model, the AI ​​will calculate the optimal delivery route and provide it to the user.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[0083] Input: Traffic information API, delivery company database, delivery management system, smart meter API, driver feedback

[0084] Output: Various collected data

[0085] Specific operation: The server calls the traffic information API to obtain real-time traffic information, obtains past delivery performance data from the delivery company's database, obtains the delivery list for the day from the delivery management system, obtains electricity usage data using the smart meter API, and collects feedback from drivers and stores it in the database.

[0086] Step 2:

[0087] The server pre-processes the collected data.

[0088] Input: Various collected data

[0089] Output: Preprocessed data

[0090] What it does: The server uses the pandas library to impute missing values ​​in the data, normalize data of different scales, and combine data from different sources into a single data frame.

[0091] Step 3:

[0092] The server trains a machine learning model based on the preprocessed data.

[0093] Input: Preprocessed data

[0094] Output: A trained machine learning model

[0095] Specific operation: The server builds a machine learning model using scikit-learn or TensorFlow, selects features, and chooses the optimal algorithm (e.g., random forest, neural network) to train the model.

[0096] Step 4:

[0097] A user enters a new delivery request into the system.

[0098] Input: Delivery request (e.g., "Make 10 deliveries in Tokyo on October 10, 2023")

[0099] Output: Delivery request data

[0100] Specific operation: The user inputs a delivery request into the system interface. The server receives this request and stores it in the database.

[0101] Step 5:

[0102] The server uses a trained machine learning model to calculate the optimal delivery route.

[0103] Input: Delivery request data, trained machine learning model

[0104] Output: Optimal delivery route

[0105] What it does: The server converts delivery request data into a format that can be fed into the model, and then uses a trained machine learning model to predict the optimal delivery route.

[0106] Step 6:

[0107] The server transmits the calculated optimum route to the terminal.

[0108] Input: Optimal delivery route

[0109] Output: Route information sent to the device

[0110] Specific operation: The server calls an API to send the calculated optimal route to the terminal, and sends the route information to the terminal.

[0111] Step 7:

[0112] The terminal displays the received route information to the user.

[0113] Input: Route information sent to the device

[0114] Output: Route information displayed to the user

[0115] Specific operation: The terminal provides an interface for visually displaying the received route information to the user.

[0116] (Application example 1)

[0117] Next, a description will be given of Application Example 1 of Embodiment 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."

[0118] Conventional delivery systems were unable to fully utilize traffic information and data on residents' absence, resulting in frequent redelivery. Furthermore, delivery routes were not optimized sufficiently, making it difficult to predict delivery times. This resulted in issues such as reduced delivery efficiency and lower customer satisfaction.

[0119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0120] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by AI with a car navigation system, means for optimizing the delivery route using an application installed on a smartphone, and means for predicting delivery times that reflect real-time traffic information. This makes it possible to reduce the frequency of redelivery and improve delivery efficiency.

[0121] "Traffic information data" refers to information about traffic collected in real time, such as road congestion, traffic accidents, and construction information.

[0122] "Resident absence / redelivery record data" is data that indicates the time periods when a particular resident was absent in the past and the history of redelivery requests.

[0123] "Today's delivery parcel information" is detailed information about parcels scheduled to be delivered on that day, and is data including the type of parcel, the quantity, the delivery address, and so on.

[0124] "Electricity meter information" is data that indicates the electricity usage status of residents and is used to infer whether residents are at home or not.

[0125] "Route characteristics data from the perspective of area drivers" is data that shows the route characteristics and points of caution that drivers in charge of a specific area have empirically recognized.

[0126] "Method of deciding using AI" is a method of determining the optimal delivery route using artificial intelligence.

[0127] "Means for linking with car navigation" refers to a method for linking the determined delivery route with the in-car navigation system.

[0128] The "application installed on a smartphone" is software that runs on a smartphone and is used to optimize delivery routes and predict delivery times.

[0129] "Means for predicting delivery time by reflecting real-time traffic information" refers to a method for predicting the time required for delivery by taking into account current traffic conditions.

[0130] The following system configuration will be described as an embodiment of the present invention.

[0131] System Configuration

[0132] The system consists of a server, smartphone, car navigation system, and various data sources. The server collects traffic information data, data on absences and redelivery requests, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. Based on this data, AI determines the optimal delivery route.

[0133] Hardware and software used

[0134] Hardware: Servers, smartphones, car navigation systems

[0135] Software: Python, Pandas (data processing), Scikit-learn (machine learning), Geopy (geographic information processing)

[0136] Data processing and calculation

[0137] The server processes the data in the following steps:

[0138] 1. Loading data: Traffic information, data on resident absences / redelivery attempts, information on the day's deliveries, electricity meter information, and route characteristics data from the perspective of area drivers are loaded from a CSV file.

[0139] 2. Data preprocessing: Combining data and handling missing values.

[0140] 3. Setting features and targets: Set delivery time as the target variable and other data as features.

[0141] 4. Train the model: Train the model using RandomForestRegressor.

[0142] 5. Delivery Route Optimization: Determine the optimal delivery route using geodesic distance.

[0143] 6. Delivery Route Prediction: Predict delivery times based on optimal delivery routes.

[0144] Specific examples

[0145] For example, if there are multiple delivery destinations in Tokyo, the server will determine the optimal route and predict delivery times, taking into account traffic information and data on resident absences, thereby reducing the frequency of redelivery and improving delivery efficiency.

[0146] Prompt Sentence Examples

[0147] "If there are multiple delivery destinations in Tokyo, create a Python program that determines the optimal route and predicts delivery times, taking into account traffic information and resident absence data."

[0148] The above is an embodiment of the present invention. This system makes it possible to reduce the frequency of redelivery and improve delivery efficiency.

[0149] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0150] Step 1:

[0151] The server reads traffic information data, data on resident absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers from CSV files. This provides all the data necessary to optimize delivery routes. The inputs are various data files, and the output is an integrated dataset.

[0152] Step 2:

[0153] The server preprocesses the loaded data. Specifically, it combines the data and handles missing values. For example, traffic information data and resident absence data are combined using addresses as keys, and missing values ​​are imputed with the mean or median. The input is the combined dataset, and the output is the preprocessed dataset.

[0154] Step 3:

[0155] The server sets features and target variables from the preprocessed dataset. The features are factors that affect delivery time (e.g., traffic information, time when residents are out, electricity meter information, etc.), and the target variable is the delivery time. The input is the preprocessed dataset, and the output is a set of features and target variables.

[0156] Step 4:

[0157] The server trains a machine learning model (RandomForestRegressor) using the features and target variables. It fits the model using the training data and generates a model for predicting delivery times. The input is a set of features and target variables, and the output is the trained machine learning model.

[0158] Step 5:

[0159] The server determines the optimal delivery route using geodesic distance. Specifically, it optimizes the route by choosing the closest delivery point from the current location, and then choosing the next closest delivery point from that point. The input is a list of delivery points, and the output is the optimized delivery route.

[0160] Step 6:

[0161] The server uses a trained machine learning model to predict delivery times based on the optimized delivery route, with the input being the optimized delivery route and the output being the predicted delivery time at each destination.

[0162] Step 7:

[0163] The server sends the optimized delivery route and predicted delivery time to an application installed on the smartphone, allowing the driver to check the optimal delivery route and predicted delivery time in real time. The input is the optimized delivery route and predicted delivery time, and the output is data sent to the smartphone application.

[0164] Step 8:

[0165] The user (driver) uses a smartphone application to deliver packages according to an optimized delivery route. The application reflects real-time traffic information and recalculates the route as necessary. The input is data sent from the server, and the output is the actual delivery operation.

[0166] Example 2

[0167] Next, a description will be given of 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 will be referred to as a "terminal."

[0168] With conventional delivery systems, there was a high chance of redelivery, making it difficult to determine efficient delivery routes. It was also difficult to maintain a consistent delivery level, regardless of whether the driver was a veteran or a novice. Furthermore, it was not possible to provide optimal routes that took into account real-time traffic and weather information. This resulted in poor delivery efficiency and lower customer satisfaction.

[0169] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0170] In this invention, the server includes: a means for determining a delivery route using artificial intelligence to reduce the likelihood of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, delivery package information for the day, electricity meter information, and route characteristics data from the perspective of area drivers; a means for linking the route determined by artificial intelligence with a navigation system; a means for receiving a list of delivery addresses and acquiring location information for each address using a geographic information system; a means for acquiring weather information and collecting traffic data; a means for preprocessing the acquired data and inputting it into a generative AI model to calculate the optimal delivery route; and a means for transmitting the generated optimal route to the navigation system and displaying it. This reduces the likelihood of redelivery and provides efficient delivery routes. It also maintains a consistent delivery level regardless of whether the driver is a veteran or a novice. Furthermore, it is possible to provide optimal routes that take real-time traffic and weather information into account, improving delivery efficiency and customer satisfaction.

[0171] "Traffic information data" refers to information relating to traffic flow, such as road congestion, accident information, and road closure information.

[0172] "Resident absence / redelivery performance data" refers to historical information such as the time periods when residents were absent during past deliveries and the number of redeliveries made.

[0173] "Same-day delivery parcel information" refers to detailed information such as the quantity, size, weight, and delivery address of parcels to be delivered on the same day.

[0174] "Electricity meter information" is data that indicates the electricity usage status of the residence or building where delivery is made, and is used to estimate whether residents are at home.

[0175] "Route characteristics data from the perspective of area drivers" refers to information that shows route characteristics and points of caution based on the experience and knowledge of drivers in a specific area.

[0176] "Artificial intelligence" refers to algorithms and models that use machine learning and data analysis to calculate optimal delivery routes.

[0177] "Navigation system" refers to a device installed in a vehicle that provides map information and route guidance functions.

[0178] "Geographic information system" refers to a system for collecting, managing, and analyzing geographic data.

[0179] "Generative AI models" refer to algorithms or models built using machine learning frameworks to generate optimal delivery routes.

[0180] "Preprocessing" refers to the process of converting collected data into the format required to input it into a generative AI model.

[0181] The present invention relates to a system for calculating and displaying efficient routes in delivery work. A specific embodiment of this system will be described below.

[0182] System Overview

[0183] This system consists of three main components: a server, a terminal, and a user. The server collects data, preprocesses it, and calculates routes using a generative AI model. The terminal functions as a car navigation system, displaying the optimal route sent from the server. The user inputs a list of delivery addresses and makes deliveries according to the system's instructions.

[0184] Hardware and software used

[0185] Server: Use a server with high-performance computing capabilities. Specifically, you can use cloud services such as Google (registered trademark) Cloud Platform and Amazon Web Services.

[0186] Terminal: Use a general navigation device (e.g., Garmin or TomTom) as a car navigation system.

[0187] Software: Google Maps API, OpenWeatherMap API, Waze API, etc. are used for data collection. Machine learning frameworks such as TensorFlow and PyTorch are used for building generative AI models.

[0188] Data collection and preprocessing

[0189] The server receives a list of delivery addresses entered by the user. For example, the user enters "1-1 Marunouchi, Chiyoda-ku, Tokyo." The server obtains the latitude and longitude of each address using the Google Maps API. It also obtains current weather information using the OpenWeatherMap API and collects traffic data using the Waze API. This data is preprocessed to be input into the generative AI model. Specifically, the address data is converted into latitude and longitude, and the weather information and traffic data are converted into numerical data.

[0190] Route calculation using generative AI models

[0191] The preprocessed data is then input into a generative AI model, which is built using TensorFlow and PyTorch to calculate the optimal delivery route. For example, multiple delivery destination data is input as a single batch, and the optimal route is generated, such as from destination A to destination B to destination C.

[0192] View routes and make deliveries

[0193] The generated optimal route is sent from the server to the terminal. The terminal analyzes the received route information and displays it on the car navigation system screen. The driver delivers the parcel by following the route displayed on the car navigation system. The car navigation system updates the route information in real time and notifies the driver.

[0194] Examples of specific examples and prompts

[0195] Examples:

[0196] The user inputs a list of delivery addresses.

[0197] The server uses the Google Maps API to obtain the latitude and longitude of each address and the OpenWeatherMap API to obtain current weather information.

[0198] The server preprocesses this data and feeds it into a generative AI model.

[0199] The generative AI model calculates the optimal delivery route and sends that route information to the car navigation system.

[0200] The driver makes the delivery by following the route displayed on the car navigation system.

[0201] Example prompt sentence:

[0202] Enter a list of delivery addresses and the system will calculate the optimal delivery route and display it on your car navigation system.

[0203] example:

[0204] 1. 1-1 Marunouchi, Chiyoda-ku, Tokyo

[0205] 2. 1-1 Jinnan, Shibuya-ku, Tokyo

[0206] 3. 2-8 Nishi-Shinjuku, Shinjuku-ku, Tokyo

[0207] In this way, the system provides efficient delivery routes, reduces the likelihood of redelivery, and improves delivery efficiency and customer satisfaction.

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] The user inputs a list of delivery addresses.

[0211] Input: Delivery address list (e.g., 1-1 Marunouchi, Chiyoda-ku, Tokyo, 1-1 Jinnan, Shibuya-ku, Tokyo, 2-8 Nishi-Shinjuku, Shinjuku-ku, Tokyo)

[0212] Output: A list of delivery addresses is sent to the server.

[0213] Specific operation: The user enters the delivery address in text format into the system's input form and clicks the "Submit" button.

[0214] Step 2:

[0215] The server uses the Google Maps API to get the latitude and longitude of each address.

[0216] Input: Delivery address list

[0217] Output: Latitude and longitude information for each address (e.g., 35.681236, 139.767125)

[0218] Specific operation: The server sends a request to the Google Maps API for each address and receives latitude and longitude information in response.

[0219] Step 3:

[0220] The server uses the OpenWeatherMap API to get current weather information.

[0221] Input: Latitude and longitude information for each address

[0222] Output: Weather information for each address (e.g. sunny, temperature 25°C, wind speed 5m / s)

[0223] Specific operation: The server sends a request to the OpenWeatherMap API based on latitude and longitude information and receives weather information in response.

[0224] Step 4:

[0225] The server collects traffic data using the Waze API.

[0226] Input: Latitude and longitude information for each address

[0227] Output: Traffic data for each address (e.g., traffic jams, road closures)

[0228] Specific operation: The server sends a request to the Waze API based on latitude and longitude information and receives traffic condition data in response.

[0229] Step 5:

[0230] Preprocess the data retrieved by the server.

[0231] Input: Latitude and longitude information, weather information, traffic condition data

[0232] Output: Preprocessed dataset (e.g. { "latitude": 35.681236, "longitude": 139.767125, "weather": 1, "temperature": 25, "wind_speed": 5, "traffic": "normal"})

[0233] Specific operation: The server converts address data into latitude and longitude, and converts weather information and traffic condition data into numerical data and compiles them into a single dataset.

[0234] Step 6:

[0235] The server inputs the preprocessed dataset into the generative AI model.

[0236] Input: Preprocessed dataset

[0237] Output: Optimal delivery route (e.g., destination A → destination B → destination C)

[0238] How it works: The server inputs a dataset into the generative AI model, which then calculates the optimal delivery route.

[0239] Step 7:

[0240] The server transmits the generated optimal route to the navigation system.

[0241] Input: Optimal delivery route

[0242] Output: Route information sent to the navigation system

[0243] What happens: The server sends the route information to the navigation system's API using an HTTP POST request.

[0244] Step 8:

[0245] The device analyzes the route information it receives and displays it on the screen.

[0246] Input: Route information

[0247] Output: The route displayed on the screen (e.g. the route shown as a blue line on a map)

[0248] Specific operation: The device analyzes the received route information, displays the route on a map, and provides voice guidance for the next turn.

[0249] Step 9:

[0250] The driver makes the delivery by following the route displayed on the car navigation system.

[0251] Input: Route displayed on car navigation system

[0252] Output: Arrival at delivery destination

[0253] Specific operations: The driver drives the car according to the instructions of the car navigation system and makes deliveries along the specified route.

[0254] Step 10:

[0255] The device updates route information in real time and notifies the driver.

[0256] Input: Real-time traffic data

[0257] Output: Updated route information

[0258] What it does: The device periodically retrieves traffic data, recalculates the route if necessary, and notifies the driver.

[0259] (Application example 2)

[0260] Next, a description will be given of 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 will be referred to as a "terminal."

[0261] Conventional delivery systems face the problem of determining optimal delivery routes that take into account traffic information and information on when residents are absent, resulting in a high likelihood of redelivery. It is also difficult to maintain delivery standards, regardless of whether the driver is a veteran or a novice. Furthermore, there was a lack of means to provide real-time updates on delivery progress or feedback after delivery completion, leading to a need for improved delivery efficiency.

[0262] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0263] In this invention, the server includes a means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by AI with a car navigation system, a means for displaying the optimal delivery route determined by AI in real time using an application installed on a smartphone, and a means for updating delivery progress in real time and providing feedback after delivery is completed.This reduces the possibility of redelivery, maintains delivery standards regardless of whether the driver is experienced or new, and improves delivery efficiency.

[0264] "Traffic information data" refers to data that includes information related to traffic, such as road congestion, traffic accidents, and construction information.

[0265] "Resident absence / redelivery performance data" is data that includes information on the time periods when residents were absent and the history of redelivery.

[0266] "Today's delivery parcel information" is data including information on the type and quantity of parcels to be delivered that day, delivery addresses, and the like.

[0267] "Electricity meter information" is data that indicates the electricity usage status of residents, and is used to estimate whether residents are at home.

[0268] "Route characteristics data from the perspective of area drivers" is data that includes information about route characteristics based on the experience and knowledge of drivers in a specific area.

[0269] "Determining by AI" is a method of calculating and determining the optimal delivery route using artificial intelligence.

[0270] "Means for linking with car navigation systems" refers to a method for displaying the determined delivery route on a car navigation system so that the driver can follow that route.

[0271] The "application installed on a smartphone" is software that runs on a smartphone and displays delivery routes and manages delivery progress.

[0272] "Means for updating delivery progress in real time" refers to a method for recording and updating the progress of delivery in real time.

[0273] "Means for providing feedback after delivery completion" refers to a method for providing evaluations and suggestions for improvement to the driver or system after a delivery is completed.

[0274] The system for implementing this invention includes a means for using traffic information data, data on residents' absence / redelivery records, information on the delivery packages for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by AI with a car navigation system, a means for displaying the optimal delivery route determined by AI in real time using an application installed on a smartphone, and a means for updating delivery progress in real time and providing feedback after delivery is completed.

[0275] Program processing explanation

[0276] Hardware used

[0277] server

[0278] Smartphone

[0279] Software used

[0280] TensorFlow: Used to load AI models and make predictions.

[0281] Google Maps API: Used to display routes.

[0282] Data processing and calculation

[0283] 1. The server collects traffic information data, data on residents' absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses this data to calculate the optimal delivery route using an AI model. The AI ​​model uses TensorFlow.

[0284] 2. The server sends the calculated optimal route to the smartphone.

[0285] 3. The smartphone uses the Google Maps API to display the received optimal route on the car navigation app.

[0286] 4. The smartphone provides real-time updates on delivery progress and feedback after delivery is completed.

[0287] Specific examples

[0288] For example, if the starting point is Tokyo Station (latitude 35.6895, longitude 139.6917) and the destination is Tokyo Tower (latitude 35.6586, longitude 139.7454), the server inputs these location information into the AI ​​model to calculate the optimal delivery route.The calculated route information is then sent to the smartphone, which then uses the Google Maps API to display the route on the car navigation app.

[0289] Prompt Sentence Examples

[0290] Enter your starting point and destination, and our AI will calculate the optimal route and display it on your car navigation system.

[0291] Example: Origin: Tokyo Station (35.6895, 139.6917), Destination: Tokyo Tower (35.6586, 139.7454)

[0292] In this way, the embodiments of the invention can reduce the likelihood of redelivery, maintain delivery levels regardless of whether the driver is a veteran or a novice, and improve delivery efficiency.

[0293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0294] Step 1:

[0295] The server collects traffic information data, data on resident absences / redelivery records, information on the delivery packages for the day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from various sensors and databases. Input data includes traffic information, time when residents are absent, redelivery history, details of delivery packages, electricity usage status, and driver experience information. This data is integrated and pre-processed for input into the AI ​​model.

[0296] Step 2:

[0297] The server uses TensorFlow to load an AI model based on the preprocessed data and calculates the optimal delivery route. The input data includes preprocessed traffic information, residents' absence times, redelivery history, delivery package details, power usage, and driver experience. The AI ​​model analyzes this data and outputs the optimal delivery route.

[0298] Step 3:

[0299] The server sends the calculated optimal route to the smartphone. The optimal route information output by the AI ​​model is included as input data. The server sends this information to the smartphone, which then receives it.

[0300] Step 4:

[0301] The smartphone uses the Google Maps API to display the received optimal route on the car navigation app. The optimal route information received from the server is included as input data. The smartphone calls the Google Maps API and displays the optimal route on the car navigation app.

[0302] Step 5:

[0303] The user (driver) starts driving according to the optimal route displayed on the car navigation app. The optimal route information displayed on the car navigation app is included as input data. The user drives based on this information.

[0304] Step 6:

[0305] The smartphone updates the delivery progress in real time. Input data includes the user's current location and delivery status. Based on this information, the smartphone updates the delivery progress in real time and sends it to the server.

[0306] Step 7:

[0307] After the delivery is completed, the smartphone provides feedback. The input data includes delivery completion information and user feedback. Based on this information, the smartphone generates feedback after the delivery is completed and provides it to the user.

[0308] Example 3

[0309] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0310] Conventional delivery systems were unable to fully utilize data on residents' absences and redelivery attempts, resulting in frequent redeliveries. Furthermore, because they did not take into account traffic information or route characteristics data from the perspective of area drivers, it was difficult to determine efficient delivery routes. Another issue was the difference in delivery ability between veteran and novice drivers.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0312] In this invention, the server includes: means for determining a delivery route for the day using artificial intelligence to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers; means for linking the route determined by artificial intelligence with an in-vehicle navigation system; means for a user to input delivery information into a terminal and for the terminal to send the input data to the server; means for the server to receive and preprocess the data; means for the server to acquire traffic information and integrate electricity meter information and route characteristic data; means for the server to input data into a machine learning model and calculate an optimal delivery route; means for the server to send the calculation results to the terminal and for the terminal to display the optimal delivery route on the in-vehicle navigation system; and means for the user to make delivery according to instructions from the in-vehicle navigation system. This reduces the possibility of redelivery and enables efficient delivery.

[0313] "Traffic information data" refers to data that indicates real-time traffic conditions, including congestion information, road closure information, and the like.

[0314] "Resident absence / redelivery performance data" is data that shows information about the history of when residents were absent and redelivery, such as past delivery dates and times and the number of redeliveries.

[0315] "Today's delivery parcel information" is information about parcels to be delivered, including the parcel ID, delivery address, and type of parcel.

[0316] "Electricity meter information" is data indicating whether a resident is at home, and is information used to determine whether a resident is at home based on electricity usage.

[0317] "Route characteristic data from the perspective of area drivers" is data that indicates characteristics that drivers consider when selecting a delivery route, such as the width of roads within the delivery area, the number of traffic lights, and the availability of parking spaces.

[0318] "Artificial intelligence" is a technology that uses machine learning models to analyze data and calculate optimal delivery routes.

[0319] An "in-vehicle navigation system" is a navigation device installed in a vehicle that displays the optimal delivery route and guides the driver through voice guidance and map display.

[0320] A "terminal" is a device through which a user inputs delivery information, and includes smartphones, tablets, and the like.

[0321] A "server" is a computer system that receives data sent from a terminal and performs preprocessing, data integration, and calculations using machine learning models.

[0322] A "machine learning model" is an algorithm that analyzes data and calculates optimal delivery routes, and is implemented using libraries such as Scikit-learn.

[0323] This invention is a system aimed at improving the efficiency of delivery operations, and utilizes traffic information data, data on residents' absence / redelivery records, information on the parcels delivered on the day, electricity meter information, and data on route characteristics from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery using artificial intelligence.

[0324] System configuration

[0325] The system consists of the following main components:

[0326] 1. Terminal: A device through which a user enters delivery information, including smartphones and tablets.

[0327] 2. Server: A computer system that receives data sent from the terminal and performs preprocessing, data integration, and calculations using machine learning models.

[0328] 3. In-vehicle navigation system: A device that displays the optimal delivery route and guides the driver through voice guidance and map display.

[0329] Hardware and software used

[0330] Hardware: Smartphones, tablets, servers, in-car navigation systems

[0331] Software: Python, Pandas, Scikit-learn, Google Maps API

[0332] Program processing

[0333] The user (driver) enters the delivery package information for the day (package ID, delivery address, package type) and the resident's absence / redelivery record data (past delivery date and time, number of redeliveries) into the terminal. The terminal converts the entered data into JSON format and sends it to the server using the HTTPS protocol.

[0334] The server converts the received JSON data into a data frame using Pandas and performs preprocessing such as missing value imputation and data normalization. The server then uses the Google Maps API to obtain real-time traffic information, including congestion and road closure information.

[0335] The server combines electricity meter information (data showing whether residents are at home) with route characteristics data from the perspective of area drivers (road width, number of traffic lights, availability of parking spaces), and gathers all the data necessary to optimize delivery routes. The combined data is then input into a machine learning model using Scikit-learn to calculate the optimal delivery route. The model then suggests routes that reduce the likelihood of redelivery.

[0336] The server converts the calculated optimal delivery route into JSON format and sends it to the terminal using the HTTPS protocol. The terminal then displays the received optimal delivery route on the in-vehicle navigation system. The in-vehicle navigation system then guides the driver through voice guidance and map display.

[0337] The user (driver) delivers the parcel according to the instructions of the in-vehicle navigation system, which reduces the possibility of redelivery and enables efficient delivery.

[0338] Examples of specific examples and prompts

[0339] For example, the driver enters the following information:

[0340] Delivery information: Package ID 12345, Delivery address 1-2-3 Shibuya-ku, Tokyo, Package type Books

[0341] Absence / redelivery record data: Past delivery date and time 2023-10-01 14:00, redelivery count 2

[0342] Traffic information data: Traffic congestion information Traffic congestion occurs on major roads in Shibuya Ward

[0343] Electricity meter information: At home

[0344] Route characteristics data: narrow road width, many traffic lights, no parking space

[0345] Example prompt sentence:

[0346] Delivery package information:

[0347] Package ID: 12345

[0348] Delivery address: 1-2-3 Shibuya-ku, Tokyo

[0349] Type of package: Books

[0350] Absence / redelivery performance data:

[0351] Previous delivery date: 2023-10-01 14:00

[0352] Number of redeliveries: 2

[0353] Traffic Information Data:

[0354] Traffic congestion information: Traffic jams on major roads in Shibuya Ward

[0355] Electricity meter information:

[0356] Home status: Home

[0357] Route feature data:

[0358] Road width: Narrow

[0359] Number of signals: Many

[0360] Parking space: None

[0361] When this prompt sentence is input into the generative AI model, the AI ​​calculates the optimal delivery route and displays it on the in-vehicle navigation system. By following this route, the driver can reduce the possibility of redelivery and achieve efficient delivery. The flow of the identification process in Example 3 will be explained using Figure 15.

[0362] Step 1:

[0363] The user enters the delivery information into the terminal.

[0364] Using a smartphone or tablet, users enter delivery package information (e.g., package ID 12345, delivery address 1-2-3, Shibuya-ku, Tokyo, package type: books) and past absence / redelivery data (e.g., past delivery date and time 2023-10-01 14:00, number of redeliveries 2) into a dedicated app. The entered data is converted to JSON format on the device.

[0365] Input: Delivery package information, absence / redelivery record data

[0366] Output: JSON format data

[0367] Step 2:

[0368] The terminal transmits the input data to the server.

[0369] The terminal sends the data converted into JSON format to the server using the HTTPS protocol, and the sent data reaches the server through a secure communication channel.

[0370] Input: JSON format data

[0371] Output: Data sent to the server

[0372] Step 3:

[0373] The server receives the data and performs pre-processing.

[0374] The server converts the received JSON data into a data frame using Pandas, then performs missing value imputation (e.g., imputing 0 if the number of redeliveries is not entered) and data normalization (e.g., converting address data to a standard format).

[0375] Input: Data sent to the server

[0376] Output: Preprocessed data frame

[0377] Step 4:

[0378] The server retrieves traffic information using the Google Maps API.

[0379] The server calls the Google Maps API to obtain real-time traffic information for a specified area (e.g., Shibuya Ward, Tokyo). The obtained data includes information on traffic congestion on major roads and road closures.

[0380] Input:Specified area information

[0381] Output: Real-time traffic information

[0382] Step 5:

[0383] The server integrates the electricity meter information with the route characteristic data.

[0384] The server combines electricity meter information (e.g., whether residents are at home) with route characteristics data from the perspective of area drivers (e.g., narrow roads, many traffic lights, lack of parking spaces), providing all the data needed to optimize delivery routes.

[0385] Input: Electricity meter information, route characteristics data

[0386] Output: Consolidated data

[0387] Step 6:

[0388] The server inputs the data into a machine learning model to calculate the optimal delivery route.

[0389] The server then inputs the combined data into a machine learning model using Scikit-learn to calculate the optimal delivery route, which then suggests routes to reduce the chance of redelivery.

[0390] Input: Integrated data

[0391] Output: Optimal delivery route

[0392] Step 7:

[0393] The server sends the calculation results to the terminal.

[0394] The server converts the calculated optimal delivery route into JSON format and sends it to the terminal using the HTTPS protocol.

[0395] Input: Optimal delivery route

[0396] Output: Data sent to the terminal

[0397] Step 8:

[0398] The device displays the optimal delivery route on the vehicle's navigation system.

[0399] The device then displays the optimal delivery route on the in-vehicle navigation system, which then guides the driver through voice guidance and map display.

[0400] Input: Data sent to the terminal

[0401] Output: Route displayed on the in-car navigation system

[0402] Step 9:

[0403] The user makes the delivery according to the instructions of the in-car navigation system.

[0404] The user (driver) makes deliveries according to the instructions of the in-car navigation system. For example, if the car navigation system instructs the driver to "turn right at the next intersection," the driver will follow the instruction and turn right. This reduces the possibility of redelivery and enables efficient delivery.

[0405] Input: In-car navigation system instructions

[0406] Output: Efficient delivery

[0407] (Application example 3)

[0408] Next, a description will be given of 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 will be referred to as a "terminal."

[0409] Conventional delivery systems have a high probability of redelivery and make it difficult to determine efficient delivery routes. Even in food delivery, they are unable to provide optimal routes that take into account traffic information and past delivery performance data, making it difficult to shorten delivery times or improve efficiency. This has led to delivery delays and redeliveries, resulting in lower customer satisfaction.

[0410] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0411] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by AI with a car navigation system, means for inputting food delivery information and determining an optimal delivery route based on traffic information data, past delivery record data, and area characteristic data, and means for displaying the optimal route on a car navigation app on a smartphone.This reduces the possibility of redelivery and enables shorter and more efficient delivery times.

[0412] "Traffic information data" refers to information about traffic provided in real time, such as road congestion, traffic accidents, and construction information.

[0413] "Resident absence / redelivery performance data" is historical information such as the time periods when residents were absent in the past and the number of redeliveries made.

[0414] "Today's delivery package information" is information about packages to be delivered on that day, such as the contents of the package to be delivered, the delivery address, and the scheduled delivery time.

[0415] "Electricity meter information" is data that indicates the electricity usage status of residents, and is information that is used to infer whether residents are at home or not.

[0416] "Route characteristics data from the perspective of area drivers" is information on the characteristics of routes based on road features and traffic conditions within the delivery area, as well as the driver's experience.

[0417] "AI" stands for artificial intelligence, a technology that calculates optimal delivery routes based on data.

[0418] A "car navigation system" is a navigation system installed in a vehicle that provides map information and route guidance.

[0419] "Food delivery" is a service that delivers food and drinks to a location specified by the customer.

[0420] A "smartphone car navigation app" is a navigation application that runs on a smartphone and is software that provides map information and route guidance.

[0421] The "optimal delivery route" is a delivery route calculated based on traffic information and past delivery performance data in order to shorten delivery times and increase efficiency.

[0422] A system for implementing the present invention includes a server, a smartphone, a car navigation application, and an AI model. A specific embodiment of this system will be described below.

[0423] System configuration

[0424] 1. Server:

[0425] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers, and uses this data to calculate the optimal delivery route using an AI model.

[0426] The server is programmed using Python and has an interface for obtaining traffic information APIs and past delivery performance data.

[0427] 2. Smartphone:

[0428] The smartphone is a device used by food delivery drivers and has an application installed for entering delivery information.

[0429] The smartphone application receives the optimal delivery route from the server and displays it on the car navigation application.

[0430] 3. Car navigation applications:

[0431] The car navigation application runs on the smartphone and displays the optimal delivery route received from the server.

[0432] Drivers use this car navigation application to follow the optimal route when making deliveries.

[0433] Processing the data

[0434] The server processes the data in the following steps:

[0435] 1. Data Collection:

[0436] The server obtains the latest traffic information data from the traffic information API.

[0437] The server reads past delivery performance data from a local file.

[0438] The server receives the delivery package information for the day entered by the food delivery driver.

[0439] 2. Calculating the optimal route using AI models:

[0440] The server uses the collected data to calculate the optimal delivery route using a random forest regression model.

[0441] The model uses traffic information, past delivery performance data, and area characteristic data as features to shorten delivery times and improve efficiency.

[0442] 3. Optimal route distribution:

[0443] The server sends the calculated optimal route to the smartphone application.

[0444] The smartphone application displays the received optimal route on the car navigation application.

[0445] Specific examples

[0446] For example, let's say a driver enters the following delivery information:

[0447] Order 1: Address 1, delivery time 12:00

[0448] Order 2: Address 2, delivery time 12:30

[0449] The server obtains the latest traffic information from the traffic information API and calculates the optimal delivery route based on past delivery performance data. For example, if past data indicates that "Address 1 has less traffic congestion in the morning," the server will suggest a route that "deliver to Address 1 first, then head to Address 2."

[0450] Prompt Sentence Examples

[0451] Use the delivery information below to calculate the best delivery route.

[0452] Order 1: Address 1, delivery time 12:00

[0453] Order 2: Address 2, delivery time 12:30

[0454] Get the latest traffic information from the traffic information API and suggest the optimal route based on past delivery performance data.

[0455] In this way, by combining servers, smartphones, car navigation applications, and AI models, the possibility of redelivery can be reduced, and delivery times can be shortened and made more efficient.

[0456] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0457] Step 1:

[0458] The user (food delivery driver) uses a smartphone application to enter the day's delivery information (order details, delivery address, estimated delivery time, etc.).

[0459] Input: Delivery information (order details, delivery address, estimated delivery time)

[0460] Output: Delivery information sent to the server

[0461] Step 2:

[0462] The server obtains the latest traffic information data from the traffic information API.

[0463] Input: Request to traffic information API

[0464] Output: Traffic information data (road congestion, traffic accidents, construction information, etc.)

[0465] Step 3:

[0466] The server reads past delivery performance data from a local file.

[0467] Input: Local file (past delivery performance data)

[0468] Output: Past delivery performance data (resident absence time, redelivery history, etc.)

[0469] Step 4:

[0470] The server calculates the optimal delivery route using a random forest regression model based on the collected data (delivery information, traffic information data, and past delivery performance data).

[0471] Input: Delivery information, traffic information data, past delivery performance data

[0472] Output: Optimal delivery route (delivery sequence, estimated delivery time, etc.)

[0473] Specific operation: The server extracts features (traffic information, past delivery performance, area characteristics) and inputs them into a random forest regression model to predict the optimal delivery route.

[0474] Step 5:

[0475] The server sends the calculated optimal route to the smartphone application.

[0476] Input: Optimal delivery route

[0477] Output: Optimal route sent to smartphone application

[0478] Step 6:

[0479] The smartphone application displays the received optimal route on the car navigation application.

[0480] Input: Optimal delivery route

[0481] Output: Optimal route displayed in a car navigation application

[0482] Specific operation: The smartphone application analyzes the optimal route received from the server and converts it into a format for display in the car navigation application.

[0483] Step 7:

[0484] The user (food delivery driver) makes deliveries by following the optimal route displayed on the car navigation application.

[0485] Input: Optimal route displayed in a car navigation application

[0486] Output: Delivery execution

[0487] What happens: The driver follows the directions in the car navigation application to reach the delivery location and complete the delivery efficiently.

[0488] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0489] "Example 1"

[0490] One embodiment of the present invention provides a delivery route determination system incorporating an emotion engine. This system recognizes a user's emotions and optimizes delivery routes based on those emotions. Specifically, the system analyzes information obtained during interactions with the user, such as voice, text, facial expressions, and physical movements, and determines delivery routes based on the results. For example, if a user expresses anger or dissatisfaction, the system can prioritize deliveries to that user, thereby improving user satisfaction.

[0491] "Example 2"

[0492] In another embodiment of the present invention, a system is provided in which an emotion engine adjusts delivery time and delivery method. Specifically, the delivery time is advanced or delayed depending on the user's emotions. Furthermore, if the user shows joy or excitement, the system can devise a delivery method, such as delivering a gift as a surprise. This makes it possible to provide a service that corresponds to the user's emotions, further improving user satisfaction. "Embodiment 3"

[0493] Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine and an AI work in cooperation with each other. Specifically, the emotion engine recognizes the user's emotions and provides that information to the AI. The AI ​​optimizes delivery routes based on that information. For example, if a user expresses joy, the AI ​​prioritizes deliveries to that user. On the other hand, if a user expresses anger, the AI ​​delays deliveries to that user and prioritizes deliveries to other users. This makes it possible to optimize delivery routes in response to the user's emotions.

[0494] The processing flow of each embodiment will be described below.

[0495] "Example 1"

[0496] Step 1: The emotion engine collects information obtained during interaction with the user, such as voice, text, facial expressions, and physical movements.

[0497] Step 2: The emotion engine analyzes the collected information and recognizes the user's emotions.

[0498] Step 3: Based on the detected emotions, the AI ​​optimizes the delivery route.

[0499] "Example 2"

[0500] Step 1: The emotion engine collects information obtained during interaction with the user and recognizes the user's emotions.

[0501] Step 2: The emotion engine adjusts delivery time and method based on the recognized emotion.

[0502] Step 3: AI optimizes delivery routes based on adjusted delivery times and methods.

[0503] "Example 3"

[0504] Step 1: The emotion engine collects information obtained during interaction with the user and recognizes the user's emotions.

[0505] Step 2: Provide the AI ​​with the emotional information recognized by the emotion engine.

[0506] Step 3: Based on the provided emotional information, the AI ​​optimizes the delivery route.

[0507] Example 1

[0508] Next, a description will be given of 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."

[0509] Conventional delivery route planning systems can optimize delivery routes by taking into account traffic information and resident absence data, but they have not yet optimized delivery routes by taking into account user emotions. Therefore, there is a need for re-optimization of delivery routes to improve user satisfaction. Furthermore, a means to maintain delivery quality regardless of the experience of the delivery driver is also necessary.

[0510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0511] In this invention, the server includes: a means for determining a delivery route for the day using artificial intelligence to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, information on the delivery parcels for the day, electricity meter information, and route characteristic data from the perspective of area drivers; a means for linking the route determined by the artificial intelligence with the vehicle navigation system; a means for collecting emotional data such as voice, text, facial expressions, and physical movements through interactions with the user; and a means for analyzing the collected emotional data and re-optimizing the delivery route based on the results. This enables the optimization of delivery routes taking into account the user's emotions, improving user satisfaction. It also allows delivery levels to be maintained regardless of experience.

[0512] "Traffic information data" refers to information about traffic obtained in real time, such as road congestion, traffic accidents, and construction information.

[0513] "Resident absence / redelivery performance data" is information based on past delivery history, such as the time periods when residents were absent and the number of redeliveries made.

[0514] "Information about parcels to be delivered on the day" refers to detailed information such as the type, quantity, and delivery address of parcels to be delivered on the day.

[0515] "Electricity meter information" is data that indicates the electricity consumption status of residents, and is information obtained from smart meters and the like.

[0516] "Route characteristic data from the perspective of area drivers" is feedback information based on the driver's experience, such as road conditions within the delivery area and the characteristics of the delivery destination.

[0517] "Artificial intelligence" is a computer program that uses machine learning and data analysis to calculate optimal delivery routes.

[0518] A "vehicle navigation system" is an electronic device that is installed in a vehicle and provides route guidance to a destination.

[0519] "Interaction with the user" refers to communication with the user during delivery through voice, text, facial expressions, physical movements, etc.

[0520] "Emotion data" is information about emotions obtained from the user's voice, text, facial expressions, body movements, and the like.

[0521] "Emotion analysis" is the process of analyzing collected emotion data to identify a user's emotional state.

[0522] "Delivery route reoptimization" is the process of recalculating existing delivery routes and changing them to the optimal route based on the results of sentiment analysis.

[0523] This system uses traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers to determine delivery routes using artificial intelligence (AI) that reduce the possibility of daily redelivery. It also includes a function to re-optimize delivery routes by taking into account the user's emotions.

[0524] Hardware and software used

[0525] Hardware: Servers, terminals, sensors (electricity meters, cameras, etc.)

[0526] Software: AI models (TensorFlow, PyTorch, etc.), sentiment analysis engine, database management system (MySQL (registered trademark), PostgreSQL, etc.)

[0527] Data collection and processing

[0528] The server collects traffic information data, data on resident absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from Google Maps API, delivery management systems, smart meters, etc. The collected data is stored in a database such as MySQL or PostgreSQL.

[0529] The server uses an AI model based on the stored data to calculate the optimal delivery route. Specifically, it uses TensorFlow and PyTorch to build a route optimization model, taking into account the time residents are absent and past redelivery data to reduce the likelihood of redelivery.

[0530] The device collects emotional data through interactions with the user during delivery, using a voice assistant and camera to capture information such as voice, text, facial expressions, and physical movements.

[0531] The server analyzes the collected emotional data using an emotion analysis engine. Specifically, it uses OpenAI's (registered trademark) emotion analysis model to recognize the user's emotions and identify emotions such as anger or frustration.

[0532] The server re-optimizes delivery routes based on the results of emotion analysis. Specifically, if a user expresses anger or dissatisfaction, the server recalculates the route to prioritize deliveries to that user.

[0533] Specific examples

[0534] For example, when deciding on a delivery route for a certain day, the following steps are taken:

[0535] 1. The server collects traffic information data (e.g., Google Maps API), data on resident absences / redelivery attempts (e.g., past delivery history), information on the day's delivery packages (e.g., data from the delivery management system), electricity meter information (e.g., smart meter data), and route characteristics data from the perspective of area drivers (e.g., driver feedback).

[0536] 2. The server stores this data in a database and calculates the optimal delivery route using an AI model (e.g., a route optimization model using TensorFlow).

[0537] 3. The device collects user emotional data through interactions with the user during delivery (e.g., voice assistant or facial recognition via camera).

[0538] 4. The server uses an emotion analysis engine (e.g., OpenAI's emotion analysis model) to analyze the collected emotion data, and if the user shows anger or dissatisfaction, it recalculates the delivery route to prioritize deliveries to that user.

[0539] Prompt Sentence Examples

[0540] "Please create an AI model that determines the optimal delivery route based on traffic information data, data on residents' absence / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. Also, please add a function that recognizes the user's emotions and optimizes the delivery route according to those emotions."

[0541] In this way, specific embodiments of the system will be described while clarifying the roles of the server, terminal, and user.

[0542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0543] Step 1:

[0544] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[0545] Input: Traffic information from Google Maps API, resident absence / redelivery performance data from the delivery management system, delivery package information for the day, electricity meter information from smart meters, driver feedback.

[0546] Data processing: Integrate the information obtained from each data source and store it in a database.

[0547] Output: A consolidated dataset.

[0548] Specific operation: The server sends an API request to obtain traffic information, obtains data on absences and redelivery from the delivery management system, and obtains electricity meter information from the smart meter. This data is then integrated and stored in a database.

[0549] Step 2:

[0550] The server uses AI models based on the stored data to calculate the optimal delivery route.

[0551] Input: The integrated dataset.

[0552] Data Computing: Using TensorFlow and PyTorch, we build route optimization models that take into account resident absence times and historical redelivery data to reduce the likelihood of redelivery attempts.

[0553] Output: Optimal delivery route.

[0554] How it works: The server inputs the combined dataset into an AI model to calculate the optimal delivery route, and the results are sent to the vehicle's navigation system.

[0555] Step 3:

[0556] The terminal collects emotional data through interactions with the user during delivery.

[0557] Input: User interaction (voice, text, facial expressions, body movements).

[0558] Data processing: Perform voice recognition, text analysis, facial recognition, and motion analysis to extract emotional data.

[0559] Output: Extracted emotion data.

[0560] Specific behavior: The device uses a voice assistant or camera to collect the user's voice, text, facial expressions, and physical movements, and analyzes this data to extract emotional data.

[0561] Step 4:

[0562] The server analyzes the collected emotion data using an emotion analysis engine.

[0563] Input: Extracted emotion data.

[0564] Data Computing: Recognize user emotions using OpenAI's sentiment analysis model to identify feelings such as anger or frustration.

[0565] Output: The result of the sentiment analysis.

[0566] How it works: The server inputs emotional data into an emotion analysis engine to identify the user's emotional state. The analysis results are used to re-optimize delivery routes.

[0567] Step 5:

[0568] The server re-optimizes delivery routes based on the results of the sentiment analysis.

[0569] Input: Sentiment analysis results, optimal delivery route.

[0570] Data calculations: Recalculating existing delivery routes taking into account the results of sentiment analysis.

[0571] Output: Reoptimized delivery routes.

[0572] Specific operation: Based on the results of emotion analysis, if the user expresses anger or dissatisfaction, the server recalculates the route to prioritize deliveries to that user. The re-optimized route is sent to the vehicle's navigation system.

[0573] (Application example 1)

[0574] Next, a description will be given of Application Example 1 of Embodiment 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."

[0575] Conventional delivery route planning systems can take into account traffic information and data on absences and redelivery requests, but they do not optimize delivery routes with consideration for user emotions. This makes it difficult to improve user satisfaction, and there is a particular issue of being unable to respond appropriately to users who express dissatisfaction or anger. Furthermore, there is a need to maintain delivery standards without relying on the experience of the delivery driver.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0577] In this invention, the server includes a means for using traffic information data, data on resident absences / redelivery records, information on the delivery parcels for the day, electricity meter information, and route characteristics data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by the AI ​​with a car navigation system, a means for recognizing user emotions and optimizing the delivery route according to those emotions, and a means for analyzing information such as voice, text, facial expressions, and physical movements. This makes it possible to optimize delivery routes taking user emotions into account, thereby improving user satisfaction. It also makes it possible to maintain delivery standards regardless of the delivery driver's experience.

[0578] "Traffic information data" refers to information about traffic obtained in real time, such as road congestion, traffic accidents, and construction information.

[0579] "Resident absence / redelivery performance data" is historical information such as the time periods when residents were absent during past deliveries and the number of redeliveries made.

[0580] "Today's delivery package information" refers to detailed information such as the type, quantity, and delivery address of packages scheduled to be delivered on that day.

[0581] "Electricity meter information" is electricity meter power consumption data used to estimate whether residents are at home.

[0582] "Route characteristic data from the perspective of area drivers" refers to route characteristic information based on the driver's experience, such as road conditions within the delivery area and the characteristics of the delivery destination.

[0583] "AI" stands for artificial intelligence, a set of algorithms and systems that analyze data and determine optimal delivery routes.

[0584] A "car navigation system" is a navigation system installed in a vehicle that provides route guidance to a destination.

[0585] "User emotion" refers to the emotional state of a user using a delivery service, and is analyzed from voice, text, facial expressions, physical movements, etc.

[0586] "Information such as voice, text, facial expressions, and physical movements" refers to various data formats used to recognize a user's emotions.

[0587] The system for implementing this invention collects traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and uses AI to determine the optimal delivery route.It also includes a function to recognize user emotions and optimize the delivery route according to those emotions.

[0588] System configuration

[0589] Hardware

[0590] Server: Collects, analyzes, and stores data.

[0591] Smartphone: Used by delivery drivers and linked to car navigation systems.

[0592] Smart meter: An electricity meter that estimates whether a user is at home.

[0593] Camera: Used to recognize the user's facial expressions.

[0594] Microphone: Used to collect the user's voice.

[0595] software

[0596] Google Maps API: Collects real-time traffic information.

[0597] Firebase: Manages user absence / redelivery record data and delivery order information for the day.

[0598] Smart Meter API: Collects electricity meter information.

[0599] Google Cloud Speech-to-Text: Converts voice data into text.

[0600] Google Cloud Natural Language: Perform sentiment analysis on text data.

[0601] OpenCV: Facial expression analysis.

[0602] TensorFlow: Analyzes body movements.

[0603] Data collection and analysis

[0604] The server uses the Google Maps API to collect real-time traffic information, Firebase to manage the user's absence / redelivery record data and the delivery order information for the day, and a smart meter API to collect electricity meter information to estimate the user's presence / absence status.

[0605] Incorporating an emotion engine

[0606] The server converts voice data to text using Google Cloud Speech-to-Text, performs sentiment analysis on the text data using Google Cloud Natural Language, analyzes facial expressions using OpenCV, and analyzes body movements using TensorFlow.

[0607] Delivery route optimization

[0608] The server uses AI to determine the optimal delivery route based on the collected data. It also takes into account the user's emotions, prioritizing deliveries to users who express particular dissatisfaction or anger, thereby improving satisfaction.

[0609] Specific examples

[0610] For example, if a user orders food delivery and has had to redeliver many times in the past, the server will optimize the delivery route taking into account the user's home hours. Also, if a user shows anger or dissatisfaction, the server will prioritize deliveries for that user to improve satisfaction.

[0611] Prompt Sentence Examples

[0612] "When a user places an order for food delivery, please design a system that collects traffic information, past absence / re-delivery data, delivery order information for that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses AI to determine the optimal delivery route. Also, please add a function that incorporates an emotion engine to recognize the user's emotions and optimize the delivery route accordingly."

[0613] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0614] Step 1:

[0615] The server uses the Google Maps API to collect real-time traffic information. It receives current traffic conditions and road congestion information as input, and generates traffic information data necessary for optimizing delivery routes as output. Specifically, it sends API requests and analyzes the response data.

[0616] Step 2:

[0617] The server uses Firebase to manage the user's absence / redelivery record data and the delivery order information for the day. It obtains past delivery history and the order information for the day as input, and generates the user data necessary for optimizing delivery routes as output. Specifically, it executes database queries and extracts the necessary data.

[0618] Step 3:

[0619] The server uses the smart meter API to collect electricity meter information. As input, it obtains the user's electricity consumption data, and as output, it generates data to estimate the user's presence or absence. Specifically, it sends an API request and analyzes the response data.

[0620] Step 4:

[0621] The server converts the voice data into text using Google Cloud Speech-to-Text. It receives the user's voice data as input and generates text data as output. Specifically, it uploads the voice file to a cloud service and receives the converted text.

[0622] Step 5:

[0623] The server performs sentiment analysis on text data using Google Cloud Natural Language. It receives the converted text data as input and generates sentiment analysis results as output. Specifically, it sends the text data to a cloud service and receives a sentiment score.

[0624] Step 6:

[0625] The server analyzes facial expressions using OpenCV. It receives the user's facial image data as input and generates facial expression analysis results as output. Specifically, it applies an image processing algorithm to extract facial feature points.

[0626] Step 7:

[0627] The server analyzes physical movements using TensorFlow. It receives user movement data as input and generates movement analysis results as output. It applies a machine learning model to extract specific movement features.

[0628] Step 8:

[0629] The server uses AI to determine the optimal delivery route based on all collected data. Traffic information data, user data, electricity meter information, emotion analysis results, facial expression analysis results, and movement analysis results are taken as input, and the optimal delivery route is generated as output. The specific operation is to apply an AI algorithm to calculate the optimal route.

[0630] Step 9:

[0631] The server synchronizes the optimal delivery route with the car navigation system. As input, it acquires optimal route data and as output, it sends route information to the car navigation system. Specifically, it sends data to the car navigation system and starts route guidance.

[0632] Step 10:

[0633] The user makes the delivery according to the optimized delivery route through the smartphone used by the delivery driver. The input is route guidance from the car navigation system, and the output is a report that the delivery has been completed. The specific operation is to use the smartphone's navigation function to arrive at the delivery destination.

[0634] Example 2

[0635] Next, a description will be given of 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 will be referred to as a "terminal."

[0636] Conventional delivery systems have difficulty determining delivery routes taking into account traffic information and information on residents' absences, which increases the likelihood of redelivery. Furthermore, because delivery depends on the experience of the delivery driver, it is difficult for new drivers to deliver efficiently. Furthermore, it is not possible to provide services that respond to user emotions, making it difficult to improve user satisfaction.

[0637] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0638] In this invention, the server includes means for determining a delivery route for the day that reduces the possibility of daily redelivery using a generative AI model, utilizing traffic information data, resident absence / redelivery record data, information on the parcels delivered that day, electricity meter information, and route characteristic data from the perspective of area drivers, means for linking the route determined by the generative AI model with a car navigation system, means for analyzing user emotion data and adjusting delivery time and delivery method, and means for delivering a surprise gift according to the user's emotion. This reduces the possibility of redelivery, enables efficient delivery regardless of whether the driver is a veteran or a novice, and makes it possible to provide a service that responds to the user's emotion.

[0639] "Traffic information data" refers to information that influences the decision on delivery routes, such as traffic conditions, road congestion, and accident information.

[0640] "Resident absence / redelivery performance data" refers to historical information on the time periods when residents were absent during past deliveries and when redelivery was performed.

[0641] "Information about parcels to be delivered on the day" refers to detailed information about parcels scheduled for delivery on the day, such as the number and size of parcels, and delivery address.

[0642] "Electricity meter information" refers to electricity consumption data used to estimate whether residents at delivery destinations are at home.

[0643] "Route characteristics data from the perspective of area drivers" refers to route characteristics and points of caution based on the experience and knowledge of drivers in a specific area.

[0644] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to calculate optimal delivery routes.

[0645] "Car navigation" refers to a navigation system installed in a vehicle that provides map information and route guidance.

[0646] "User emotional data" refers to data that indicates the user's emotional state, and refers to information obtained from smartphone sensors or wearable devices.

[0647] An "emotion engine" refers to a system that analyzes user emotional data and adjusts delivery times and methods based on the results.

[0648] The "means for delivering a surprise gift" refers to a method or process for delivering a special gift in addition to regular delivery depending on the user's emotions.

[0649] MODE FOR CARRYING OUT THE INVENTION

[0650] This invention is a system that uses traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers to determine a delivery route using a generative AI model that reduces the possibility of daily redelivery.Furthermore, the system has the function of linking the route determined by the generative AI model with a car navigation system, analyzing user emotion data, and adjusting delivery time and delivery method.

[0651] Server Roles

[0652] The server first receives a delivery request from the user. This request includes the delivery address, desired delivery time, and any special instructions. Next, the server uses a generative AI model to calculate the optimal delivery route, taking into account traffic conditions and distance using map information services such as Google Maps API. The calculated route is then sent from the server to the car navigation system. The server then receives the user's emotional data and analyzes it using an emotion engine. Based on the analysis results, the server adjusts the delivery time and method, and adds a surprise gift if necessary.

[0653] Role of the terminal (car navigation system)

[0654] The terminal (car navigation system) receives the optimal route information sent from the server. Based on the received route information, the route is displayed on the car navigation system screen. The driver delivers the parcel along this route. The car navigation system updates the location information in real time and can also recalculate the route as needed.

[0655] User Roles

[0656] Users submit delivery requests to the system. The request can include the delivery address, desired delivery time, and any special instructions. The user's emotional data is also sent to the system. The emotion engine analyzes this data and adjusts the delivery time and method depending on the user's emotions. For example, if the user expresses joy or excitement, the system may deliver a gift as a surprise.

[0657] Specific examples

[0658] For example, if a user sends a delivery request to "1-1-1 Shibuya, Shibuya-ku, Tokyo," the server calculates the optimal route using the Google Maps API. The calculated route is sent from the server to the car navigation system and displayed on the screen. The driver then makes the delivery following this route.

[0659] For example, if a user requests delivery to "1-1-1 Shibuya, Shibuya-ku, Tokyo" and indicates "joy" as the emotion data, the emotion engine will analyze this data and speed up the delivery. It may also add a small gift as a surprise to the delivery.

[0660] Prompt Sentence Examples

[0661] "If a user requests delivery to 1-1-1 Shibuya, Shibuya-ku, Tokyo, and indicates happiness as emotion data, explain how to calculate the optimal delivery route, speed up the delivery time, and add a gift as a surprise."

[0662] In this way, the system provides the optimal delivery route and method based on the user's request and emotional data.

[0663] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0664] Program processing flow

[0665] Step 1: Receiving a delivery request

[0666] The server receives delivery requests from users, which include delivery addresses, desired delivery times, and any special instructions.

[0667] Input: Delivery request from user (address, desired delivery time, special instructions)

[0668] Output: Delivery request data

[0669] Specific operation: The server receives an HTTP request and extracts the necessary information from the request body.

[0670] Step 2: Calculate the optimal route

[0671] The server uses a generative AI model to calculate the optimal delivery route, taking into account traffic information, data on residents' absences / re-delivery requests, information on the parcels delivered that day, electricity meter information, and route characteristics from the perspective of area drivers.

[0672] Input: Delivery request data, traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, route characteristics data from the perspective of area drivers

[0673] Output: Optimal route information

[0674] Specific operation: The server sends a request to the Google Maps API, analyzes the returned data, and determines the optimal route.

[0675] Step 3: Submit route information

[0676] The server transmits the calculated optimum route information to the car navigation system.

[0677] Input: Optimal route information

[0678] Output: Send route information to car navigation system

[0679] Specific operation: The server sends route information to the car navigation system using WebSocket or HTTP POST request.

[0680] Step 4: View Routes

[0681] The terminal (car navigation system) receives the optimum route information sent from the server and displays the route on the car navigation system screen.

[0682] Input: Route information from the server

[0683] Output: Route displayed on the car navigation screen

[0684] Specific operation: The device uses the screen drawing API to display the route on a map.

[0685] Step 5: Real-time location updates

[0686] The device (car navigation system) updates location information in real time and recalculates the route as needed.

[0687] Input: GPS data

[0688] Output: Updated route information

[0689] What it does: The device acquires GPS data, sends it to the server, and requests new routes if necessary.

[0690] Step 6: Receiving and analyzing emotion data

[0691] The server receives the user's emotion data and analyzes it using an emotion engine.

[0692] Input: User emotion data

[0693] Output: Analysis results (user's emotional state)

[0694] Specific operation: The server calls the emotion analysis API and analyzes the user's emotion data.

[0695] Step 7: Adjust delivery method

[0696] The server adjusts the delivery time and method based on the analysis results. For example, if the user expresses joy, it may speed up the delivery or add a surprise gift.

[0697] Input: Analysis results (user's emotional state)

[0698] Output: Adjusted delivery schedule and delivery methods

[0699] Specific behavior: The server updates the delivery schedule and instructs the customer to add gifts as needed.

[0700] Step 8: Confirm delivery

[0701] After the delivery is completed, the user checks the delivery details and provides feedback.

[0702] Input: Delivery completion notification

[0703] Output: User feedback

[0704] Specific operation: The user receives a delivery completion notification on the smartphone app, checks the delivery details, and fills out and submits a feedback form.

[0705] (Application example 2)

[0706] Next, a description will be given of 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 will be referred to as a "terminal."

[0707] Conventional delivery systems can determine delivery routes by taking into account traffic information and data on resident absences, but they are unable to adjust delivery times and methods based on user emotions, making it difficult to fully improve user satisfaction. Furthermore, because delivery depends on the experience of the delivery driver, it is difficult to maintain a high level of delivery. Furthermore, they are unable to provide value-added services, such as delivering surprise gifts based on the user's emotions.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0709] In this invention, the server includes: a means for determining a delivery route for the day using AI to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, information on the delivery parcels for the day, electricity meter information, and route characteristics data from the perspective of area drivers; a means for linking the route determined by AI with a car navigation system; a means for detecting user emotion data and adjusting the delivery time and delivery method; and a means for delivering a surprise gift according to the user's emotion. This enables flexible adjustment of delivery time and method according to the user's emotion, thereby improving user satisfaction. It also enables a high level of delivery to be maintained regardless of the delivery driver's experience, and further enables the provision of value-added services to users.

[0710] "Traffic information data" refers to information about traffic that affects delivery routes, such as road congestion, traffic accidents, and construction information.

[0711] "Resident absence / redelivery performance data" refers to historical information on the time periods when residents were absent during past deliveries and when redelivery was performed.

[0712] "Today's delivery parcel information" is information about parcels scheduled to be delivered on that day, including the number and size of parcels, delivery address, etc.

[0713] "Electricity meter information" is data on residents' electricity usage and is used to infer whether residents are at home.

[0714] "Route characteristics data from the perspective of area drivers" refers to information on route characteristics and points of caution based on the experiences of drivers in a specific area.

[0715] "Method of deciding using AI" refers to a method of using artificial intelligence to determine the optimal delivery route.

[0716] "Means for linking with car navigation systems" refers to a method for displaying the determined delivery route on the in-car navigation system so that the driver can follow that route.

[0717] "User emotion data" is data for detecting the user's emotional state, and includes emotions such as joy, excitement, and sadness.

[0718] "Means for adjusting delivery time and delivery method" refers to methods for speeding up or delaying delivery time or changing delivery method based on user emotion data.

[0719] "Means for delivering a surprise gift" refers to a method for delivering an additional gift depending on the user's emotions.

[0720] A system for implementing this invention includes a means for using AI to determine a delivery route for the day that reduces the possibility of daily redelivery by utilizing traffic information data, data on resident absence / redelivery history, information on the parcels delivered on the day, electricity meter information, and route characteristic data from the perspective of area drivers, a means for linking the route determined by AI with a car navigation system, a means for detecting user emotion data and adjusting delivery time and delivery method, and a means for delivering a surprise gift according to the user's emotion.

[0721] System configuration

[0722] Hardware

[0723] Server: Processes data and runs AI models.

[0724] Smartphone: Used by the driver and linked to the car navigation system.

[0725] Emotion detection device: A device for collecting user emotion data (e.g., a smartphone camera or a wearable device).

[0726] software

[0727] AI Routing API: An API for determining the optimal delivery route.

[0728] Emotion Detection Library: A library for detecting user emotions.

[0729] Car navigation application: An application for displaying routes determined by AI.

[0730] Data processing and calculation

[0731] The server collects traffic information, data on residents' absences / re-delivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses this data to determine the optimal delivery route using an AI routing API. The determined route is sent to the driver's smartphone navigation application and displayed to them.

[0732] The user's emotional data is collected through the emotion detection device and analyzed using the emotion detection library. Based on the analysis results, the server adjusts the delivery time and delivery method and delivers the surprise gift as needed.

[0733] Specific examples

[0734] For example, if User A orders food delivery, the server determines the optimal delivery route based on traffic information and resident absence data, and displays it on the driver's smartphone. If User A's emotion is detected as "happy," the server instructs the driver to deliver an additional surprise gift.

[0735] Prompt Sentence Examples

[0736] "Develop a food delivery application that adjusts delivery time and method based on the user's emotions. Use AI to determine the optimal delivery route and an emotion engine to adjust delivery based on the user's emotions. For example, if the user expresses joy or excitement, deliver a surprise gift."

[0737] In this way, it becomes possible to flexibly adjust delivery times and methods according to the user's emotions, improving user satisfaction. It also makes it possible to maintain a high level of delivery without relying on the delivery driver's experience, and to provide value-added services to users.

[0738] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0739] Step 1:

[0740] The server collects traffic information data, data on resident absence / redelivery records, information on the delivery package for the day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from various sensors and databases. Input data includes traffic information, resident absence data, delivery package information, electricity meter information, and route characteristics data. Based on this data, the server preprocesses the data and converts it into a format for input into the AI ​​model.

[0741] Step 2:

[0742] The server sends the preprocessed data to the AI ​​routing API to determine the optimal delivery route. The AI ​​routing API calculates the optimal route based on the input data and returns the results to the server. The output data includes optimal delivery route information. The server receives this route information and proceeds to the next step.

[0743] Step 3:

[0744] The server sends the determined optimal delivery route information to the driver's smartphone. The smartphone's car navigation application receives this route information and displays it to the driver. The optimal delivery route information is included as input data, and the route information to be displayed on the smartphone's car navigation screen is included as output data. The driver then starts driving along this route.

[0745] Step 4:

[0746] A user collects emotion data using an emotion detection device (e.g., a smartphone camera or a wearable device). The emotion detection device analyzes the user's facial expressions, voice, etc., and generates emotion data. The input data includes the user's facial expressions and voice data, and the emotion data is generated as output data.

[0747] Step 5:

[0748] The server sends the user's emotional data to the emotion detection library, which analyzes the user's emotional state. The emotion detection library determines the user's emotion based on the input data and returns the result to the server. The output data includes the user's emotional state (e.g., happy, neutral, sad). The server receives this emotional state and proceeds to the next step.

[0749] Step 6:

[0750] The server adjusts the delivery time and delivery method based on the user's emotional state. For example, if the user is determined to be "happy," the server instructs the delivery time to be earlier or to add a surprise gift. The input data includes the user's emotional state, and the output data includes the adjusted delivery time and delivery method.

[0751] Step 7:

[0752] The server sends the adjusted delivery time and delivery method to the driver's smartphone. The smartphone's car navigation application receives this information and displays it to the driver. The input data includes the adjusted delivery time and delivery method, and the output data includes the information to be displayed on the smartphone's car navigation screen. The driver then makes the delivery according to this information.

[0753] The above steps enable flexible adjustment of delivery times and methods according to the user's emotions, improving user satisfaction. It also enables a high level of delivery to be maintained without relying on the delivery driver's experience, and provides value-added services to users.

[0754] Example 3

[0755] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0756] Conventional delivery systems often required redelivery, making it difficult to determine efficient delivery routes. Furthermore, because delivery relied on the driver's experience and skill, it was difficult to maintain a consistent level of delivery. Furthermore, delivery efficiency often declined because real-time traffic information and information on resident absences were not effectively utilized. To solve these issues, a system utilizing more advanced data analysis and AI technology was needed.

[0757] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0758] In this invention, the server includes means for determining a delivery route for the day that reduces the possibility of daily redelivery using a generative AI model, utilizing traffic information data, resident absence / redelivery record data, information on parcels delivered that day, electricity meter information, and route characteristic data from the perspective of area drivers, means for linking the route determined by the generative AI model with a navigation system, means for the user to input delivery information, and means for the server to collect and integrate additional data. This makes it possible to determine an efficient delivery route while reducing the possibility of redelivery and maintaining delivery standards.

[0759] "Traffic information data" refers to data that includes real-time traffic conditions, road congestion, accident information, and so on.

[0760] "Resident absence / redelivery performance data" is data that includes historical information such as the number of times a resident was absent during past deliveries and the number of times redelivery was performed.

[0761] "Today's delivery parcel information" is data including information such as the type and quantity of parcels scheduled to be delivered on that day, and the delivery address.

[0762] "Electricity meter information" is data that indicates the electricity usage status of each resident and is used to infer whether the resident is at home or not.

[0763] "Route characteristics data from the perspective of area drivers" is data that shows the characteristics and points to note of delivery routes in a specific area based on past delivery history and driver experience.

[0764] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence techniques to calculate the optimal delivery route based on input data.

[0765] A "navigation system" is a system that provides route guidance to drivers, such as a car navigation device installed in a vehicle or a smartphone app.

[0766] "Means for users to input delivery information" refers to the interface or application that drivers use on smartphones or tablet devices to input delivery package information and data on residents' absence / redelivery status.

[0767] "Means for the server to collect and integrate additional data" refers to the function by which the server collects traffic information, electricity meter information, etc. from external data sources, integrates them, and processes them to input them into the AI ​​model.

[0768] This invention is a system for maximizing delivery driver efficiency and reducing the likelihood of redelivery. The system utilizes traffic information data, data on resident absences / redelivery attempts, information on the day's delivery packages, electricity meter information, and route characteristics data from the area driver's perspective, and uses a generative AI model to determine the optimal delivery route.

[0769] The server first receives the delivery package information for the day entered by the user (driver) and the actual data on absences and redelivery requests. Next, the server collects traffic information, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from map service APIs (e.g., Google Maps API), the electric power company's smart meter database, and past route history databases.

[0770] The server combines this data and inputs it into a generative AI model, built using machine learning frameworks such as TensorFlow and PyTorch, which uses historical data and real-time information to calculate the optimal route to reduce the chance of redelivery.

[0771] The calculated optimal route is sent to the navigation system and displayed on the driver's device. The driver then delivers the parcel by following the route displayed on the navigation system. This reduces the possibility of redelivery and enables the delivery level to be maintained.

[0772] As a specific example, a driver in charge of deliveries in a certain area enters "Parcel A, Parcel B, Parcel C" into the system as parcel information for that day's delivery. Additionally, as resident absence / redelivery history data, the driver enters information such as "Resident X has been absent three times in the past, and Resident Y has been redelivered once in the past." The system uses this information, traffic information data obtained from the map service API, electricity meter information obtained from the power company, and past route history data to determine the optimal delivery route using a generative AI model.

[0773] Examples of prompts to input to a generative AI model might include:

[0774] "Delivery package information: Package A, Package B, Package C. Resident absence / redelivery performance data: Resident X was absent three times in the past, and resident Y has had one redelivery in the past. Please calculate the optimal delivery route based on traffic information data, electricity meter information, and route characteristics data from the perspective of area drivers."

[0775] Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine and a generative AI model work in cooperation with each other. Specifically, the emotion engine recognizes a user's emotions and provides that information to the generative AI model. The generative AI model optimizes delivery routes based on that information. For example, if a user expresses joy, the generative AI model prioritizes deliveries to that user. On the other hand, if a user expresses anger, the generative AI model delays deliveries to that user and prioritizes deliveries to other users. This makes it possible to optimize delivery routes in response to user emotions.

[0776] In this way, the present invention provides a system that utilizes advanced data analysis and AI technology to maximize delivery efficiency and reduce the possibility of redelivery. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[0777] Step 1:

[0778] The user (driver) uses a smartphone or tablet device to enter the delivery package information for the day and the resident's absence / re-delivery record data into a dedicated application. For example, enter "Package A, Package B, Package C" into the application's input form and select information such as "Resident X has been absent three times in the past, and Resident Y has been redelivered once in the past." The entered data is sent to the server.

[0779] Step 2:

[0780] The server receives delivery package information and data on resident absences / redelivery attempts sent by users. Next, the server collects traffic information data, electricity meter information, and route characteristics data from the perspective of area drivers. Specifically, the server calls the map service API to obtain real-time traffic information and accesses the power company's smart meter database to obtain electricity meter information. It also collects route characteristics data from the perspective of area drivers from a database of past route history. This data is integrated within the server.

[0781] Step 3:

[0782] The server preprocesses the integrated data and converts it into a format that can be input to the generative AI model. For example, it converts the data into JSON format and inputs it into the generative AI model. Specifically, it generates JSON data like the following:

[0783] json

[0784] {

[0785] "deliveries": ["Delivery A", "Delivery B", "Delivery C"],

[0786] "absence_data": {"Resident X": 3, "Resident Y": 1},

[0787] "traffic_data": {...},

[0788] "meter_data": {...},

[0789] "route_features": {...}

[0790] }

[0791] This data is fed into a generative AI model.

[0792] Step 4:

[0793] The server inputs the integrated data into a generative AI model to calculate the optimal delivery route. The generative AI model calculates the optimal route that reduces the possibility of redelivery based on past data and real-time information. For example, it generates a route such as "Route 1: Package A -> Package B -> Package C." The calculation results are stored on the server.

[0794] Step 5:

[0795] The server sends the calculated optimal delivery route to the navigation system. Specifically, it uses the navigation system's API to send the route information and display it on the driver's device. For example, the navigation system might display information such as "Route 1: Package A -> Package B -> Package C."

[0796] Step 6:

[0797] The user (driver) delivers by following the optimal delivery route displayed on the navigation system. For example, following the instructions of the navigation system, deliveries are made in the order of "delivering package A first, then package B, and finally package C." This reduces the possibility of redelivery and makes it possible to maintain the delivery level.

[0798] (Application example 3)

[0799] Next, a description will be given of 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 will be referred to as a "terminal."

[0800] In conventional delivery systems, the possibility of redelivery was high, making it difficult to determine efficient delivery routes. Furthermore, delivery routes were not optimized taking into account user emotions, making it difficult to improve user satisfaction. In particular, in food delivery, delivery delays and redeliveries have a significant impact on customer satisfaction, so these issues must be resolved.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0802] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by the AI ​​with a car navigation system, means for an emotion engine to recognize user emotions and provide that information to the AI, means for optimizing the delivery route according to the user's emotions, and means for displaying the optimized delivery route on a smartphone navigation app.This reduces the possibility of redelivery and makes it possible to optimize the delivery route according to the user's emotions.

[0803] "Traffic information data" refers to information about traffic that affects delivery routes, such as road congestion, traffic accidents, and construction information.

[0804] "Resident absence / redelivery performance data" is a record of past deliveries during which residents were absent and redeliveries were made.

[0805] "Today's delivery parcel information" is detailed information about parcels to be delivered on that day, including the delivery address, delivery time slot, and type of parcel.

[0806] "Electricity meter information" is data that indicates the usage status of the electricity meter at each delivery destination, and is information that is used to estimate whether residents are at home.

[0807] "Route characteristics data from the perspective of area drivers" is information on route characteristics, points to note, and efficient delivery methods as shared by drivers who are familiar with the delivery area.

[0808] "AI" stands for artificial intelligence, an algorithm or system that calculates optimal delivery routes based on data.

[0809] A "car navigation system" is a navigation system installed in a vehicle that guides the driver to the optimal route.

[0810] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's behavior based on that information.

[0811] A "smartphone navigation app" is a navigation application that runs on a smartphone and is software that displays the optimal route for the user.

[0812] The following system configuration and processing procedure will be described as an embodiment of the present invention.

[0813] System Configuration

[0814] This system is configured using the following hardware and software.

[0815] Hardware

[0816] server

[0817] Smartphone

[0818] Car navigation system installed in a vehicle

[0819] software

[0820] AI libraries (e.g. RouteOptimizer)

[0821] Emotion engine (e.g., EmotionEngine)

[0822] Smartphone navigation app

[0823] Processing steps

[0824] 1. Enter delivery information

[0825] Using a terminal (smartphone), the delivery driver inputs information about the parcel to be delivered that day, including the delivery address, delivery time slot, and type of parcel.

[0826] 2. Obtaining traffic information

[0827] The server retrieves the latest traffic data from the traffic information API, including road congestion, traffic accidents, and construction information.

[0828] 3. Obtaining electricity meter information

[0829] The server obtains electricity meter information for each delivery destination and uses this information to estimate whether residents are at home.

[0830] 4. Delivery route optimization

[0831] The server uses an AI library (Route Optimizer) to calculate the optimal delivery route based on delivery information, traffic information, electricity meter information, data on residents' absence / redelivery history, and route characteristics data from the perspective of area drivers.

[0832] 5. Use of Emotion Engine

[0833] The server uses an emotion engine to recognize the user's emotions, which then provides the AI ​​with information on the user's emotions and is reflected in optimizing delivery routes.

[0834] 6. View optimized route

[0835] The optimized delivery route is displayed on the smartphone navigation app, and the driver follows this route to make the delivery.

[0836] Specific examples

[0837] For example, suppose one of the delivery destinations is "Address 1," and past data indicates that the resident is often out in the morning. Based on this information, the AI ​​will include "Address 1" in the afternoon delivery route. If the emotion engine also recognizes that the resident of "Address 2" is happy, the AI ​​will prioritize "Address 2" in the delivery route.

[0838] Prompt Sentence Examples

[0839] "Generate optimal delivery routes taking into account the emotions of residents in the delivery destination. Adjust the route based on the user's emotions based on delivery information, traffic information, and electricity meter information."

[0840] The above is an embodiment of the present invention. This system reduces the possibility of redelivery and enables optimization of delivery routes according to the user's emotions.

[0841] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0842] Step 1:

[0843] Using a terminal (smartphone), the delivery driver inputs information about the parcels to be delivered that day. The input information includes the delivery address, delivery time slot, and type of parcel. This information is sent to the server and stored in a database.

[0844] Step 2:

[0845] The server obtains the latest traffic data from the traffic information API. The obtained data includes road congestion, traffic accidents, construction information, etc. The server analyzes this data and extracts factors that affect delivery routes.

[0846] Step 3:

[0847] The server obtains electricity meter information for each delivery destination. Using the electricity meter information API, it obtains electricity usage information for each address and estimates whether residents are at home. This information is also stored in the database.

[0848] Step 4:

[0849] The server retrieves data on resident absences and redelivery attempts from the database, and analyzes each resident's absence time and redelivery frequency based on past delivery data.

[0850] Step 5:

[0851] The server acquires route characteristic data from the perspective of area drivers. This is information on route characteristics, points to note, and efficient delivery methods from drivers who are familiar with the delivery area.

[0852] Step 6:

[0853] The server uses an AI library (RouteOptimizer) to calculate the optimal delivery route based on delivery information, traffic information, electricity meter information, data on residents' absences / re-deliveries, and route characteristics data from the perspective of area drivers. The AI ​​receives this data as input and outputs the optimal route to reduce the possibility of re-delivery.

[0854] Step 7:

[0855] The server uses an emotion engine to recognize the user's emotions. The emotion engine provides the AI ​​with the user's emotional information and reflects it in optimizing delivery routes. For example, if a user is happy, delivery to that user will be prioritized.

[0856] Step 8:

[0857] The server sends the optimized delivery route to the smartphone's navigation app, which the driver uses to make the delivery along the optimized route. The navigation app provides real-time route guidance to support the driver.

[0858] These are the specific processing steps of this system, which reduces the possibility of redelivery and enables delivery routes to be optimized according to the user's emotions.

[0859] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0860] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0861] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0862] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0863] [Second embodiment]

[0864] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0865] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0866] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0867] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0868] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0869] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0870] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0871] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0872] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0873] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0874] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0875] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0876] "Example 1"

[0877] One aspect of the present invention is a delivery route determination system. This system collects traffic information data, data on resident absences / redelivery attempts, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and AI determines the optimal delivery route based on this data. Specifically, the AI ​​determines the delivery route taking into account resident absence times and redelivery attempt history data in order to reduce the possibility of redelivery.

[0878] "Example 2"

[0879] Furthermore, the route determined by AI is displayed in conjunction with the car navigation system. This allows the driver to make deliveries by following the optimal route determined by AI. Specifically, the route determined by AI is displayed on the car navigation screen, and the driver delivers by following that route. This makes it possible to maintain delivery standards regardless of whether the driver is a veteran or a novice.

[0880] "Example 3"

[0881] As a concrete example, a driver in charge of deliveries in a certain area inputs information about the day's deliveries and data on residents' absences / re-deliveries into the system. The system uses this information, traffic information data, electricity meter information, and route characteristics data from the area driver's perspective to determine the optimal delivery route using AI. This route is displayed on the car navigation system, and the driver follows it to make the delivery. This reduces the possibility of re-delivery and makes it possible to maintain delivery standards.

[0882] The processing flow of each embodiment will be described below.

[0883] "Example 1"

[0884] Step 1: The delivery route determination system collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[0885] Step 2: Based on the collected data, the AI ​​determines the optimal delivery route. Specifically, to reduce the possibility of redelivery, the AI ​​determines the delivery route by taking into account the time when residents are absent and past redelivery data.

[0886] "Example 2"

[0887] Step 1: The route determined by the AI ​​is displayed in conjunction with the car navigation system.

[0888] Step 2: The driver follows the instructions on the car navigation system to make the delivery. This allows the delivery level to be maintained regardless of whether the driver is a veteran or a novice.

[0889] "Example 3"

[0890] Step 1: A driver in charge of deliveries in a certain area enters the delivery package information for the day and the actual data on residents' absence / re-delivery into the system.

[0891] Step 2: The system uses this information, traffic data, electricity meter information, and route characteristics data from the perspective of area drivers to determine the optimal delivery route using AI.

[0892] Step 3: This route is displayed on the car navigation system and the driver follows it to make the delivery, reducing the chance of redelivery and maintaining delivery levels.

[0893] Example 1

[0894] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[0895] Conventional delivery route determination systems had a high probability of redelivery, making efficient delivery difficult. Furthermore, they were unable to determine the optimal route taking into account traffic information and whether residents were at home, resulting in poor delivery efficiency. Another issue was the discrepancy in delivery quality between veteran and novice drivers.

[0896] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0897] In this invention, the server includes means for collecting traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers, means for preprocessing the collected data, means for training a machine learning model based on the preprocessed data, means for receiving delivery requests from users, means for calculating an optimal delivery route using the trained machine learning model, means for transmitting the calculated optimal route to a terminal, and means for displaying the route information received by the terminal to the user. This reduces the possibility of redelivery and enables efficient delivery route determination. It also allows for the maintenance of delivery quality between veteran and novice drivers.

[0898] "Traffic information data" refers to data that indicates real-time traffic conditions and road congestion.

[0899] "Resident absence / redelivery performance data" is data that indicates the time when residents were absent during past deliveries and the history of redeliveries.

[0900] "Today's delivery parcel information" is data showing detailed information about parcels to be delivered on the same day.

[0901] "Electricity meter information" is data on electricity usage that is used to estimate whether residents are at home.

[0902] "Route characteristics data from the perspective of area drivers" is data on route characteristics based on feedback from drivers.

[0903] "Means of collection" refers to the methods and devices used to obtain the required data.

[0904] "Preprocessing means" refers to methods or devices used to convert collected data into a form suitable for analysis or model training.

[0905] "Means for training a machine learning model" refers to a method or apparatus for training a machine learning algorithm using collected and pre-processed data.

[0906] "Means for receiving a delivery request" refers to a method or device for receiving a delivery request from a user.

[0907] "Means for calculating optimal delivery routes" refers to a method or apparatus for using a trained machine learning model to calculate the most efficient delivery route.

[0908] "Means for transmitting to the terminal" refers to a method or device for transmitting the calculated delivery route to the user's terminal.

[0909] The term "means for displaying the route information received by the terminal to the user" refers to a method or device for visually presenting the delivery route information received by the terminal to the user.

[0910] This invention relates to a delivery route determination system that determines the optimal delivery route by utilizing traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristic data from the perspective of area drivers.

[0911] Generating a Program

[0912] The system's programs are generated using Python, with key libraries including requests for data collection, pandas for data processing, and scikit-learn and TensorFlow for building machine learning models.

[0913] Program processing explanation

[0914] The server collects the following data:

[0915] Traffic data: Use common map APIs to get real-time traffic information.

[0916] Resident absence / redelivery performance data: Obtain past delivery performance data from the delivery company database.

[0917] Today's delivery package information: Obtain today's delivery list from the delivery management system.

[0918] Electricity meter information: Use the smart meter API to obtain electricity usage data to infer whether residents are at home.

[0919] Route characteristics data from the perspective of area drivers: Feedback from drivers is collected and route characteristics are stored in a database.

[0920] After collecting this data, the server uses pandas to preprocess the data, specifically by filling in missing values ​​and normalizing the data.

[0921] The server then uses scikit-learn and TensorFlow to build a machine learning model that optimizes delivery routes by taking into account the time residents are away and past redelivery attempts to reduce the likelihood of redelivery.

[0922] After the model is trained, the server calculates the optimal delivery route and sends it to the device each time a new delivery request comes in.

[0923] Examples and prompts

[0924] As a concrete example, consider the following scenario:

[0925] The user inputs a new delivery request into the system. For example, the user might input "Make 10 deliveries within Tokyo on October 10, 2023." Based on this information, the server calculates the optimal delivery route and sends it to the device.

[0926] Example prompts to input to a generative AI model:

[0927] "I plan to make 10 deliveries within Tokyo on October 10, 2023. Please calculate the optimal delivery route taking into account traffic information data, data on residents' absence / redelivery attempts, information on the delivery packages for that day, electricity meter information, and route characteristics data from the perspective of area drivers."

[0928] By inputting this prompt into the generative AI model, the AI ​​will calculate the optimal delivery route and provide it to the user.

[0929] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0930] Step 1:

[0931] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[0932] Input: Traffic information API, delivery company database, delivery management system, smart meter API, driver feedback

[0933] Output: Various collected data

[0934] Specific operation: The server calls the traffic information API to obtain real-time traffic information, obtains past delivery performance data from the delivery company's database, obtains the delivery list for the day from the delivery management system, obtains electricity usage data using the smart meter API, and collects feedback from drivers and stores it in the database.

[0935] Step 2:

[0936] The server pre-processes the collected data.

[0937] Input: Various collected data

[0938] Output: Preprocessed data

[0939] What it does: The server uses the pandas library to impute missing values ​​in the data, normalize data of different scales, and combine data from different sources into a single data frame.

[0940] Step 3:

[0941] The server trains a machine learning model based on the preprocessed data.

[0942] Input: Preprocessed data

[0943] Output: A trained machine learning model

[0944] Specific operation: The server builds a machine learning model using scikit-learn or TensorFlow, selects features, and chooses the optimal algorithm (e.g., random forest, neural network) to train the model.

[0945] Step 4:

[0946] A user enters a new delivery request into the system.

[0947] Input: Delivery request (e.g., "Make 10 deliveries in Tokyo on October 10, 2023")

[0948] Output: Delivery request data

[0949] Specific operation: The user inputs a delivery request into the system interface. The server receives this request and stores it in the database.

[0950] Step 5:

[0951] The server uses a trained machine learning model to calculate the optimal delivery route.

[0952] Input: Delivery request data, trained machine learning model

[0953] Output: Optimal delivery route

[0954] What it does: The server converts delivery request data into a format that can be fed into the model, and then uses a trained machine learning model to predict the optimal delivery route.

[0955] Step 6:

[0956] The server transmits the calculated optimum route to the terminal.

[0957] Input: Optimal delivery route

[0958] Output: Route information sent to the device

[0959] Specific operation: The server calls an API to send the calculated optimal route to the terminal, and sends the route information to the terminal.

[0960] Step 7:

[0961] The terminal displays the received route information to the user.

[0962] Input: Route information sent to the device

[0963] Output: Route information displayed to the user

[0964] Specific operation: The terminal provides an interface for visually displaying the received route information to the user.

[0965] (Application example 1)

[0966] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[0967] Conventional delivery systems were unable to fully utilize traffic information and data on residents' absence, resulting in frequent redelivery. Furthermore, delivery routes were not optimized sufficiently, making it difficult to predict delivery times. This resulted in issues such as reduced delivery efficiency and lower customer satisfaction.

[0968] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0969] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by AI with a car navigation system, means for optimizing the delivery route using an application installed on a smartphone, and means for predicting delivery times that reflect real-time traffic information. This makes it possible to reduce the frequency of redelivery and improve delivery efficiency.

[0970] "Traffic information data" refers to information about traffic collected in real time, such as road congestion, traffic accidents, and construction information.

[0971] "Resident absence / redelivery record data" is data that indicates the time periods when a particular resident was absent in the past and the history of redelivery requests.

[0972] "Today's delivery parcel information" is detailed information about parcels scheduled to be delivered on that day, and is data including the type of parcel, the quantity, the delivery address, and so on.

[0973] "Electricity meter information" is data that indicates the electricity usage status of residents and is used to infer whether residents are at home or not.

[0974] "Route characteristics data from the perspective of area drivers" is data that shows the route characteristics and points of caution that drivers in charge of a specific area have empirically recognized.

[0975] "Method of deciding using AI" is a method of determining the optimal delivery route using artificial intelligence.

[0976] "Means for linking with car navigation" refers to a method for linking the determined delivery route with the in-car navigation system.

[0977] The "application installed on a smartphone" is software that runs on a smartphone and is used to optimize delivery routes and predict delivery times.

[0978] "Means for predicting delivery time by reflecting real-time traffic information" refers to a method for predicting the time required for delivery by taking into account current traffic conditions.

[0979] The following system configuration will be described as an embodiment of the present invention.

[0980] System Configuration

[0981] The system consists of a server, smartphone, car navigation system, and various data sources. The server collects traffic information data, data on absences and redelivery requests, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. Based on this data, AI determines the optimal delivery route.

[0982] Hardware and software used

[0983] Hardware: Servers, smartphones, car navigation systems

[0984] Software: Python, Pandas (data processing), Scikit-learn (machine learning), Geopy (geographic information processing)

[0985] Data processing and calculation

[0986] The server processes the data in the following steps:

[0987] 1. Loading data: Traffic information, data on resident absences / redelivery attempts, information on the day's deliveries, electricity meter information, and route characteristics data from the perspective of area drivers are loaded from a CSV file.

[0988] 2. Data preprocessing: Combining data and handling missing values.

[0989] 3. Setting features and targets: Set delivery time as the target variable and other data as features.

[0990] 4. Train the model: Train the model using RandomForestRegressor.

[0991] 5. Delivery Route Optimization: Determine the optimal delivery route using geodesic distance.

[0992] 6. Delivery Route Prediction: Predict delivery times based on optimal delivery routes.

[0993] Specific examples

[0994] For example, if there are multiple delivery destinations in Tokyo, the server will determine the optimal route and predict delivery times, taking into account traffic information and data on resident absences, thereby reducing the frequency of redelivery and improving delivery efficiency.

[0995] Prompt Sentence Examples

[0996] "If there are multiple delivery destinations in Tokyo, create a Python program that determines the optimal route and predicts delivery times, taking into account traffic information and resident absence data."

[0997] The above is an embodiment of the present invention. This system makes it possible to reduce the frequency of redelivery and improve delivery efficiency.

[0998] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0999] Step 1:

[1000] The server reads traffic information data, data on resident absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers from CSV files. This provides all the data necessary to optimize delivery routes. The inputs are various data files, and the output is an integrated dataset.

[1001] Step 2:

[1002] The server preprocesses the loaded data. Specifically, it combines the data and handles missing values. For example, traffic information data and resident absence data are combined using addresses as keys, and missing values ​​are imputed with the mean or median. The input is the combined dataset, and the output is the preprocessed dataset.

[1003] Step 3:

[1004] The server sets features and target variables from the preprocessed dataset. The features are factors that affect delivery time (e.g., traffic information, time when residents are out, electricity meter information, etc.), and the target variable is the delivery time. The input is the preprocessed dataset, and the output is a set of features and target variables.

[1005] Step 4:

[1006] The server trains a machine learning model (RandomForestRegressor) using the features and target variables. It fits the model using the training data and generates a model for predicting delivery times. The input is a set of features and target variables, and the output is the trained machine learning model.

[1007] Step 5:

[1008] The server determines the optimal delivery route using geodesic distance. Specifically, it optimizes the route by choosing the closest delivery point from the current location, and then choosing the next closest delivery point from that point. The input is a list of delivery points, and the output is the optimized delivery route.

[1009] Step 6:

[1010] The server uses a trained machine learning model to predict delivery times based on the optimized delivery route, with the input being the optimized delivery route and the output being the predicted delivery time at each destination.

[1011] Step 7:

[1012] The server sends the optimized delivery route and predicted delivery time to an application installed on the smartphone, allowing the driver to check the optimal delivery route and predicted delivery time in real time. The input is the optimized delivery route and predicted delivery time, and the output is data sent to the smartphone application.

[1013] Step 8:

[1014] The user (driver) uses a smartphone application to deliver packages according to an optimized delivery route. The application reflects real-time traffic information and recalculates the route as necessary. The input is data sent from the server, and the output is the actual delivery operation.

[1015] Example 2

[1016] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1017] With conventional delivery systems, there was a high chance of redelivery, making it difficult to determine efficient delivery routes. It was also difficult to maintain a consistent delivery level, regardless of whether the driver was a veteran or a novice. Furthermore, it was not possible to provide optimal routes that took into account real-time traffic and weather information. This resulted in poor delivery efficiency and lower customer satisfaction.

[1018] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1019] In this invention, the server includes: a means for determining a delivery route using artificial intelligence to reduce the likelihood of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, delivery package information for the day, electricity meter information, and route characteristics data from the perspective of area drivers; a means for linking the route determined by artificial intelligence with a navigation system; a means for receiving a list of delivery addresses and acquiring location information for each address using a geographic information system; a means for acquiring weather information and collecting traffic data; a means for preprocessing the acquired data and inputting it into a generative AI model to calculate the optimal delivery route; and a means for transmitting the generated optimal route to the navigation system and displaying it. This reduces the likelihood of redelivery and provides efficient delivery routes. It also maintains a consistent delivery level regardless of whether the driver is a veteran or a novice. Furthermore, it is possible to provide optimal routes that take real-time traffic and weather information into account, improving delivery efficiency and customer satisfaction.

[1020] "Traffic information data" refers to information relating to traffic flow, such as road congestion, accident information, and road closure information.

[1021] "Resident absence / redelivery performance data" refers to historical information such as the time periods when residents were absent during past deliveries and the number of redeliveries made.

[1022] "Same-day delivery parcel information" refers to detailed information such as the quantity, size, weight, and delivery address of parcels to be delivered on the same day.

[1023] "Electricity meter information" is data that indicates the electricity usage status of the residence or building where delivery is made, and is used to estimate whether residents are at home.

[1024] "Route characteristics data from the perspective of area drivers" refers to information that shows route characteristics and points of caution based on the experience and knowledge of drivers in a specific area.

[1025] "Artificial intelligence" refers to algorithms and models that use machine learning and data analysis to calculate optimal delivery routes.

[1026] "Navigation system" refers to a device installed in a vehicle that provides map information and route guidance functions.

[1027] "Geographic information system" refers to a system for collecting, managing, and analyzing geographic data.

[1028] "Generative AI models" refer to algorithms or models built using machine learning frameworks to generate optimal delivery routes.

[1029] "Preprocessing" refers to the process of converting collected data into the format required to input it into a generative AI model.

[1030] The present invention relates to a system for calculating and displaying efficient routes in delivery work. A specific embodiment of this system will be described below.

[1031] System Overview

[1032] This system consists of three main components: a server, a terminal, and a user. The server collects data, preprocesses it, and calculates routes using a generative AI model. The terminal functions as a car navigation system, displaying the optimal route sent from the server. The user inputs a list of delivery addresses and makes deliveries according to the system's instructions.

[1033] Hardware and software used

[1034] Server: Use a server with high-performance computing power. Specifically, you can use cloud services such as Google Cloud Platform or Amazon Web Services.

[1035] Terminal: Use a general navigation device (e.g., Garmin or TomTom) as a car navigation system.

[1036] Software: Google Maps API, OpenWeatherMap API, Waze API, etc. are used for data collection. Machine learning frameworks such as TensorFlow and PyTorch are used for building generative AI models.

[1037] Data collection and preprocessing

[1038] The server receives a list of delivery addresses entered by the user. For example, the user enters "1-1 Marunouchi, Chiyoda-ku, Tokyo." The server obtains the latitude and longitude of each address using the Google Maps API. It also obtains current weather information using the OpenWeatherMap API and collects traffic data using the Waze API. This data is preprocessed to be input into the generative AI model. Specifically, the address data is converted into latitude and longitude, and the weather information and traffic data are converted into numerical data.

[1039] Route calculation using generative AI models

[1040] The preprocessed data is then input into a generative AI model, which is built using TensorFlow and PyTorch to calculate the optimal delivery route. For example, multiple delivery destination data is input as a single batch, and the optimal route is generated, such as from destination A to destination B to destination C.

[1041] View routes and make deliveries

[1042] The generated optimal route is sent from the server to the terminal. The terminal analyzes the received route information and displays it on the car navigation system screen. The driver delivers the parcel by following the route displayed on the car navigation system. The car navigation system updates the route information in real time and notifies the driver.

[1043] Examples of specific examples and prompts

[1044] Examples:

[1045] The user inputs a list of delivery addresses.

[1046] The server uses the Google Maps API to obtain the latitude and longitude of each address and the OpenWeatherMap API to obtain current weather information.

[1047] The server preprocesses this data and feeds it into a generative AI model.

[1048] The generative AI model calculates the optimal delivery route and sends that route information to the car navigation system.

[1049] The driver makes the delivery by following the route displayed on the car navigation system.

[1050] Example prompt sentence:

[1051] Enter a list of delivery addresses and the system will calculate the optimal delivery route and display it on your car navigation system.

[1052] example:

[1053] 1. 1-1 Marunouchi, Chiyoda-ku, Tokyo

[1054] 2. 1-1 Jinnan, Shibuya-ku, Tokyo

[1055] 3. 2-8 Nishi-Shinjuku, Shinjuku-ku, Tokyo

[1056] In this way, the system provides efficient delivery routes, reduces the likelihood of redelivery, and improves delivery efficiency and customer satisfaction.

[1057] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1058] Step 1:

[1059] The user inputs a list of delivery addresses.

[1060] Input: Delivery address list (e.g., 1-1 Marunouchi, Chiyoda-ku, Tokyo, 1-1 Jinnan, Shibuya-ku, Tokyo, 2-8 Nishi-Shinjuku, Shinjuku-ku, Tokyo)

[1061] Output: A list of delivery addresses is sent to the server.

[1062] Specific operation: The user enters the delivery address in text format into the system's input form and clicks the "Submit" button.

[1063] Step 2:

[1064] The server uses the Google Maps API to get the latitude and longitude of each address.

[1065] Input: Delivery address list

[1066] Output: Latitude and longitude information for each address (e.g., 35.681236, 139.767125)

[1067] Specific operation: The server sends a request to the Google Maps API for each address and receives latitude and longitude information in response.

[1068] Step 3:

[1069] The server uses the OpenWeatherMap API to get current weather information.

[1070] Input: Latitude and longitude information for each address

[1071] Output: Weather information for each address (e.g. sunny, temperature 25°C, wind speed 5m / s)

[1072] Specific operation: The server sends a request to the OpenWeatherMap API based on latitude and longitude information and receives weather information in response.

[1073] Step 4:

[1074] The server collects traffic data using the Waze API.

[1075] Input: Latitude and longitude information for each address

[1076] Output: Traffic data for each address (e.g., traffic jams, road closures)

[1077] Specific operation: The server sends a request to the Waze API based on latitude and longitude information and receives traffic condition data in response.

[1078] Step 5:

[1079] Preprocess the data retrieved by the server.

[1080] Input: Latitude and longitude information, weather information, traffic condition data

[1081] Output: Preprocessed dataset (e.g. { "latitude": 35.681236, "longitude": 139.767125, "weather": 1, "temperature": 25, "wind_speed": 5, "traffic": "normal"})

[1082] Specific operation: The server converts address data into latitude and longitude, and converts weather information and traffic condition data into numerical data and compiles them into a single dataset.

[1083] Step 6:

[1084] The server inputs the preprocessed dataset into the generative AI model.

[1085] Input: Preprocessed dataset

[1086] Output: Optimal delivery route (e.g., destination A → destination B → destination C)

[1087] How it works: The server inputs a dataset into the generative AI model, which then calculates the optimal delivery route.

[1088] Step 7:

[1089] The server transmits the generated optimal route to the navigation system.

[1090] Input: Optimal delivery route

[1091] Output: Route information sent to the navigation system

[1092] What happens: The server sends the route information to the navigation system's API using an HTTP POST request.

[1093] Step 8:

[1094] The device analyzes the route information it receives and displays it on the screen.

[1095] Input: Route information

[1096] Output: The route displayed on the screen (e.g. the route shown as a blue line on a map)

[1097] Specific operation: The device analyzes the received route information, displays the route on a map, and provides voice guidance for the next turn.

[1098] Step 9:

[1099] The driver makes the delivery by following the route displayed on the car navigation system.

[1100] Input: Route displayed on car navigation system

[1101] Output: Arrival at delivery destination

[1102] Specific operations: The driver drives the car according to the instructions of the car navigation system and makes deliveries along the specified route.

[1103] Step 10:

[1104] The device updates route information in real time and notifies the driver.

[1105] Input: Real-time traffic data

[1106] Output: Updated route information

[1107] What it does: The device periodically retrieves traffic data, recalculates the route if necessary, and notifies the driver.

[1108] (Application example 2)

[1109] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1110] Conventional delivery systems face the problem of determining optimal delivery routes that take into account traffic information and information on when residents are absent, resulting in a high likelihood of redelivery. It is also difficult to maintain delivery standards, regardless of whether the driver is a veteran or a novice. Furthermore, there was a lack of means to provide real-time updates on delivery progress or feedback after delivery completion, leading to a need for improved delivery efficiency.

[1111] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1112] In this invention, the server includes a means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by AI with a car navigation system, a means for displaying the optimal delivery route determined by AI in real time using an application installed on a smartphone, and a means for updating delivery progress in real time and providing feedback after delivery is completed.This reduces the possibility of redelivery, maintains delivery standards regardless of whether the driver is experienced or new, and improves delivery efficiency.

[1113] "Traffic information data" refers to data that includes information related to traffic, such as road congestion, traffic accidents, and construction information.

[1114] "Resident absence / redelivery performance data" is data that includes information on the time periods when residents were absent and the history of redelivery.

[1115] "Today's delivery parcel information" is data including information on the type and quantity of parcels to be delivered that day, delivery addresses, and the like.

[1116] "Electricity meter information" is data that indicates the electricity usage status of residents, and is used to estimate whether residents are at home.

[1117] "Route characteristics data from the perspective of area drivers" is data that includes information about route characteristics based on the experience and knowledge of drivers in a specific area.

[1118] "Determining by AI" is a method of calculating and determining the optimal delivery route using artificial intelligence.

[1119] "Means for linking with car navigation systems" refers to a method for displaying the determined delivery route on a car navigation system so that the driver can follow that route.

[1120] The "application installed on a smartphone" is software that runs on a smartphone and displays delivery routes and manages delivery progress.

[1121] "Means for updating delivery progress in real time" refers to a method for recording and updating the progress of delivery in real time.

[1122] "Means for providing feedback after delivery completion" refers to a method for providing evaluations and suggestions for improvement to the driver or system after a delivery is completed.

[1123] The system for implementing this invention includes a means for using traffic information data, data on residents' absence / redelivery records, information on the delivery packages for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by AI with a car navigation system, a means for displaying the optimal delivery route determined by AI in real time using an application installed on a smartphone, and a means for updating delivery progress in real time and providing feedback after delivery is completed.

[1124] Program processing explanation

[1125] Hardware used

[1126] server

[1127] Smartphone

[1128] Software used

[1129] TensorFlow: Used to load AI models and make predictions.

[1130] Google Maps API: Used to display routes.

[1131] Data processing and calculation

[1132] 1. The server collects traffic information data, data on residents' absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses this data to calculate the optimal delivery route using an AI model. The AI ​​model uses TensorFlow.

[1133] 2. The server sends the calculated optimal route to the smartphone.

[1134] 3. The smartphone uses the Google Maps API to display the received optimal route on the car navigation app.

[1135] 4. The smartphone provides real-time updates on delivery progress and feedback after delivery is completed.

[1136] Specific examples

[1137] For example, if the starting point is Tokyo Station (latitude 35.6895, longitude 139.6917) and the destination is Tokyo Tower (latitude 35.6586, longitude 139.7454), the server inputs these location information into the AI ​​model to calculate the optimal delivery route.The calculated route information is then sent to the smartphone, which then uses the Google Maps API to display the route on the car navigation app.

[1138] Prompt Sentence Examples

[1139] Enter your starting point and destination, and our AI will calculate the optimal route and display it on your car navigation system.

[1140] Example: Origin: Tokyo Station (35.6895, 139.6917), Destination: Tokyo Tower (35.6586, 139.7454)

[1141] In this way, the embodiments of the invention can reduce the likelihood of redelivery, maintain delivery levels regardless of whether the driver is a veteran or a novice, and improve delivery efficiency.

[1142] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1143] Step 1:

[1144] The server collects traffic information data, data on resident absences / redelivery records, information on the delivery packages for the day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from various sensors and databases. Input data includes traffic information, time when residents are absent, redelivery history, details of delivery packages, electricity usage status, and driver experience information. This data is integrated and pre-processed for input into the AI ​​model.

[1145] Step 2:

[1146] The server uses TensorFlow to load an AI model based on the preprocessed data and calculates the optimal delivery route. The input data includes preprocessed traffic information, residents' absence times, redelivery history, delivery package details, power usage, and driver experience. The AI ​​model analyzes this data and outputs the optimal delivery route.

[1147] Step 3:

[1148] The server sends the calculated optimal route to the smartphone. The optimal route information output by the AI ​​model is included as input data. The server sends this information to the smartphone, which then receives it.

[1149] Step 4:

[1150] The smartphone uses the Google Maps API to display the received optimal route on the car navigation app. The optimal route information received from the server is included as input data. The smartphone calls the Google Maps API and displays the optimal route on the car navigation app.

[1151] Step 5:

[1152] The user (driver) starts driving according to the optimal route displayed on the car navigation app. The optimal route information displayed on the car navigation app is included as input data. The user drives based on this information.

[1153] Step 6:

[1154] The smartphone updates the delivery progress in real time. Input data includes the user's current location and delivery status. Based on this information, the smartphone updates the delivery progress in real time and sends it to the server.

[1155] Step 7:

[1156] After the delivery is completed, the smartphone provides feedback. The input data includes delivery completion information and user feedback. Based on this information, the smartphone generates feedback after the delivery is completed and provides it to the user.

[1157] Example 3

[1158] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1159] Conventional delivery systems were unable to fully utilize data on residents' absences and redelivery attempts, resulting in frequent redeliveries. Furthermore, because they did not take into account traffic information or route characteristics data from the perspective of area drivers, it was difficult to determine efficient delivery routes. Another issue was the difference in delivery ability between veteran and novice drivers.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1161] In this invention, the server includes: means for determining a delivery route for the day using artificial intelligence to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers; means for linking the route determined by artificial intelligence with an in-vehicle navigation system; means for a user to input delivery information into a terminal and for the terminal to send the input data to the server; means for the server to receive and preprocess the data; means for the server to acquire traffic information and integrate electricity meter information and route characteristic data; means for the server to input data into a machine learning model and calculate an optimal delivery route; means for the server to send the calculation results to the terminal and for the terminal to display the optimal delivery route on the in-vehicle navigation system; and means for the user to make delivery according to instructions from the in-vehicle navigation system. This reduces the possibility of redelivery and enables efficient delivery.

[1162] "Traffic information data" refers to data that indicates real-time traffic conditions, including congestion information, road closure information, and the like.

[1163] "Resident absence / redelivery performance data" is data that shows information about the history of when residents were absent and redelivery, such as past delivery dates and times and the number of redeliveries.

[1164] "Today's delivery parcel information" is information about parcels to be delivered, including the parcel ID, delivery address, and type of parcel.

[1165] "Electricity meter information" is data indicating whether a resident is at home, and is information used to determine whether a resident is at home based on electricity usage.

[1166] "Route characteristic data from the perspective of area drivers" is data that indicates characteristics that drivers consider when selecting a delivery route, such as the width of roads within the delivery area, the number of traffic lights, and the availability of parking spaces.

[1167] "Artificial intelligence" is a technology that uses machine learning models to analyze data and calculate optimal delivery routes.

[1168] An "in-vehicle navigation system" is a navigation device installed in a vehicle that displays the optimal delivery route and guides the driver through voice guidance and map display.

[1169] A "terminal" is a device through which a user inputs delivery information, and includes smartphones, tablets, and the like.

[1170] A "server" is a computer system that receives data sent from a terminal and performs preprocessing, data integration, and calculations using machine learning models.

[1171] A "machine learning model" is an algorithm that analyzes data and calculates optimal delivery routes, and is implemented using libraries such as Scikit-learn.

[1172] This invention is a system aimed at improving the efficiency of delivery operations, and utilizes traffic information data, data on residents' absence / redelivery records, information on the parcels delivered on the day, electricity meter information, and data on route characteristics from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery using artificial intelligence.

[1173] System configuration

[1174] The system consists of the following main components:

[1175] 1. Terminal: A device through which a user enters delivery information, including smartphones and tablets.

[1176] 2. Server: A computer system that receives data sent from the terminal and performs preprocessing, data integration, and calculations using machine learning models.

[1177] 3. In-vehicle navigation system: A device that displays the optimal delivery route and guides the driver through voice guidance and map display.

[1178] Hardware and software used

[1179] Hardware: Smartphones, tablets, servers, in-car navigation systems

[1180] Software: Python, Pandas, Scikit-learn, Google Maps API

[1181] Program processing

[1182] The user (driver) enters the delivery package information for the day (package ID, delivery address, package type) and the resident's absence / redelivery record data (past delivery date and time, number of redeliveries) into the terminal. The terminal converts the entered data into JSON format and sends it to the server using the HTTPS protocol.

[1183] The server converts the received JSON data into a data frame using Pandas and performs preprocessing such as missing value imputation and data normalization. The server then uses the Google Maps API to obtain real-time traffic information, including congestion and road closure information.

[1184] The server combines electricity meter information (data showing whether residents are at home) with route characteristics data from the perspective of area drivers (road width, number of traffic lights, availability of parking spaces), and gathers all the data necessary to optimize delivery routes. The combined data is then input into a machine learning model using Scikit-learn to calculate the optimal delivery route. The model then suggests routes that reduce the likelihood of redelivery.

[1185] The server converts the calculated optimal delivery route into JSON format and sends it to the terminal using the HTTPS protocol. The terminal then displays the received optimal delivery route on the in-vehicle navigation system. The in-vehicle navigation system then guides the driver through voice guidance and map display.

[1186] The user (driver) delivers the parcel according to the instructions of the in-vehicle navigation system, which reduces the possibility of redelivery and enables efficient delivery.

[1187] Examples of specific examples and prompts

[1188] For example, the driver enters the following information:

[1189] Delivery information: Package ID 12345, Delivery address 1-2-3 Shibuya-ku, Tokyo, Package type Books

[1190] Absence / redelivery record data: Past delivery date and time 2023-10-01 14:00, redelivery count 2

[1191] Traffic information data: Traffic congestion information Traffic congestion occurs on major roads in Shibuya Ward

[1192] Electricity meter information: At home

[1193] Route characteristics data: narrow road width, many traffic lights, no parking space

[1194] Example prompt sentence:

[1195] Delivery package information:

[1196] Package ID: 12345

[1197] Delivery address: 1-2-3 Shibuya-ku, Tokyo

[1198] Type of package: Books

[1199] Absence / redelivery performance data:

[1200] Previous delivery date: 2023-10-01 14:00

[1201] Number of redeliveries: 2

[1202] Traffic Information Data:

[1203] Traffic congestion information: Traffic jams on major roads in Shibuya Ward

[1204] Electricity meter information:

[1205] Home status: Home

[1206] Route feature data:

[1207] Road width: Narrow

[1208] Number of signals: Many

[1209] Parking space: None

[1210] When this prompt sentence is input into the generative AI model, the AI ​​calculates the optimal delivery route and displays it on the in-vehicle navigation system. By following this route, the driver can reduce the possibility of redelivery and achieve efficient delivery. The flow of the identification process in Example 3 will be explained using Figure 15.

[1211] Step 1:

[1212] The user enters the delivery information into the terminal.

[1213] Using a smartphone or tablet, users enter delivery package information (e.g., package ID 12345, delivery address 1-2-3, Shibuya-ku, Tokyo, package type: books) and past absence / redelivery data (e.g., past delivery date and time 2023-10-01 14:00, number of redeliveries 2) into a dedicated app. The entered data is converted to JSON format on the device.

[1214] Input: Delivery package information, absence / redelivery record data

[1215] Output: JSON format data

[1216] Step 2:

[1217] The terminal transmits the input data to the server.

[1218] The terminal sends the data converted into JSON format to the server using the HTTPS protocol, and the sent data reaches the server through a secure communication channel.

[1219] Input: JSON format data

[1220] Output: Data sent to the server

[1221] Step 3:

[1222] The server receives the data and performs pre-processing.

[1223] The server converts the received JSON data into a data frame using Pandas, then performs missing value imputation (e.g., imputing 0 if the number of redeliveries is not entered) and data normalization (e.g., converting address data to a standard format).

[1224] Input: Data sent to the server

[1225] Output: Preprocessed data frame

[1226] Step 4:

[1227] The server retrieves traffic information using the Google Maps API.

[1228] The server calls the Google Maps API to obtain real-time traffic information for a specified area (e.g., Shibuya Ward, Tokyo). The obtained data includes information on traffic congestion on major roads and road closures.

[1229] Input:Specified area information

[1230] Output: Real-time traffic information

[1231] Step 5:

[1232] The server integrates the electricity meter information with the route characteristic data.

[1233] The server combines electricity meter information (e.g., whether residents are at home) with route characteristics data from the perspective of area drivers (e.g., narrow roads, many traffic lights, lack of parking spaces), providing all the data needed to optimize delivery routes.

[1234] Input: Electricity meter information, route characteristics data

[1235] Output: Consolidated data

[1236] Step 6:

[1237] The server inputs the data into a machine learning model to calculate the optimal delivery route.

[1238] The server then inputs the combined data into a machine learning model using Scikit-learn to calculate the optimal delivery route, which then suggests routes to reduce the chance of redelivery.

[1239] Input: Integrated data

[1240] Output: Optimal delivery route

[1241] Step 7:

[1242] The server sends the calculation results to the terminal.

[1243] The server converts the calculated optimal delivery route into JSON format and sends it to the terminal using the HTTPS protocol.

[1244] Input: Optimal delivery route

[1245] Output: Data sent to the terminal

[1246] Step 8:

[1247] The device displays the optimal delivery route on the vehicle's navigation system.

[1248] The device then displays the optimal delivery route on the in-vehicle navigation system, which then guides the driver through voice guidance and map display.

[1249] Input: Data sent to the terminal

[1250] Output: Route displayed on the in-car navigation system

[1251] Step 9:

[1252] The user makes the delivery according to the instructions of the in-car navigation system.

[1253] The user (driver) makes deliveries according to the instructions of the in-car navigation system. For example, if the car navigation system instructs the driver to "turn right at the next intersection," the driver will follow the instruction and turn right. This reduces the possibility of redelivery and enables efficient delivery.

[1254] Input: In-car navigation system instructions

[1255] Output: Efficient delivery

[1256] (Application example 3)

[1257] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1258] Conventional delivery systems have a high probability of redelivery and make it difficult to determine efficient delivery routes. Even in food delivery, they are unable to provide optimal routes that take into account traffic information and past delivery performance data, making it difficult to shorten delivery times or improve efficiency. This has led to delivery delays and redeliveries, resulting in lower customer satisfaction.

[1259] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1260] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by AI with a car navigation system, means for inputting food delivery information and determining an optimal delivery route based on traffic information data, past delivery record data, and area characteristic data, and means for displaying the optimal route on a car navigation app on a smartphone.This reduces the possibility of redelivery and enables shorter and more efficient delivery times.

[1261] "Traffic information data" refers to information about traffic provided in real time, such as road congestion, traffic accidents, and construction information.

[1262] "Resident absence / redelivery performance data" is historical information such as the time periods when residents were absent in the past and the number of redeliveries made.

[1263] "Today's delivery package information" is information about packages to be delivered on that day, such as the contents of the package to be delivered, the delivery address, and the scheduled delivery time.

[1264] "Electricity meter information" is data that indicates the electricity usage status of residents, and is information that is used to infer whether residents are at home or not.

[1265] "Route characteristics data from the perspective of area drivers" is information on the characteristics of routes based on road features and traffic conditions within the delivery area, as well as the driver's experience.

[1266] "AI" stands for artificial intelligence, a technology that calculates optimal delivery routes based on data.

[1267] A "car navigation system" is a navigation system installed in a vehicle that provides map information and route guidance.

[1268] "Food delivery" is a service that delivers food and drinks to a location specified by the customer.

[1269] A "smartphone car navigation app" is a navigation application that runs on a smartphone and is software that provides map information and route guidance.

[1270] The "optimal delivery route" is a delivery route calculated based on traffic information and past delivery performance data in order to shorten delivery times and increase efficiency.

[1271] A system for implementing the present invention includes a server, a smartphone, a car navigation application, and an AI model. A specific embodiment of this system will be described below.

[1272] System configuration

[1273] 1. Server:

[1274] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers, and uses this data to calculate the optimal delivery route using an AI model.

[1275] The server is programmed using Python and has an interface for obtaining traffic information APIs and past delivery performance data.

[1276] 2. Smartphone:

[1277] The smartphone is a device used by food delivery drivers and has an application installed for entering delivery information.

[1278] The smartphone application receives the optimal delivery route from the server and displays it on the car navigation application.

[1279] 3. Car navigation applications:

[1280] The car navigation application runs on the smartphone and displays the optimal delivery route received from the server.

[1281] Drivers use this car navigation application to follow the optimal route when making deliveries.

[1282] Processing the data

[1283] The server processes the data in the following steps:

[1284] 1. Data Collection:

[1285] The server obtains the latest traffic information data from the traffic information API.

[1286] The server reads past delivery performance data from a local file.

[1287] The server receives the delivery package information for the day entered by the food delivery driver.

[1288] 2. Calculating the optimal route using AI models:

[1289] The server uses the collected data to calculate the optimal delivery route using a random forest regression model.

[1290] The model uses traffic information, past delivery performance data, and area characteristic data as features to shorten delivery times and improve efficiency.

[1291] 3. Optimal route distribution:

[1292] The server sends the calculated optimal route to the smartphone application.

[1293] The smartphone application displays the received optimal route on the car navigation application.

[1294] Specific examples

[1295] For example, let's say a driver enters the following delivery information:

[1296] Order 1: Address 1, delivery time 12:00

[1297] Order 2: Address 2, delivery time 12:30

[1298] The server obtains the latest traffic information from the traffic information API and calculates the optimal delivery route based on past delivery performance data. For example, if past data indicates that "Address 1 has less traffic congestion in the morning," the server will suggest a route that "deliver to Address 1 first, then head to Address 2."

[1299] Prompt Sentence Examples

[1300] Use the delivery information below to calculate the best delivery route.

[1301] Order 1: Address 1, delivery time 12:00

[1302] Order 2: Address 2, delivery time 12:30

[1303] Get the latest traffic information from the traffic information API and suggest the optimal route based on past delivery performance data.

[1304] In this way, by combining servers, smartphones, car navigation applications, and AI models, the possibility of redelivery can be reduced, and delivery times can be shortened and made more efficient.

[1305] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1306] Step 1:

[1307] The user (food delivery driver) uses a smartphone application to enter the day's delivery information (order details, delivery address, estimated delivery time, etc.).

[1308] Input: Delivery information (order details, delivery address, estimated delivery time)

[1309] Output: Delivery information sent to the server

[1310] Step 2:

[1311] The server obtains the latest traffic information data from the traffic information API.

[1312] Input: Request to traffic information API

[1313] Output: Traffic information data (road congestion, traffic accidents, construction information, etc.)

[1314] Step 3:

[1315] The server reads past delivery performance data from a local file.

[1316] Input: Local file (past delivery performance data)

[1317] Output: Past delivery performance data (resident absence time, redelivery history, etc.)

[1318] Step 4:

[1319] The server calculates the optimal delivery route using a random forest regression model based on the collected data (delivery information, traffic information data, and past delivery performance data).

[1320] Input: Delivery information, traffic information data, past delivery performance data

[1321] Output: Optimal delivery route (delivery sequence, estimated delivery time, etc.)

[1322] Specific operation: The server extracts features (traffic information, past delivery performance, area characteristics) and inputs them into a random forest regression model to predict the optimal delivery route.

[1323] Step 5:

[1324] The server sends the calculated optimal route to the smartphone application.

[1325] Input: Optimal delivery route

[1326] Output: Optimal route sent to smartphone application

[1327] Step 6:

[1328] The smartphone application displays the received optimal route on the car navigation application.

[1329] Input: Optimal delivery route

[1330] Output: Optimal route displayed in a car navigation application

[1331] Specific operation: The smartphone application analyzes the optimal route received from the server and converts it into a format for display in the car navigation application.

[1332] Step 7:

[1333] The user (food delivery driver) makes deliveries by following the optimal route displayed on the car navigation application.

[1334] Input: Optimal route displayed in a car navigation application

[1335] Output: Delivery execution

[1336] What happens: The driver follows the directions in the car navigation application to reach the delivery location and complete the delivery efficiently.

[1337] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1338] "Example 1"

[1339] One embodiment of the present invention provides a delivery route determination system incorporating an emotion engine. This system recognizes a user's emotions and optimizes delivery routes based on those emotions. Specifically, the system analyzes information obtained during interactions with the user, such as voice, text, facial expressions, and physical movements, and determines delivery routes based on the results. For example, if a user expresses anger or dissatisfaction, the system can prioritize deliveries to that user, thereby improving user satisfaction.

[1340] "Example 2"

[1341] In another embodiment of the present invention, a system is provided in which an emotion engine adjusts delivery time and delivery method. Specifically, the delivery time is advanced or delayed depending on the user's emotions. Furthermore, if the user shows joy or excitement, the system can devise a delivery method, such as delivering a gift as a surprise. This makes it possible to provide a service that corresponds to the user's emotions, further improving user satisfaction. "Embodiment 3"

[1342] Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine and an AI work in cooperation with each other. Specifically, the emotion engine recognizes the user's emotions and provides that information to the AI. The AI ​​optimizes delivery routes based on that information. For example, if a user expresses joy, the AI ​​prioritizes deliveries to that user. On the other hand, if a user expresses anger, the AI ​​delays deliveries to that user and prioritizes deliveries to other users. This makes it possible to optimize delivery routes in response to the user's emotions.

[1343] The processing flow of each embodiment will be described below.

[1344] "Example 1"

[1345] Step 1: The emotion engine collects information obtained during interaction with the user, such as voice, text, facial expressions, and physical movements.

[1346] Step 2: The emotion engine analyzes the collected information and recognizes the user's emotions.

[1347] Step 3: Based on the detected emotions, the AI ​​optimizes the delivery route.

[1348] "Example 2"

[1349] Step 1: The emotion engine collects information obtained during interaction with the user and recognizes the user's emotions.

[1350] Step 2: The emotion engine adjusts delivery time and method based on the recognized emotion.

[1351] Step 3: AI optimizes delivery routes based on adjusted delivery times and methods.

[1352] "Example 3"

[1353] Step 1: The emotion engine collects information obtained during interaction with the user and recognizes the user's emotions.

[1354] Step 2: Provide the AI ​​with the emotional information recognized by the emotion engine.

[1355] Step 3: Based on the provided emotional information, the AI ​​optimizes the delivery route.

[1356] Example 1

[1357] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1358] Conventional delivery route planning systems can optimize delivery routes by taking into account traffic information and resident absence data, but they have not yet optimized delivery routes by taking into account user emotions. Therefore, there is a need for re-optimization of delivery routes to improve user satisfaction. Furthermore, a means to maintain delivery quality regardless of the experience of the delivery driver is also necessary.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1360] In this invention, the server includes: a means for determining a delivery route for the day using artificial intelligence to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, information on the delivery parcels for the day, electricity meter information, and route characteristic data from the perspective of area drivers; a means for linking the route determined by the artificial intelligence with the vehicle navigation system; a means for collecting emotional data such as voice, text, facial expressions, and physical movements through interactions with the user; and a means for analyzing the collected emotional data and re-optimizing the delivery route based on the results. This enables the optimization of delivery routes taking into account the user's emotions, improving user satisfaction. It also allows delivery levels to be maintained regardless of experience.

[1361] "Traffic information data" refers to information about traffic obtained in real time, such as road congestion, traffic accidents, and construction information.

[1362] "Resident absence / redelivery performance data" is information based on past delivery history, such as the time periods when residents were absent and the number of redeliveries made.

[1363] "Information about parcels to be delivered on the day" refers to detailed information such as the type, quantity, and delivery address of parcels to be delivered on the day.

[1364] "Electricity meter information" is data that indicates the electricity consumption status of residents, and is information obtained from smart meters and the like.

[1365] "Route characteristic data from the perspective of area drivers" is feedback information based on the driver's experience, such as road conditions within the delivery area and the characteristics of the delivery destination.

[1366] "Artificial intelligence" is a computer program that uses machine learning and data analysis to calculate optimal delivery routes.

[1367] A "vehicle navigation system" is an electronic device that is installed in a vehicle and provides route guidance to a destination.

[1368] "Interaction with the user" refers to communication with the user during delivery through voice, text, facial expressions, physical movements, etc.

[1369] "Emotion data" is information about emotions obtained from the user's voice, text, facial expressions, body movements, and the like.

[1370] "Emotion analysis" is the process of analyzing collected emotion data to identify a user's emotional state.

[1371] "Delivery route reoptimization" is the process of recalculating existing delivery routes and changing them to the optimal route based on the results of sentiment analysis.

[1372] This system uses traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers to determine delivery routes using artificial intelligence (AI) that reduce the possibility of daily redelivery. It also includes a function to re-optimize delivery routes by taking into account the user's emotions.

[1373] Hardware and software used

[1374] Hardware: Servers, terminals, sensors (electricity meters, cameras, etc.)

[1375] Software: AI models (TensorFlow, PyTorch, etc.), sentiment analysis engine, database management system (MySQL, PostgreSQL, etc.)

[1376] Data collection and processing

[1377] The server collects traffic information data, data on resident absences / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from Google Maps API, delivery management systems, smart meters, etc. The collected data is stored in a database such as MySQL or PostgreSQL.

[1378] The server uses an AI model based on the stored data to calculate the optimal delivery route. Specifically, it uses TensorFlow and PyTorch to build a route optimization model, taking into account the time residents are absent and past redelivery data to reduce the likelihood of redelivery.

[1379] The device collects emotional data through interactions with the user during delivery, using a voice assistant and camera to capture information such as voice, text, facial expressions, and physical movements.

[1380] The server analyzes the collected emotional data using an emotion analysis engine, specifically using OpenAI's emotion analysis model to recognize the user's emotions and identify emotions such as anger or frustration.

[1381] The server re-optimizes delivery routes based on the results of emotion analysis. Specifically, if a user expresses anger or dissatisfaction, the server recalculates the route to prioritize deliveries to that user.

[1382] Specific examples

[1383] For example, when deciding on a delivery route for a certain day, the following steps are taken:

[1384] 1. The server collects traffic information data (e.g., Google Maps API), data on resident absences / redelivery attempts (e.g., past delivery history), information on the day's delivery packages (e.g., data from the delivery management system), electricity meter information (e.g., smart meter data), and route characteristics data from the perspective of area drivers (e.g., driver feedback).

[1385] 2. The server stores this data in a database and calculates the optimal delivery route using an AI model (e.g., a route optimization model using TensorFlow).

[1386] 3. The device collects user emotional data through interactions with the user during delivery (e.g., voice assistant or facial recognition via camera).

[1387] 4. The server uses an emotion analysis engine (e.g., OpenAI's emotion analysis model) to analyze the collected emotion data, and if the user shows anger or dissatisfaction, it recalculates the delivery route to prioritize deliveries to that user.

[1388] Prompt Sentence Examples

[1389] "Please create an AI model that determines the optimal delivery route based on traffic information data, data on residents' absence / redelivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. Also, please add a function that recognizes the user's emotions and optimizes the delivery route according to those emotions."

[1390] In this way, specific embodiments of the system will be described while clarifying the roles of the server, terminal, and user.

[1391] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1392] Step 1:

[1393] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[1394] Input: Traffic information from Google Maps API, resident absence / redelivery performance data from the delivery management system, delivery package information for the day, electricity meter information from smart meters, driver feedback.

[1395] Data processing: Integrate the information obtained from each data source and store it in a database.

[1396] Output: A consolidated dataset.

[1397] Specific operation: The server sends an API request to obtain traffic information, obtains data on absences and redelivery from the delivery management system, and obtains electricity meter information from the smart meter. This data is then integrated and stored in a database.

[1398] Step 2:

[1399] The server uses AI models based on the stored data to calculate the optimal delivery route.

[1400] Input: The integrated dataset.

[1401] Data Computing: Using TensorFlow and PyTorch, we build route optimization models that take into account resident absence times and historical redelivery data to reduce the likelihood of redelivery attempts.

[1402] Output: Optimal delivery route.

[1403] How it works: The server inputs the combined dataset into an AI model to calculate the optimal delivery route, and the results are sent to the vehicle's navigation system.

[1404] Step 3:

[1405] The terminal collects emotional data through interactions with the user during delivery.

[1406] Input: User interaction (voice, text, facial expressions, body movements).

[1407] Data processing: Perform voice recognition, text analysis, facial recognition, and motion analysis to extract emotional data.

[1408] Output: Extracted emotion data.

[1409] Specific behavior: The device uses a voice assistant or camera to collect the user's voice, text, facial expressions, and physical movements, and analyzes this data to extract emotional data.

[1410] Step 4:

[1411] The server analyzes the collected emotion data using an emotion analysis engine.

[1412] Input: Extracted emotion data.

[1413] Data Computing: Recognize user emotions using OpenAI's sentiment analysis model to identify feelings such as anger or frustration.

[1414] Output: The result of the sentiment analysis.

[1415] How it works: The server inputs emotional data into an emotion analysis engine to identify the user's emotional state. The analysis results are used to re-optimize delivery routes.

[1416] Step 5:

[1417] The server re-optimizes delivery routes based on the results of the sentiment analysis.

[1418] Input: Sentiment analysis results, optimal delivery route.

[1419] Data calculations: Recalculating existing delivery routes taking into account the results of sentiment analysis.

[1420] Output: Reoptimized delivery routes.

[1421] Specific operation: Based on the results of emotion analysis, if the user expresses anger or dissatisfaction, the server recalculates the route to prioritize deliveries to that user. The re-optimized route is sent to the vehicle's navigation system.

[1422] (Application example 1)

[1423] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1424] Conventional delivery route planning systems can take into account traffic information and data on absences and redelivery requests, but they do not optimize delivery routes with consideration for user emotions. This makes it difficult to improve user satisfaction, and there is a particular issue of being unable to respond appropriately to users who express dissatisfaction or anger. Furthermore, there is a need to maintain delivery standards without relying on the experience of the delivery driver.

[1425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1426] In this invention, the server includes a means for using traffic information data, data on resident absences / redelivery records, information on the delivery parcels for the day, electricity meter information, and route characteristics data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, a means for linking the route determined by the AI ​​with a car navigation system, a means for recognizing user emotions and optimizing the delivery route according to those emotions, and a means for analyzing information such as voice, text, facial expressions, and physical movements. This makes it possible to optimize delivery routes taking user emotions into account, thereby improving user satisfaction. It also makes it possible to maintain delivery standards regardless of the delivery driver's experience.

[1427] "Traffic information data" refers to information about traffic obtained in real time, such as road congestion, traffic accidents, and construction information.

[1428] "Resident absence / redelivery performance data" is historical information such as the time periods when residents were absent during past deliveries and the number of redeliveries made.

[1429] "Today's delivery package information" refers to detailed information such as the type, quantity, and delivery address of packages scheduled to be delivered on that day.

[1430] "Electricity meter information" is electricity meter power consumption data used to estimate whether residents are at home.

[1431] "Route characteristic data from the perspective of area drivers" refers to route characteristic information based on the driver's experience, such as road conditions within the delivery area and the characteristics of the delivery destination.

[1432] "AI" stands for artificial intelligence, a set of algorithms and systems that analyze data and determine optimal delivery routes.

[1433] A "car navigation system" is a navigation system installed in a vehicle that provides route guidance to a destination.

[1434] "User emotion" refers to the emotional state of a user using a delivery service, and is analyzed from voice, text, facial expressions, physical movements, etc.

[1435] "Information such as voice, text, facial expressions, and physical movements" refers to various data formats used to recognize a user's emotions.

[1436] The system for implementing this invention collects traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and uses AI to determine the optimal delivery route.It also includes a function to recognize user emotions and optimize the delivery route according to those emotions.

[1437] System configuration

[1438] Hardware

[1439] Server: Collects, analyzes, and stores data.

[1440] Smartphone: Used by delivery drivers and linked to car navigation systems.

[1441] Smart meter: An electricity meter that estimates whether a user is at home.

[1442] Camera: Used to recognize the user's facial expressions.

[1443] Microphone: Used to collect the user's voice.

[1444] software

[1445] Google Maps API: Collects real-time traffic information.

[1446] Firebase: Manages user absence / redelivery record data and delivery order information for the day.

[1447] Smart Meter API: Collects electricity meter information.

[1448] Google Cloud Speech-to-Text: Converts voice data into text.

[1449] Google Cloud Natural Language: Perform sentiment analysis on text data.

[1450] OpenCV: Facial expression analysis.

[1451] TensorFlow: Analyzes body movements.

[1452] Data collection and analysis

[1453] The server uses the Google Maps API to collect real-time traffic information, Firebase to manage the user's absence / redelivery record data and the delivery order information for the day, and a smart meter API to collect electricity meter information to estimate the user's presence / absence status.

[1454] Incorporating an emotion engine

[1455] The server converts voice data to text using Google Cloud Speech-to-Text, performs sentiment analysis on the text data using Google Cloud Natural Language, analyzes facial expressions using OpenCV, and analyzes body movements using TensorFlow.

[1456] Delivery route optimization

[1457] The server uses AI to determine the optimal delivery route based on the collected data. It also takes into account the user's emotions, prioritizing deliveries to users who express particular dissatisfaction or anger, thereby improving satisfaction.

[1458] Specific examples

[1459] For example, if a user orders food delivery and has had to redeliver many times in the past, the server will optimize the delivery route taking into account the user's home hours. Also, if a user shows anger or dissatisfaction, the server will prioritize deliveries for that user to improve satisfaction.

[1460] Prompt Sentence Examples

[1461] "When a user places an order for food delivery, please design a system that collects traffic information, past absence / re-delivery data, delivery order information for that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses AI to determine the optimal delivery route. Also, please add a function that incorporates an emotion engine to recognize the user's emotions and optimize the delivery route accordingly."

[1462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1463] Step 1:

[1464] The server uses the Google Maps API to collect real-time traffic information. It receives current traffic conditions and road congestion information as input, and generates traffic information data necessary for optimizing delivery routes as output. Specifically, it sends API requests and analyzes the response data.

[1465] Step 2:

[1466] The server uses Firebase to manage the user's absence / redelivery record data and the delivery order information for the day. It obtains past delivery history and the order information for the day as input, and generates the user data necessary for optimizing delivery routes as output. Specifically, it executes database queries and extracts the necessary data.

[1467] Step 3:

[1468] The server uses the smart meter API to collect electricity meter information. As input, it obtains the user's electricity consumption data, and as output, it generates data to estimate the user's presence or absence. Specifically, it sends an API request and analyzes the response data.

[1469] Step 4:

[1470] The server converts the voice data into text using Google Cloud Speech-to-Text. It receives the user's voice data as input and generates text data as output. Specifically, it uploads the voice file to a cloud service and receives the converted text.

[1471] Step 5:

[1472] The server performs sentiment analysis on text data using Google Cloud Natural Language. It receives the converted text data as input and generates sentiment analysis results as output. Specifically, it sends the text data to a cloud service and receives a sentiment score.

[1473] Step 6:

[1474] The server analyzes facial expressions using OpenCV. It receives the user's facial image data as input and generates facial expression analysis results as output. Specifically, it applies an image processing algorithm to extract facial feature points.

[1475] Step 7:

[1476] The server analyzes physical movements using TensorFlow. It receives user movement data as input and generates movement analysis results as output. It applies a machine learning model to extract specific movement features.

[1477] Step 8:

[1478] The server uses AI to determine the optimal delivery route based on all collected data. Traffic information data, user data, electricity meter information, emotion analysis results, facial expression analysis results, and movement analysis results are taken as input, and the optimal delivery route is generated as output. The specific operation is to apply an AI algorithm to calculate the optimal route.

[1479] Step 9:

[1480] The server synchronizes the optimal delivery route with the car navigation system. As input, it acquires optimal route data and as output, it sends route information to the car navigation system. Specifically, it sends data to the car navigation system and starts route guidance.

[1481] Step 10:

[1482] The user makes the delivery according to the optimized delivery route through the smartphone used by the delivery driver. The input is route guidance from the car navigation system, and the output is a report that the delivery has been completed. The specific operation is to use the smartphone's navigation function to arrive at the delivery destination.

[1483] Example 2

[1484] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1485] Conventional delivery systems have difficulty determining delivery routes taking into account traffic information and information on residents' absences, which increases the likelihood of redelivery. Furthermore, because delivery depends on the experience of the delivery driver, it is difficult for new drivers to deliver efficiently. Furthermore, it is not possible to provide services that respond to user emotions, making it difficult to improve user satisfaction.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1487] In this invention, the server includes means for determining a delivery route for the day that reduces the possibility of daily redelivery using a generative AI model, utilizing traffic information data, resident absence / redelivery record data, information on the parcels delivered that day, electricity meter information, and route characteristic data from the perspective of area drivers, means for linking the route determined by the generative AI model with a car navigation system, means for analyzing user emotion data and adjusting delivery time and delivery method, and means for delivering a surprise gift according to the user's emotion. This reduces the possibility of redelivery, enables efficient delivery regardless of whether the driver is a veteran or a novice, and makes it possible to provide a service that responds to the user's emotion.

[1488] "Traffic information data" refers to information that influences the decision on delivery routes, such as traffic conditions, road congestion, and accident information.

[1489] "Resident absence / redelivery performance data" refers to historical information on the time periods when residents were absent during past deliveries and when redelivery was performed.

[1490] "Information about parcels to be delivered on the day" refers to detailed information about parcels scheduled for delivery on the day, such as the number and size of parcels, and delivery address.

[1491] "Electricity meter information" refers to electricity consumption data used to estimate whether residents at delivery destinations are at home.

[1492] "Route characteristics data from the perspective of area drivers" refers to route characteristics and points of caution based on the experience and knowledge of drivers in a specific area.

[1493] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to calculate optimal delivery routes.

[1494] "Car navigation" refers to a navigation system installed in a vehicle that provides map information and route guidance.

[1495] "User emotional data" refers to data that indicates the user's emotional state, and refers to information obtained from smartphone sensors or wearable devices.

[1496] An "emotion engine" refers to a system that analyzes user emotional data and adjusts delivery times and methods based on the results.

[1497] The "means for delivering a surprise gift" refers to a method or process for delivering a special gift in addition to regular delivery depending on the user's emotions.

[1498] MODE FOR CARRYING OUT THE INVENTION

[1499] This invention is a system that uses traffic information data, data on resident absences / redelivery records, information on parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers to determine a delivery route using a generative AI model that reduces the possibility of daily redelivery.Furthermore, the system has the function of linking the route determined by the generative AI model with a car navigation system, analyzing user emotion data, and adjusting delivery time and delivery method.

[1500] Server Roles

[1501] The server first receives a delivery request from the user. This request includes the delivery address, desired delivery time, and any special instructions. Next, the server uses a generative AI model to calculate the optimal delivery route, taking into account traffic conditions and distance using map information services such as Google Maps API. The calculated route is then sent from the server to the car navigation system. The server then receives the user's emotional data and analyzes it using an emotion engine. Based on the analysis results, the server adjusts the delivery time and method, and adds a surprise gift if necessary.

[1502] Role of the terminal (car navigation system)

[1503] The terminal (car navigation system) receives the optimal route information sent from the server. Based on the received route information, the route is displayed on the car navigation system screen. The driver delivers the parcel along this route. The car navigation system updates the location information in real time and can also recalculate the route as needed.

[1504] User Roles

[1505] Users submit delivery requests to the system. The request can include the delivery address, desired delivery time, and any special instructions. The user's emotional data is also sent to the system. The emotion engine analyzes this data and adjusts the delivery time and method depending on the user's emotions. For example, if the user expresses joy or excitement, the system may deliver a gift as a surprise.

[1506] Specific examples

[1507] For example, if a user sends a delivery request to "1-1-1 Shibuya, Shibuya-ku, Tokyo," the server calculates the optimal route using the Google Maps API. The calculated route is sent from the server to the car navigation system and displayed on the screen. The driver then makes the delivery following this route.

[1508] For example, if a user requests delivery to "1-1-1 Shibuya, Shibuya-ku, Tokyo" and indicates "joy" as the emotion data, the emotion engine will analyze this data and speed up the delivery. It may also add a small gift as a surprise to the delivery.

[1509] Prompt Sentence Examples

[1510] "If a user requests delivery to 1-1-1 Shibuya, Shibuya-ku, Tokyo, and indicates happiness as emotion data, explain how to calculate the optimal delivery route, speed up the delivery time, and add a gift as a surprise."

[1511] In this way, the system provides the optimal delivery route and method based on the user's request and emotional data.

[1512] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1513] Program processing flow

[1514] Step 1: Receiving a delivery request

[1515] The server receives delivery requests from users, which include delivery addresses, desired delivery times, and any special instructions.

[1516] Input: Delivery request from user (address, desired delivery time, special instructions)

[1517] Output: Delivery request data

[1518] Specific operation: The server receives an HTTP request and extracts the necessary information from the request body.

[1519] Step 2: Calculate the optimal route

[1520] The server uses a generative AI model to calculate the optimal delivery route, taking into account traffic information, data on residents' absences / re-delivery requests, information on the parcels delivered that day, electricity meter information, and route characteristics from the perspective of area drivers.

[1521] Input: Delivery request data, traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, route characteristics data from the perspective of area drivers

[1522] Output: Optimal route information

[1523] Specific operation: The server sends a request to the Google Maps API, analyzes the returned data, and determines the optimal route.

[1524] Step 3: Submit route information

[1525] The server transmits the calculated optimum route information to the car navigation system.

[1526] Input: Optimal route information

[1527] Output: Send route information to car navigation system

[1528] Specific operation: The server sends route information to the car navigation system using WebSocket or HTTP POST request.

[1529] Step 4: View Routes

[1530] The terminal (car navigation system) receives the optimum route information sent from the server and displays the route on the car navigation system screen.

[1531] Input: Route information from the server

[1532] Output: Route displayed on the car navigation screen

[1533] Specific operation: The device uses the screen drawing API to display the route on a map.

[1534] Step 5: Real-time location updates

[1535] The device (car navigation system) updates location information in real time and recalculates the route as needed.

[1536] Input: GPS data

[1537] Output: Updated route information

[1538] What it does: The device acquires GPS data, sends it to the server, and requests new routes if necessary.

[1539] Step 6: Receiving and analyzing emotion data

[1540] The server receives the user's emotion data and analyzes it using an emotion engine.

[1541] Input: User emotion data

[1542] Output: Analysis results (user's emotional state)

[1543] Specific operation: The server calls the emotion analysis API and analyzes the user's emotion data.

[1544] Step 7: Adjust delivery method

[1545] The server adjusts the delivery time and method based on the analysis results. For example, if the user expresses joy, it may speed up the delivery or add a surprise gift.

[1546] Input: Analysis results (user's emotional state)

[1547] Output: Adjusted delivery schedule and delivery methods

[1548] Specific behavior: The server updates the delivery schedule and instructs the customer to add gifts as needed.

[1549] Step 8: Confirm delivery

[1550] After the delivery is completed, the user checks the delivery details and provides feedback.

[1551] Input: Delivery completion notification

[1552] Output: User feedback

[1553] Specific operation: The user receives a delivery completion notification on the smartphone app, checks the delivery details, and fills out and submits a feedback form.

[1554] (Application example 2)

[1555] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1556] Conventional delivery systems can determine delivery routes by taking into account traffic information and data on resident absences, but they are unable to adjust delivery times and methods based on user emotions, making it difficult to fully improve user satisfaction. Furthermore, because delivery depends on the experience of the delivery driver, it is difficult to maintain a high level of delivery. Furthermore, they are unable to provide value-added services, such as delivering surprise gifts based on the user's emotions.

[1557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1558] In this invention, the server includes: a means for determining a delivery route for the day using AI to reduce the possibility of daily redelivery by utilizing traffic information data, resident absence / redelivery history data, information on the delivery parcels for the day, electricity meter information, and route characteristics data from the perspective of area drivers; a means for linking the route determined by AI with a car navigation system; a means for detecting user emotion data and adjusting the delivery time and delivery method; and a means for delivering a surprise gift according to the user's emotion. This enables flexible adjustment of delivery time and method according to the user's emotion, thereby improving user satisfaction. It also enables a high level of delivery to be maintained regardless of the delivery driver's experience, and further enables the provision of value-added services to users.

[1559] "Traffic information data" refers to information about traffic that affects delivery routes, such as road congestion, traffic accidents, and construction information.

[1560] "Resident absence / redelivery performance data" refers to historical information on the time periods when residents were absent during past deliveries and when redelivery was performed.

[1561] "Today's delivery parcel information" is information about parcels scheduled to be delivered on that day, including the number and size of parcels, delivery address, etc.

[1562] "Electricity meter information" is data on residents' electricity usage and is used to infer whether residents are at home.

[1563] "Route characteristics data from the perspective of area drivers" refers to information on route characteristics and points of caution based on the experiences of drivers in a specific area.

[1564] "Method of deciding using AI" refers to a method of using artificial intelligence to determine the optimal delivery route.

[1565] "Means for linking with car navigation systems" refers to a method for displaying the determined delivery route on the in-car navigation system so that the driver can follow that route.

[1566] "User emotion data" is data for detecting the user's emotional state, and includes emotions such as joy, excitement, and sadness.

[1567] "Means for adjusting delivery time and delivery method" refers to methods for speeding up or delaying delivery time or changing delivery method based on user emotion data.

[1568] "Means for delivering a surprise gift" refers to a method for delivering an additional gift depending on the user's emotions.

[1569] A system for implementing this invention includes a means for using AI to determine a delivery route for the day that reduces the possibility of daily redelivery by utilizing traffic information data, data on resident absence / redelivery history, information on the parcels delivered on the day, electricity meter information, and route characteristic data from the perspective of area drivers, a means for linking the route determined by AI with a car navigation system, a means for detecting user emotion data and adjusting delivery time and delivery method, and a means for delivering a surprise gift according to the user's emotion.

[1570] System configuration

[1571] Hardware

[1572] Server: Processes data and runs AI models.

[1573] Smartphone: Used by the driver and linked to the car navigation system.

[1574] Emotion detection device: A device for collecting user emotion data (e.g., a smartphone camera or a wearable device).

[1575] software

[1576] AI Routing API: An API for determining the optimal delivery route.

[1577] Emotion Detection Library: A library for detecting user emotions.

[1578] Car navigation application: An application for displaying routes determined by AI.

[1579] Data processing and calculation

[1580] The server collects traffic information, data on residents' absences / re-delivery records, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and then uses this data to determine the optimal delivery route using an AI routing API. The determined route is sent to the driver's smartphone navigation application and displayed to them.

[1581] The user's emotional data is collected through the emotion detection device and analyzed using the emotion detection library. Based on the analysis results, the server adjusts the delivery time and delivery method and delivers the surprise gift as needed.

[1582] Specific examples

[1583] For example, if User A orders food delivery, the server determines the optimal delivery route based on traffic information and resident absence data, and displays it on the driver's smartphone. If User A's emotion is detected as "happy," the server instructs the driver to deliver an additional surprise gift.

[1584] Prompt Sentence Examples

[1585] "Develop a food delivery application that adjusts delivery time and method based on the user's emotions. Use AI to determine the optimal delivery route and an emotion engine to adjust delivery based on the user's emotions. For example, if the user expresses joy or excitement, deliver a surprise gift."

[1586] In this way, it becomes possible to flexibly adjust delivery times and methods according to the user's emotions, improving user satisfaction. It also makes it possible to maintain a high level of delivery without relying on the delivery driver's experience, and to provide value-added services to users.

[1587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1588] Step 1:

[1589] The server collects traffic information data, data on resident absence / redelivery records, information on the delivery package for the day, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from various sensors and databases. Input data includes traffic information, resident absence data, delivery package information, electricity meter information, and route characteristics data. Based on this data, the server preprocesses the data and converts it into a format for input into the AI ​​model.

[1590] Step 2:

[1591] The server sends the preprocessed data to the AI ​​routing API to determine the optimal delivery route. The AI ​​routing API calculates the optimal route based on the input data and returns the results to the server. The output data includes optimal delivery route information. The server receives this route information and proceeds to the next step.

[1592] Step 3:

[1593] The server sends the determined optimal delivery route information to the driver's smartphone. The smartphone's car navigation application receives this route information and displays it to the driver. The optimal delivery route information is included as input data, and the route information to be displayed on the smartphone's car navigation screen is included as output data. The driver then starts driving along this route.

[1594] Step 4:

[1595] A user collects emotion data using an emotion detection device (e.g., a smartphone camera or a wearable device). The emotion detection device analyzes the user's facial expressions, voice, etc., and generates emotion data. The input data includes the user's facial expressions and voice data, and the emotion data is generated as output data.

[1596] Step 5:

[1597] The server sends the user's emotional data to the emotion detection library, which analyzes the user's emotional state. The emotion detection library determines the user's emotion based on the input data and returns the result to the server. The output data includes the user's emotional state (e.g., happy, neutral, sad). The server receives this emotional state and proceeds to the next step.

[1598] Step 6:

[1599] The server adjusts the delivery time and delivery method based on the user's emotional state. For example, if the user is determined to be "happy," the server instructs the delivery time to be earlier or to add a surprise gift. The input data includes the user's emotional state, and the output data includes the adjusted delivery time and delivery method.

[1600] Step 7:

[1601] The server sends the adjusted delivery time and delivery method to the driver's smartphone. The smartphone's car navigation application receives this information and displays it to the driver. The input data includes the adjusted delivery time and delivery method, and the output data includes the information to be displayed on the smartphone's car navigation screen. The driver then makes the delivery according to this information.

[1602] The above steps enable flexible adjustment of delivery times and methods according to the user's emotions, improving user satisfaction. It also enables a high level of delivery to be maintained without relying on the delivery driver's experience, and provides value-added services to users.

[1603] Example 3

[1604] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1605] Conventional delivery systems often required redelivery, making it difficult to determine efficient delivery routes. Furthermore, because delivery relied on the driver's experience and skill, it was difficult to maintain a consistent level of delivery. Furthermore, delivery efficiency often declined because real-time traffic information and information on resident absences were not effectively utilized. To solve these issues, a system utilizing more advanced data analysis and AI technology was needed.

[1606] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1607] In this invention, the server includes means for determining a delivery route for the day that reduces the possibility of daily redelivery using a generative AI model, utilizing traffic information data, resident absence / redelivery record data, information on parcels delivered that day, electricity meter information, and route characteristic data from the perspective of area drivers, means for linking the route determined by the generative AI model with a navigation system, means for the user to input delivery information, and means for the server to collect and integrate additional data. This makes it possible to determine an efficient delivery route while reducing the possibility of redelivery and maintaining delivery standards.

[1608] "Traffic information data" refers to data that includes real-time traffic conditions, road congestion, accident information, and so on.

[1609] "Resident absence / redelivery performance data" is data that includes historical information such as the number of times a resident was absent during past deliveries and the number of times redelivery was performed.

[1610] "Today's delivery parcel information" is data including information such as the type and quantity of parcels scheduled to be delivered on that day, and the delivery address.

[1611] "Electricity meter information" is data that indicates the electricity usage status of each resident and is used to infer whether the resident is at home or not.

[1612] "Route characteristics data from the perspective of area drivers" is data that shows the characteristics and points to note of delivery routes in a specific area based on past delivery history and driver experience.

[1613] A "generative AI model" refers to an algorithm or program that uses machine learning and artificial intelligence techniques to calculate the optimal delivery route based on input data.

[1614] A "navigation system" is a system that provides route guidance to drivers, such as a car navigation device installed in a vehicle or a smartphone app.

[1615] "Means for users to input delivery information" refers to the interface or application that drivers use on smartphones or tablet devices to input delivery package information and data on residents' absence / redelivery status.

[1616] "Means for the server to collect and integrate additional data" refers to the function by which the server collects traffic information, electricity meter information, etc. from external data sources, integrates them, and processes them to input them into the AI ​​model.

[1617] This invention is a system for maximizing delivery driver efficiency and reducing the likelihood of redelivery. The system utilizes traffic information data, data on resident absences / redelivery attempts, information on the day's delivery packages, electricity meter information, and route characteristics data from the area driver's perspective, and uses a generative AI model to determine the optimal delivery route.

[1618] The server first receives the delivery package information for the day entered by the user (driver) and the actual data on absences and redelivery requests. Next, the server collects traffic information, electricity meter information, and route characteristics data from the perspective of area drivers. This data is obtained from map service APIs (e.g., Google Maps API), the electric power company's smart meter database, and past route history databases.

[1619] The server combines this data and inputs it into a generative AI model, built using machine learning frameworks such as TensorFlow and PyTorch, which uses historical data and real-time information to calculate the optimal route to reduce the chance of redelivery.

[1620] The calculated optimal route is sent to the navigation system and displayed on the driver's device. The driver then delivers the parcel by following the route displayed on the navigation system. This reduces the possibility of redelivery and enables the delivery level to be maintained.

[1621] As a specific example, a driver in charge of deliveries in a certain area enters "Parcel A, Parcel B, Parcel C" into the system as parcel information for that day's delivery. Additionally, as resident absence / redelivery history data, the driver enters information such as "Resident X has been absent three times in the past, and Resident Y has been redelivered once in the past." The system uses this information, traffic information data obtained from the map service API, electricity meter information obtained from the power company, and past route history data to determine the optimal delivery route using a generative AI model.

[1622] Examples of prompts to input to a generative AI model might include:

[1623] "Delivery package information: Package A, Package B, Package C. Resident absence / redelivery performance data: Resident X was absent three times in the past, and resident Y has had one redelivery in the past. Please calculate the optimal delivery route based on traffic information data, electricity meter information, and route characteristics data from the perspective of area drivers."

[1624] Furthermore, as another embodiment of the present invention, a system is provided in which an emotion engine and a generative AI model work in cooperation with each other. Specifically, the emotion engine recognizes a user's emotions and provides that information to the generative AI model. The generative AI model optimizes delivery routes based on that information. For example, if a user expresses joy, the generative AI model prioritizes deliveries to that user. On the other hand, if a user expresses anger, the generative AI model delays deliveries to that user and prioritizes deliveries to other users. This makes it possible to optimize delivery routes in response to user emotions.

[1625] In this way, the present invention provides a system that utilizes advanced data analysis and AI technology to maximize delivery efficiency and reduce the possibility of redelivery. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[1626] Step 1:

[1627] The user (driver) uses a smartphone or tablet device to enter the delivery package information for the day and the resident's absence / re-delivery record data into a dedicated application. For example, enter "Package A, Package B, Package C" into the application's input form and select information such as "Resident X has been absent three times in the past, and Resident Y has been redelivered once in the past." The entered data is sent to the server.

[1628] Step 2:

[1629] The server receives delivery package information and data on resident absences / redelivery attempts sent by users. Next, the server collects traffic information data, electricity meter information, and route characteristics data from the perspective of area drivers. Specifically, the server calls the map service API to obtain real-time traffic information and accesses the power company's smart meter database to obtain electricity meter information. It also collects route characteristics data from the perspective of area drivers from a database of past route history. This data is integrated within the server.

[1630] Step 3:

[1631] The server preprocesses the integrated data and converts it into a format that can be input to the generative AI model. For example, it converts the data into JSON format and inputs it into the generative AI model. Specifically, it generates JSON data like the following:

[1632] json

[1633] {

[1634] "deliveries": ["Delivery A", "Delivery B", "Delivery C"],

[1635] "absence_data": {"Resident X": 3, "Resident Y": 1},

[1636] "traffic_data": {...},

[1637] "meter_data": {...},

[1638] "route_features": {...}

[1639] }

[1640] This data is fed into a generative AI model.

[1641] Step 4:

[1642] The server inputs the integrated data into a generative AI model to calculate the optimal delivery route. The generative AI model calculates the optimal route that reduces the possibility of redelivery based on past data and real-time information. For example, it generates a route such as "Route 1: Package A -> Package B -> Package C." The calculation results are stored on the server.

[1643] Step 5:

[1644] The server sends the calculated optimal delivery route to the navigation system. Specifically, it uses the navigation system's API to send the route information and display it on the driver's device. For example, the navigation system might display information such as "Route 1: Package A -> Package B -> Package C."

[1645] Step 6:

[1646] The user (driver) delivers by following the optimal delivery route displayed on the navigation system. For example, following the instructions of the navigation system, deliveries are made in the order of "delivering package A first, then package B, and finally package C." This reduces the possibility of redelivery and makes it possible to maintain the delivery level.

[1647] (Application example 3)

[1648] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1649] In conventional delivery systems, the possibility of redelivery was high, making it difficult to determine efficient delivery routes. Furthermore, delivery routes were not optimized taking into account user emotions, making it difficult to improve user satisfaction. In particular, in food delivery, delivery delays and redeliveries have a significant impact on customer satisfaction, so these issues must be resolved.

[1650] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1651] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by the AI ​​with a car navigation system, means for an emotion engine to recognize user emotions and provide that information to the AI, means for optimizing the delivery route according to the user's emotions, and means for displaying the optimized delivery route on a smartphone navigation app.This reduces the possibility of redelivery and makes it possible to optimize the delivery route according to the user's emotions.

[1652] "Traffic information data" refers to information about traffic that affects delivery routes, such as road congestion, traffic accidents, and construction information.

[1653] "Resident absence / redelivery performance data" is a record of past deliveries during which residents were absent and redeliveries were made.

[1654] "Today's delivery parcel information" is detailed information about parcels to be delivered on that day, including the delivery address, delivery time slot, and type of parcel.

[1655] "Electricity meter information" is data that indicates the usage status of the electricity meter at each delivery destination, and is information that is used to estimate whether residents are at home.

[1656] "Route characteristics data from the perspective of area drivers" is information on route characteristics, points to note, and efficient delivery methods as shared by drivers who are familiar with the delivery area.

[1657] "AI" stands for artificial intelligence, an algorithm or system that calculates optimal delivery routes based on data.

[1658] A "car navigation system" is a navigation system installed in a vehicle that guides the driver to the optimal route.

[1659] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's behavior based on that information.

[1660] A "smartphone navigation app" is a navigation application that runs on a smartphone and is software that displays the optimal route for the user.

[1661] The following system configuration and processing procedure will be described as an embodiment of the present invention.

[1662] System Configuration

[1663] This system is configured using the following hardware and software.

[1664] Hardware

[1665] server

[1666] Smartphone

[1667] Car navigation system installed in a vehicle

[1668] software

[1669] AI libraries (e.g. RouteOptimizer)

[1670] Emotion engine (e.g., EmotionEngine)

[1671] Smartphone navigation app

[1672] Processing steps

[1673] 1. Enter delivery information

[1674] Using a terminal (smartphone), the delivery driver inputs information about the parcel to be delivered that day, including the delivery address, delivery time slot, and type of parcel.

[1675] 2. Obtaining traffic information

[1676] The server retrieves the latest traffic data from the traffic information API, including road congestion, traffic accidents, and construction information.

[1677] 3. Obtaining electricity meter information

[1678] The server obtains electricity meter information for each delivery destination and uses this information to estimate whether residents are at home.

[1679] 4. Delivery route optimization

[1680] The server uses an AI library (Route Optimizer) to calculate the optimal delivery route based on delivery information, traffic information, electricity meter information, data on residents' absence / redelivery history, and route characteristics data from the perspective of area drivers.

[1681] 5. Use of Emotion Engine

[1682] The server uses an emotion engine to recognize the user's emotions, which then provides the AI ​​with information on the user's emotions and is reflected in optimizing delivery routes.

[1683] 6. View optimized route

[1684] The optimized delivery route is displayed on the smartphone navigation app, and the driver follows this route to make the delivery.

[1685] Specific examples

[1686] For example, suppose one of the delivery destinations is "Address 1," and past data indicates that the resident is often out in the morning. Based on this information, the AI ​​will include "Address 1" in the afternoon delivery route. If the emotion engine also recognizes that the resident of "Address 2" is happy, the AI ​​will prioritize "Address 2" in the delivery route.

[1687] Prompt Sentence Examples

[1688] "Generate optimal delivery routes taking into account the emotions of residents in the delivery destination. Adjust the route based on the user's emotions based on delivery information, traffic information, and electricity meter information."

[1689] The above is an embodiment of the present invention. This system reduces the possibility of redelivery and enables optimization of delivery routes according to the user's emotions.

[1690] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1691] Step 1:

[1692] Using a terminal (smartphone), the delivery driver inputs information about the parcels to be delivered that day. The input information includes the delivery address, delivery time slot, and type of parcel. This information is sent to the server and stored in a database.

[1693] Step 2:

[1694] The server obtains the latest traffic data from the traffic information API. The obtained data includes road congestion, traffic accidents, construction information, etc. The server analyzes this data and extracts factors that affect delivery routes.

[1695] Step 3:

[1696] The server obtains electricity meter information for each delivery destination. Using the electricity meter information API, it obtains electricity usage information for each address and estimates whether residents are at home. This information is also stored in the database.

[1697] Step 4:

[1698] The server retrieves data on resident absences and redelivery attempts from the database, and analyzes each resident's absence time and redelivery frequency based on past delivery data.

[1699] Step 5:

[1700] The server acquires route characteristic data from the perspective of area drivers. This is information on route characteristics, points to note, and efficient delivery methods from drivers who are familiar with the delivery area.

[1701] Step 6:

[1702] The server uses an AI library (RouteOptimizer) to calculate the optimal delivery route based on delivery information, traffic information, electricity meter information, data on residents' absences / re-deliveries, and route characteristics data from the perspective of area drivers. The AI ​​receives this data as input and outputs the optimal route to reduce the possibility of re-delivery.

[1703] Step 7:

[1704] The server uses an emotion engine to recognize the user's emotions. The emotion engine provides the AI ​​with the user's emotional information and reflects it in optimizing delivery routes. For example, if a user is happy, delivery to that user will be prioritized.

[1705] Step 8:

[1706] The server sends the optimized delivery route to the smartphone's navigation app, which the driver uses to make the delivery along the optimized route. The navigation app provides real-time route guidance to support the driver.

[1707] These are the specific processing steps of this system, which reduces the possibility of redelivery and enables delivery routes to be optimized according to the user's emotions.

[1708] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1709] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1710] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1711] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1712] [Third embodiment]

[1713] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1714] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1715] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1716] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1717] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1718] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1719] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1720] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1721] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1722] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1723] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1724] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1725] "Example 1"

[1726] One aspect of the present invention is a delivery route determination system. This system collects traffic information data, data on resident absences / redelivery attempts, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers, and AI determines the optimal delivery route based on this data. Specifically, the AI ​​determines the delivery route taking into account resident absence times and redelivery attempt history data in order to reduce the possibility of redelivery.

[1727] "Example 2"

[1728] Furthermore, the route determined by AI is displayed in conjunction with the car navigation system. This allows the driver to make deliveries by following the optimal route determined by AI. Specifically, the route determined by AI is displayed on the car navigation screen, and the driver delivers by following that route. This makes it possible to maintain delivery standards regardless of whether the driver is a veteran or a novice.

[1729] "Example 3"

[1730] As a concrete example, a driver in charge of deliveries in a certain area inputs information about the day's deliveries and data on residents' absences / re-deliveries into the system. The system uses this information, traffic information data, electricity meter information, and route characteristics data from the area driver's perspective to determine the optimal delivery route using AI. This route is displayed on the car navigation system, and the driver follows it to make the delivery. This reduces the possibility of re-delivery and makes it possible to maintain delivery standards.

[1731] The processing flow of each embodiment will be described below.

[1732] "Example 1"

[1733] Step 1: The delivery route determination system collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[1734] Step 2: Based on the collected data, the AI ​​determines the optimal delivery route. Specifically, to reduce the possibility of redelivery, the AI ​​determines the delivery route by taking into account the time when residents are absent and past redelivery data.

[1735] "Example 2"

[1736] Step 1: The route determined by the AI ​​is displayed in conjunction with the car navigation system.

[1737] Step 2: The driver follows the instructions on the car navigation system to make the delivery. This allows the delivery level to be maintained regardless of whether the driver is a veteran or a novice.

[1738] "Example 3"

[1739] Step 1: A driver in charge of deliveries in a certain area enters the delivery package information for the day and the actual data on residents' absence / re-delivery into the system.

[1740] Step 2: The system uses this information, traffic data, electricity meter information, and route characteristics data from the perspective of area drivers to determine the optimal delivery route using AI.

[1741] Step 3: This route is displayed on the car navigation system and the driver follows it to make the delivery, reducing the chance of redelivery and maintaining delivery levels.

[1742] Example 1

[1743] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1744] Conventional delivery route determination systems had a high probability of redelivery, making efficient delivery difficult. Furthermore, they were unable to determine the optimal route taking into account traffic information and whether residents were at home, resulting in poor delivery efficiency. Another issue was the discrepancy in delivery quality between veteran and novice drivers.

[1745] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1746] In this invention, the server includes means for collecting traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers, means for preprocessing the collected data, means for training a machine learning model based on the preprocessed data, means for receiving delivery requests from users, means for calculating an optimal delivery route using the trained machine learning model, means for transmitting the calculated optimal route to a terminal, and means for displaying the route information received by the terminal to the user. This reduces the possibility of redelivery and enables efficient delivery route determination. It also allows for the maintenance of delivery quality between veteran and novice drivers.

[1747] "Traffic information data" refers to data that indicates real-time traffic conditions and road congestion.

[1748] "Resident absence / redelivery performance data" is data that indicates the time when residents were absent during past deliveries and the history of redeliveries.

[1749] "Today's delivery parcel information" is data showing detailed information about parcels to be delivered on the same day.

[1750] "Electricity meter information" is data on electricity usage that is used to estimate whether residents are at home.

[1751] "Route characteristics data from the perspective of area drivers" is data on route characteristics based on feedback from drivers.

[1752] "Means of collection" refers to the methods and devices used to obtain the required data.

[1753] "Preprocessing means" refers to methods or devices used to convert collected data into a form suitable for analysis or model training.

[1754] "Means for training a machine learning model" refers to a method or apparatus for training a machine learning algorithm using collected and pre-processed data.

[1755] "Means for receiving a delivery request" refers to a method or device for receiving a delivery request from a user.

[1756] "Means for calculating optimal delivery routes" refers to a method or apparatus for using a trained machine learning model to calculate the most efficient delivery route.

[1757] "Means for transmitting to the terminal" refers to a method or device for transmitting the calculated delivery route to the user's terminal.

[1758] The term "means for displaying the route information received by the terminal to the user" refers to a method or device for visually presenting the delivery route information received by the terminal to the user.

[1759] This invention relates to a delivery route determination system that determines the optimal delivery route by utilizing traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristic data from the perspective of area drivers.

[1760] Generating a Program

[1761] The system's programs are generated using Python, with key libraries including requests for data collection, pandas for data processing, and scikit-learn and TensorFlow for building machine learning models.

[1762] Program processing explanation

[1763] The server collects the following data:

[1764] Traffic data: Use common map APIs to get real-time traffic information.

[1765] Resident absence / redelivery performance data: Obtain past delivery performance data from the delivery company database.

[1766] Today's delivery package information: Obtain today's delivery list from the delivery management system.

[1767] Electricity meter information: Use the smart meter API to obtain electricity usage data to infer whether residents are at home.

[1768] Route characteristics data from the perspective of area drivers: Feedback from drivers is collected and route characteristics are stored in a database.

[1769] After collecting this data, the server uses pandas to preprocess the data, specifically by filling in missing values ​​and normalizing the data.

[1770] The server then uses scikit-learn and TensorFlow to build a machine learning model that optimizes delivery routes by taking into account the time residents are away and past redelivery attempts to reduce the likelihood of redelivery.

[1771] After the model is trained, the server calculates the optimal delivery route and sends it to the device each time a new delivery request comes in.

[1772] Examples and prompts

[1773] As a concrete example, consider the following scenario:

[1774] The user inputs a new delivery request into the system. For example, the user might input "Make 10 deliveries within Tokyo on October 10, 2023." Based on this information, the server calculates the optimal delivery route and sends it to the device.

[1775] Example prompts to input to a generative AI model:

[1776] "I plan to make 10 deliveries within Tokyo on October 10, 2023. Please calculate the optimal delivery route taking into account traffic information data, data on residents' absence / redelivery attempts, information on the delivery packages for that day, electricity meter information, and route characteristics data from the perspective of area drivers."

[1777] By inputting this prompt into the generative AI model, the AI ​​will calculate the optimal delivery route and provide it to the user.

[1778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1779] Step 1:

[1780] The server collects traffic information data, data on residents' absence / redelivery records, information on the day's delivery packages, electricity meter information, and route characteristics data from the perspective of area drivers.

[1781] Input: Traffic information API, delivery company database, delivery management system, smart meter API, driver feedback

[1782] Output: Various collected data

[1783] Specific operation: The server calls the traffic information API to obtain real-time traffic information, obtains past delivery performance data from the delivery company's database, obtains the delivery list for the day from the delivery management system, obtains electricity usage data using the smart meter API, and collects feedback from drivers and stores it in the database.

[1784] Step 2:

[1785] The server pre-processes the collected data.

[1786] Input: Various collected data

[1787] Output: Preprocessed data

[1788] What it does: The server uses the pandas library to impute missing values ​​in the data, normalize data of different scales, and combine data from different sources into a single data frame.

[1789] Step 3:

[1790] The server trains a machine learning model based on the preprocessed data.

[1791] Input: Preprocessed data

[1792] Output: A trained machine learning model

[1793] Specific operation: The server builds a machine learning model using scikit-learn or TensorFlow, selects features, and chooses the optimal algorithm (e.g., random forest, neural network) to train the model.

[1794] Step 4:

[1795] A user enters a new delivery request into the system.

[1796] Input: Delivery request (e.g., "Make 10 deliveries in Tokyo on October 10, 2023")

[1797] Output: Delivery request data

[1798] Specific operation: The user inputs a delivery request into the system interface. The server receives this request and stores it in the database.

[1799] Step 5:

[1800] The server uses a trained machine learning model to calculate the optimal delivery route.

[1801] Input: Delivery request data, trained machine learning model

[1802] Output: Optimal delivery route

[1803] What it does: The server converts delivery request data into a format that can be fed into the model, and then uses a trained machine learning model to predict the optimal delivery route.

[1804] Step 6:

[1805] The server transmits the calculated optimum route to the terminal.

[1806] Input: Optimal delivery route

[1807] Output: Route information sent to the device

[1808] Specific operation: The server calls an API to send the calculated optimal route to the terminal, and sends the route information to the terminal.

[1809] Step 7:

[1810] The terminal displays the received route information to the user.

[1811] Input: Route information sent to the device

[1812] Output: Route information displayed to the user

[1813] Specific operation: The terminal provides an interface for visually displaying the received route information to the user.

[1814] (Application example 1)

[1815] Next, a description will be given of 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 headset type terminal 314 will be referred to as a "terminal."

[1816] Conventional delivery systems were unable to fully utilize traffic information and data on residents' absence, resulting in frequent redelivery. Furthermore, delivery routes were not optimized sufficiently, making it difficult to predict delivery times. This resulted in issues such as reduced delivery efficiency and lower customer satisfaction.

[1817] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1818] In this invention, the server includes means for using traffic information data, resident absence / redelivery record data, delivery package information for the day, electricity meter information, and route characteristic data from the perspective of area drivers to determine a delivery route for the day that reduces the possibility of daily redelivery, means for linking the route determined by AI with a car navigation system, means for optimizing the delivery route using an application installed on a smartphone, and means for predicting delivery times that reflect real-time traffic information. This makes it possible to reduce the frequency of redelivery and improve delivery efficiency.

[1819] "Traffic information data" refers to information about traffic collected in real time, such as road congestion, traffic accidents, and construction information.

[1820] "Resident absence / redelivery record data" is data that indicates the time periods when a particular resident was absent in the past and the history of redelivery requests.

[1821] "Today's delivery parcel information" is detailed information about parcels scheduled to be delivered on that day, and is data including the type of parcel, the quantity, the delivery address, and so on.

[1822] "Electricity meter information" is data that indicates the electricity usage status of residents and is used to infer whether residents are at home or not.

[1823] "Route characteristics data from the perspective of area drivers" is data that shows the route characteristics and points of caution that drivers in charge of a specific area have empirically recognized.

[1824] "Method of deciding using AI" is a method of determining the optimal delivery route using artificial intelligence.

[1825] "Means for linking with car navigation" refers to a method for linking the determined delivery route with the in-car navigation system.

[1826] The "application installed on a smartphone" is software that runs on a smartphone and is used to optimize delivery routes and predict delivery times.

[1827] "Means for predicting delivery time by reflecting real-time traffic information" refers to a method for predicting the time required for delivery by taking into account current traffic conditions.

[1828] The following system configuration will be described as an embodiment of the present invention.

[1829] System Configuration

[1830] The system consists of a server, smartphone, car navigation system, and various data sources. The server collects traffic information data, data on absences and redelivery requests, information on the parcels delivered that day, electricity meter information, and route characteristics data from the perspective of area drivers. Based on this data, AI determines the optimal delivery route.

[1831] Hardware and software used

[1832] Hardware: Servers, smartphones, car navigation systems

[1833] Software: Python, Pandas (data processing), Scikit-learn (machine learning), Geopy (geographic information processing)

[1834] Data processing and calculation

[1835] The server pro...

Claims

1. A method for using artificial intelligence to determine a delivery route for the day that reduces the possibility of daily redelivery by utilizing traffic information data, data on residents' absence or redelivery records, information on parcels delivered that day, information on electricity meters, and data on route characteristics from the perspective of area drivers; and A means for linking the route determined by the artificial intelligence with the vehicle navigation system; A means for collecting emotion data, such as voice, text, facial expressions, and physical movements, through interactions with users; A means to analyze the collected emotion data and re-optimize delivery routes based on the results of the analysis; and A system including:

2. 2. The system according to claim 1, wherein the means for determining using artificial intelligence determines a delivery route taking into account the time when residents are absent or past data on redelivery in order to reduce the possibility of redelivery.

3. 2. The system of claim 1, wherein the means for interfacing with the vehicle navigation system maintains delivery levels regardless of the experience of area drivers.

Images