system

Abstract

Provide a system. A means for collecting and analyzing traffic information; a means of collecting and analyzing inventory data; a means for performing a demand forecast; A means for automatically generating an optimal delivery plan based on the analysis and prediction results; A means for outputting a delivery plan; A system including:

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] In recent years, the logistics industry has been faced with increasing demand diversification and the need to improve delivery efficiency. In particular, challenges include changes in traffic conditions, increasingly complex inventory management, and the difficulty of demand forecasting. These factors cause delays and excessive costs, hindering efficient delivery. Therefore, there is a need for a system that can automatically generate efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means: a system including means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, and means for outputting the delivery plan. This system makes it possible to manage real-time traffic conditions, inventory status, and demand forecasts in an integrated manner, and automatically generate efficient delivery plans.

[0006] "Traffic information" refers to data including road congestion status, accident information, construction information, etc., acquired in real time.

[0007] "Inventory data" is information that indicates the inventory status of products in warehouses and stores.

[0008] "Demand forecasting" is the process of predicting future demand based on past data, seasonality, event information, etc.

[0009] "Analysis" is the process of converting collected data into understandable information and identifying patterns and trends.

[0010] A "delivery plan" is a plan that compiles routes and schedules for efficiently delivering products.

[0011] "Automatic generation" refers to the system independently creating plans and data without human intervention.

[0012] "Output" refers to providing the analysis results and optimized delivery plans to the user or terminal.

[0013] A "system" is a collection of multiple elements and functions integrated to achieve a specific purpose. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention relates to a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts. This system utilizes a server and terminals to improve overall delivery efficiency.

[0036] Explanation of program processing

[0037] Collection and analysis of real-time traffic information

[0038] 1. The server collects real-time traffic information.

[0039] The server calls the traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. This data is updated according to the frequency of distribution and stored on the server.

[0040] 2. The server analyzes the traffic data.

[0041] Using the collected traffic data, the server evaluates the required travel time and congestion level of each route, and then uses an algorithm to analyze this data and calculate the optimal delivery route.

[0042] 3. The device notifies the driver of the optimal route.

[0043] The server calculates the optimal route and delivers it to the device, which then notifies the driver's application in real time. The device then displays detailed route information via push notifications and in-app messages.

[0044] Inventory data collection and analysis

[0045] 1. The server collects inventory data.

[0046] The server calls an API to obtain inventory information from the inventory management systems of each warehouse and store, allowing for real-time inventory status.

[0047] 2. The server parses the inventory data.

[0048] Analyze collected inventory data to identify which items are low or need to be replenished. If necessary, create a list of urgent items.

[0049] 3. The server reflects this in the delivery plan.

[0050] Based on the results of the inventory data analysis, the server adds inventory replenishment routes to the delivery plan, which is reflected in the delivery route and sent to the terminal.

[0051] Generate demand forecasts and delivery plans

[0052] 1. The server collects past sales data.

[0053] The server retrieves past sales data and seasonal data from the database and uses this as the basis for demand forecasting.

[0054] 2. The server makes a demand forecast.

[0055] Using this data, AI algorithms predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[0056] 3. The server generates an optimal delivery plan.

[0057] Based on the demand forecast results, the system calculates how many products to deliver to which stores and when, and generates an efficient delivery schedule.

[0058] 4. The device notifies the driver of the delivery plan.

[0059] The generated delivery plan is sent to the terminal, where the driver can view it through the application. The terminal is updated in real time, optimizing the driver's behavior.

[0060] Specific examples

[0061] Consider a delivery company that needs to deliver products to multiple stores during the morning rush hour. First, the server collects real-time road data from a traffic information API and analyzes congestion levels. Next, it retrieves inventory information from warehouses and store inventory management systems to identify products that are low in stock. It then performs demand forecasting based on past sales data, predicting that certain products are likely to be in short supply ahead of a weekend sale.

[0062] Based on this data, the server generates optimal delivery routes and creates detailed delivery plans that take into account inventory replenishment and demand forecasts. The terminal then notifies the driver of this information, ensuring efficient delivery. In this way, the system of the present invention integrates real-time information and data analysis to achieve efficient logistics.

[0063] The processing flow will be explained below.

[0064] Collection and analysis of real-time traffic information

[0065] Step 1:

[0066] The server periodically calls the traffic information API to obtain the latest traffic data, including road congestion status, accident information, and construction information.

[0067] Step 2:

[0068] The server stores the acquired traffic data in a database, which is used in later analysis steps.

[0069] Step 3:

[0070] The server analyzes the traffic data and calculates the travel time and congestion level for each delivery route using algorithms and traffic prediction models.

[0071] Step 4:

[0072] The server calculates the optimal delivery route, compares the travel time of each route, and selects the most efficient route.

[0073] Step 5:

[0074] The device receives the optimal route information from the server and notifies the driver via push notification or in-app message, displaying detailed route information.

[0075] Inventory data collection and analysis

[0076] Step 1:

[0077] The server calls an API that collects inventory data from each warehouse or store's inventory management system, including product quantities and replenishment needs.

[0078] Step 2:

[0079] The server stores the collected inventory data in a database, which is updated in real time.

[0080] Step 3:

[0081] The server analyzes the inventory data to determine which items are low in stock and creates a list of items that are low in stock or need to be replenished.

[0082] Step 4:

[0083] The server automatically generates a delivery plan based on the items in short supply, prioritizing items with high urgency and adding those stores or warehouses to the delivery route.

[0084] Step 5:

[0085] The device notifies the driver of updated delivery plans, including schedules and pickup lists, which can be viewed within the app.

[0086] Generate demand forecasts and delivery plans

[0087] Step 1:

[0088] The server retrieves past sales data, seasonal data, and event information from the database.

[0089] Step 2:

[0090] Based on the data acquired by the server, demand forecasts are made using AI algorithms. The forecasting model learns from past data and calculates future demand.

[0091] Step 3:

[0092] The server automatically generates an optimal delivery plan based on the demand forecast results, calculating how many items to deliver to which stores and when.

[0093] Step 4:

[0094] The server then combines the delivery plan into an optimal route and finalizes the plan.

[0095] Step 5:

[0096] The device receives an optimized delivery plan from the server and notifies the driver, allowing the driver to make efficient deliveries based on information updated in real time.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] In the modern logistics industry, it is extremely important to create efficient delivery plans. However, it is difficult to collect and analyze a wide range of information, such as traffic information, inventory data, and demand forecasts, in real time, and integrate them to calculate optimal delivery routes. There is also a need for a method to quickly notify drivers of delivery plans that take this information into account. A system that can solve these problems is needed.

[0100] 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.

[0101] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for collecting traffic data in real time, means for calculating an optimal delivery route using the traffic data, means for acquiring data from inventory management systems of each warehouse and store, means for identifying shortages in inventory data and reflecting them in the delivery plan, means for collecting past sales data and performing demand forecasting, and means for notifying the terminal of the generated delivery plan. This enables real-time information collection and analysis, and efficient generation and notification of delivery plans.

[0102] "Traffic information" refers to data relating to traffic conditions such as road congestion, accident information, and construction information.

[0103] "Inventory data" is information regarding the inventory status of products at each warehouse and store.

[0104] "Demand forecasting" refers to the algorithms and results that predict future demand based on past sales data and seasonal data.

[0105] "Delivery plan" refers to a schedule including the order and route of product delivery, which is automatically generated based on collected and analyzed data.

[0106] "Real-time" means collecting, analyzing, and processing data at the same speed as the real world.

[0107] "API" stands for Application Programming Interface, a mechanism for exchanging data and functions between software programs.

[0108] An "analytical algorithm" is a computational method for analyzing data and extracting useful information for a specific purpose.

[0109] A "terminal" is a device for inputting and outputting information, and in this system specifically refers to a device on which the application used by the driver is installed.

[0110] "Sales data" refers to data relating to past transactions and product sales.

[0111] This invention relates to a system that automatically generates efficient delivery plans based on real-time collection and analysis of traffic information, inventory data, demand forecasts, etc. This system mainly functions using a server and terminals.

[0112] The server first collects traffic information. Specifically, it uses a traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. For this, it can use the Google (registered trademark) Maps API, etc. The obtained traffic data is stored in a PostgreSQL database.

[0113] Next, the server analyzes the collected traffic data. Based on the traffic data, it evaluates the required time and congestion level of each route and calculates the optimal delivery route using the Dijkstra algorithm or A algorithm. The results of this analysis are saved in JSON format and later sent to the terminal.

[0114] The server also retrieves inventory data from each warehouse and store's inventory management system. Specifically, it uses APIs to collect real-time inventory status from systems such as SAP and Oracle SCM. The retrieved inventory data is analyzed to determine whether a specific item is out of stock. This creates a list of items that are in short supply.

[0115] Additionally, the server collects past sales data to forecast demand. To do this, it retrieves data from a database or a third-party sales database (e.g., Amazon Web Services or Google BigQuery). It then uses AI algorithms (e.g., TENSORFLOW® or PyTorch) to predict future demand from the past data. This prediction also takes into account the effects of seasonal fluctuations and specific events.

[0116] Based on the results of the analysis and predictions above, the server automatically generates an optimal delivery plan. The server calculates how many products to deliver to which stores and when, creating an efficient schedule. The generated delivery plan is sent to the terminal in real time.

[0117] The terminal is responsible for notifying the driver of the delivery plan. The optimal route information and delivery plan sent from the server are displayed by the terminal's application. The driver can use this information to make deliveries along the optimal route. The terminal also supports real-time updates, allowing it to quickly respond to changes in traffic and inventory conditions.

[0118] As a concrete example, consider the case where a delivery company makes deliveries during the morning rush hour. The company uses a server to collect traffic information from the Google Maps API, analyzes it, and calculates the optimal route. It obtains inventory data from SAP and Oracle SCM and identifies products that are in short supply. It also uses an AI algorithm to forecast demand based on past sales data, predicting that certain products are likely to be in short supply. Based on this data, the server generates an optimal delivery plan and sends it to the terminal. The driver can then follow the instructions on the terminal to make efficient deliveries.

[0119] Examples of prompts for a generative AI model include:

[0120] "Please give me some prompts for building an AI algorithm that automatically generates optimal delivery route plans using real-time traffic information, inventory data, and demand forecasts in a logistics delivery system."

[0121] In this way, the system of the present invention integrates real-time information and data analysis to achieve more efficient logistics.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] Collection of traffic information

[0125] Input: Traffic request from Google Maps API

[0126] Specific operation: The server accesses the Google Maps API at specified intervals to obtain the latest road congestion information, accident information, construction information, etc.

[0127] Output: Traffic information dataset

[0128] A concrete example: A server calls the Google Maps API every minute and stores the collected traffic data in a PostgreSQL database.

[0129] Step 2:

[0130] Traffic data analysis

[0131] Input: Traffic information dataset collected in step 1

[0132] How it works: The server analyzes the stored traffic data and evaluates the travel time and congestion level of each route.

[0133] Output: Analyzed traffic information (travel time, congestion level, etc.)

[0134] Specific example: The server uses Dijkstra algorithm to calculate the shortest route for each delivery route and also evaluates the congestion level.

[0135] Step 3:

[0136] Calculating the best delivery route

[0137] Input: Traffic information parsed in step 2

[0138] Specific operation: The server uses algorithm A to calculate the optimal delivery route based on traffic data.

[0139] Output: Optimal delivery route information

[0140] Specific example: The server saves the calculation results in JSON format and delivers them to the device later.

[0141] Step 4:

[0142] Inventory data collection

[0143] Input: API requests from inventory management systems at each warehouse and store

[0144] Specific operation: The server uses the API of inventory management systems such as SAP and Oracle SCM to obtain real-time inventory data for each warehouse and store.

[0145] Output: Inventory dataset

[0146] Specific example: The server periodically collects data from each warehouse's system and stores it in a database.

[0147] Step 5:

[0148] Inventory data analysis

[0149] Input: Inventory dataset collected in step 4

[0150] What happens: The server analyzes the collected inventory data and identifies which items are in short supply.

[0151] Output: List of missing items

[0152] Specific example: The server checks the stock level of each product and generates a list of products that are below a threshold.

[0153] Step 6:

[0154] Demand forecasting

[0155] Input: Historical sales data from a sales database

[0156] How it works: The server collects past sales data and uses AI algorithms (e.g., TensorFlow) to predict future demand.

[0157] Output: Demand forecast data

[0158] Specific example: The server uses a TensorFlow model to predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[0159] Step 7:

[0160] Generate a delivery plan

[0161] Input: Optimal delivery route information in Step 3, Shortage product list in Step 5, Demand forecast data in Step 6

[0162] Specific operation: The server integrates this data and automatically generates an efficient delivery plan.

[0163] Output: Delivery plan

[0164] Specific example: The server calculates how many items to deliver to which stores and when, and saves the delivery plan as a list.

[0165] Step 8:

[0166] Delivery plan notification

[0167] Input: The shipping plan generated in step 7

[0168] Specific operation: The server sends the generated delivery plan to the terminal.

[0169] Output: Delivery plan notified to the terminal

[0170] A concrete example: Drivers can check their trip plans through an application on their device and receive real-time updates.

[0171] In this way, the system uses the data collected and analyzed at each step to automatically generate optimal delivery plans and achieve efficient logistics.

[0172] (Application example 1)

[0173] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0174] Conventional food delivery systems face challenges in streamlining delivery plans due to the difficulty of managing fluctuations in traffic information and inventory data in real time. Demand forecasts are also inadequate, leading to excess or shortages of inventory. This leads to problems such as reduced work efficiency for delivery drivers and lower customer satisfaction.

[0175] 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.

[0176] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for outputting the delivery plan, means for performing real-time delivery updates, and means for sending notification information to the terminal, thereby integrating real-time information and enabling the automatic generation of an efficient delivery plan.

[0177] "Traffic information" is data about current road conditions, such as road congestion, accident information, and construction information.

[0178] "Inventory data" refers to data about the current quantity of goods or materials in a warehouse or store.

[0179] "Demand forecasting" is a method of predicting future demand for products and services based on past sales data and seasonal data.

[0180] "Distribution planning" refers to the planning of routes and schedules for efficiently delivering products, taking into account demand forecasts and inventory status.

[0181] "Real-time updates" refers to the process of updating the system to reflect current situations and data immediately.

[0182] "Notification information" refers to information provided in real time, such as alerts and instructions sent from the server to the terminal.

[0183] A "terminal" is a device used to receive information, such as a smartphone or tablet.

[0184] A "server" is a computer system that collects, analyzes, stores, and provides the results to other devices.

[0185] "API" stands for Application Program Interface, a mechanism for exchanging data and functions between different software.

[0186] The system for implementing this invention is mainly composed of a server and a terminal. The server mainly collects data, analyzes it, makes predictions, and generates plans, while the terminal notifies the driver of this information.

[0187] Explanation of program processing

[0188] 1. Collection and analysis of real-time traffic information

[0189] The server uses Google Maps API and HERE API to collect real-time traffic information. The collected data includes road congestion, accident information, construction information, etc. This data is analyzed to evaluate the required time and congestion level for each route.

[0190] 2. Inventory data collection and analysis

[0191] The server retrieves inventory data from restaurant inventory management systems via an API. The collected data is used to understand the current inventory status and identify which menu items are in short supply.

[0192] 3. Demand forecasting

[0193] The server collects past order data and seasonal data and uses AI algorithms (e.g., TensorFlow) to forecast demand. This forecast predicts future demand and determines which products will be needed at what time.

[0194] 4. Generating and notifying a delivery plan

[0195] The server integrates traffic information, inventory data, and demand forecasts to generate an optimal delivery plan. The plan includes delivery schedules and routes to ensure efficient delivery. This plan is updated in real time and sent to the driver's device via push notifications and in-app messages.

[0196] Specific hardware and software names used

[0197] Hardware: Smartphone (iOS or ANDROID (registered trademark) device)

[0198] software:

[0199] Real-time traffic information API: Google Maps API, HERE API

[0200] Inventory Data Management: RESTful API

[0201] AI algorithm: TensorFlow (demand forecasting)

[0202] Database: Firebase or AWS® RDS

[0203] Push notification service: Firebase Cloud Messaging

[0204] Specific examples

[0205] For example, when delivering pizza on a Friday night, the server operates as follows: First, the server obtains real-time traffic information from the Google Maps API and analyzes whether major roads are congested. At the same time, data obtained from the restaurant's inventory management system reveals that there is a shortage of pizza cheese. The AI ​​uses past data to forecast demand and predicts that demand for pizza will peak on Friday night.

[0206] Based on this information, the server generates optimal delivery routes and inventory replenishment routes and notifies the drivers. Drivers can then check the latest delivery routes and schedules on their smartphone apps, enabling them to deliver efficiently.

[0207] Prompt Sentence Examples

[0208] Program Name: FoodMaster

[0209] Use: Automatic generation of efficient delivery plans for food delivery

[0210] function:

[0211] 1. Collect and analyze real-time traffic information using Google Maps API

[0212] 2. Collect and analyze inventory data from restaurant inventory management systems

[0213] 3. Demand forecasting using past data using TensorFlow

[0214] 4. Automatically generate and notify optimal routes and delivery schedules using Firebase

[0215] 5. Push notifications and real-time updates in the app

[0216] Input data:

[0217] Traffic information API response data

[0218] Inventory information from restaurant inventory management systems

[0219] Historical Order Data

[0220] Output data:

[0221] Delivery route and schedule notifications

[0222] Inventory replenishment notifications to restaurants

[0223] prompt:

[0224] "Real-time traffic information," "Inventory management," "AI demand forecasting," "Optimal route calculation," "Firebase notifications"

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] The server collects real-time traffic information using the Google Maps API and HERE API. Specifically, the server calls the API to obtain road congestion status, accident information, construction information, etc., and stores the response data. This data is used to evaluate the travel time and congestion level of each road segment.

[0228] Input: Traffic information API request

[0229] Output: Response data such as congestion status, accident information, construction information, etc.

[0230] Step 2:

[0231] The server analyzes the collected traffic information. Specifically, it uses algorithms to calculate the travel time and congestion level of each route. For example, if a road is congested, this information can be used to identify routes that drivers should avoid.

[0232] Input: Collected traffic information data

[0233] Output: Travel time and congestion data for each route

[0234] Step 3:

[0235] The server retrieves inventory data from the restaurant's inventory management system via an API. Specifically, the server sends a request to the restaurant's inventory system to understand the current inventory status and saves the response data. This allows the server to identify which menu items are in short supply.

[0236] Input: API request to inventory management system

[0237] Output: Stock status response data

[0238] Step 4:

[0239] The server analyzes the acquired inventory data and creates a list of items that need to be replenished. For example, if there is a shortage of pizza cheese, it adds that item to the list as a high-urgency item to be replenished.

[0240] Input: Retrieved inventory data

[0241] Output: A list of products that need to be replenished

[0242] Step 5:

[0243] The server performs demand forecasting based on past order data and seasonal data. Specifically, it uses AI algorithms (e.g., TensorFlow) to predict future demand. This forecast also takes into account seasonal fluctuations and the impact of specific events.

[0244] Input: Past order data, seasonal data

[0245] Output: Future demand forecast data

[0246] Step 6:

[0247] The server integrates traffic information, inventory data, and demand forecast results to generate an optimal delivery plan. Specifically, it uses algorithms to calculate optimal delivery routes and schedules.

[0248] Input: Traffic information, inventory data, demand forecast data

[0249] Output: Delivery plan (optimal delivery route and schedule)

[0250] Step 7:

[0251] The server updates the generated delivery plan in real time and sends a push notification to the driver's device using Firebase Cloud Messaging. The driver can then check the latest delivery plan in the app.

[0252] Input: Generated dispatch plan

[0253] Output: Notification data sent to the device (push notifications and in-app updates)

[0254] 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.

[0255] This invention combines a system that integrates real-time traffic information, inventory data, and demand forecasts to automatically generate efficient delivery plans, with an emotion engine that recognizes user emotions. In addition to the functions of collecting and analyzing traffic information, managing and analyzing inventory data, forecasting demand, and generating and outputting delivery plans, this system also recognizes user emotions, thereby improving the efficiency of delivery work and the user experience.

[0256] Explanation of program processing

[0257] Collection and analysis of real-time traffic information

[0258] 1. The server collects real-time traffic information.

[0259] The server calls the traffic information API, obtains the latest data such as road congestion, accident information, and construction information, and stores it in a database.

[0260] 2. The server analyzes the traffic data.

[0261] Based on the collected data, the required time and congestion level for each route are calculated, and the optimal delivery route is selected using an algorithm.

[0262] 3. The device notifies the driver of the optimal route.

[0263] The terminal notifies the driver of the optimal route information received from the server and displays detailed route information.

[0264] Inventory data collection and analysis

[0265] 1. The server collects inventory data.

[0266] Real-time inventory information is obtained from each warehouse and store's inventory management system via API and stored in a database.

[0267] 2. The server parses the inventory data.

[0268] Analyze collected inventory data to identify items that are low or need replenishing.

[0269] 3. The server reflects this in the delivery plan.

[0270] Based on the results of inventory data analysis, a delivery plan is automatically generated that prioritizes replenishing missing items and is incorporated into the optimal delivery route.

[0271] 4. The device notifies the driver of the updated delivery plan.

[0272] Drivers make efficient deliveries based on the schedule and product pickup list displayed on the terminal.

[0273] Generate demand forecasts and delivery plans

[0274] 1. The server collects past sales data.

[0275] Past sales data, seasonal data, and event information are retrieved from the database and input into the forecasting model.

[0276] 2. The server makes a demand forecast.

[0277] AI algorithms are used to predict future demand based on the acquired data.

[0278] 3. The server generates an optimal delivery plan based on the demand forecast results.

[0279] Routes for efficiently delivering products to each store are calculated based on predicted demand, and this is reflected in delivery plans.

[0280] 4. The device notifies the driver of the delivery plan.

[0281] The generated delivery plan is sent to the driver via the terminal, and delivery activities are carried out based on information updated in real time.

[0282] Recognizing user emotions with an emotion engine

[0283] 1. The device collects the user's voice data.

[0284] Voice data is collected when a user speaks into the terminal.

[0285] 2. The server analyzes the audio data.

[0286] The emotion engine recognizes the user's emotions from the collected voice data, and the analysis results are stored in a database and added to the user's data.

[0287] 3. The device collects the user's facial expression data.

[0288] The system uses the device's built-in camera to collect the user's facial expression data in real time.

[0289] 4. The server analyzes the facial expression data.

[0290] The emotion engine is used to recognize the user's emotions from facial expression data, and the results are also stored in the database.

[0291] 5. The server uses the emotion data to optimize the delivery plan.

[0292] We provide flexible delivery services that take into account the customer experience, including user emotional data.

[0293] Specific examples

[0294] For example, suppose a delivery company needs to plan efficient delivery routes based on real-time traffic information and then combine inventory data and demand forecasts to plan replenishment. In this case, the server collects and analyzes various data to automatically generate optimal delivery routes and replenishment plans. Furthermore, the terminal analyzes the user's voice input and facial expressions using an emotion engine. If the user is feeling stressed, the system can provide flexibility in the delivery plan, thereby improving user satisfaction. In this way, the system of the present invention integrates real-time information, data analysis, and emotion recognition to simultaneously improve logistics efficiency and customer satisfaction.

[0295] The processing flow will be explained below.

[0296] Collection and analysis of real-time traffic information

[0297] Step 1:

[0298] The server periodically calls the traffic information API to obtain real-time data such as road congestion, accident information, construction information, etc. The obtained data is stored in the server's database.

[0299] Step 2:

[0300] The server analyzes the stored traffic data and evaluates the travel time and congestion level of each delivery route, using traffic prediction models and algorithms.

[0301] Step 3:

[0302] Based on the analysis results, the server selects the most efficient route, taking into account delivery delays and fuel efficiency.

[0303] Step 4:

[0304] The device notifies the driver of the optimal route information received from the server, and provides detailed route information to the driver using push notifications and in-app messages.

[0305] Inventory data collection and analysis

[0306] Step 1:

[0307] The server collects inventory data from each warehouse and store's inventory management system via API, including product counts, location information, and replenishment needs.

[0308] Step 2:

[0309] The server collects inventory data, stores it in a database, and updates it in real time. The stored data is then analyzed.

[0310] Step 3:

[0311] The server analyzes inventory data to identify items that are in short supply or need urgent replenishment, and creates a list of high-priority items based on the analysis results.

[0312] Step 4:

[0313] The server automatically generates a delivery plan that reflects the analysis results, and the generated delivery plan includes routes that prioritize urgent products.

[0314] Step 5:

[0315] The terminal notifies the driver of the latest delivery plan, and the driver can check the schedule and product pickup list through the terminal application.

[0316] Generate demand forecasts and delivery plans

[0317] Step 1:

[0318] The server retrieves past sales data, seasonal data, and event data from the database. This data serves as the basis for demand forecasting.

[0319] Step 2:

[0320] The server uses AI algorithms to predict future demand based on the acquired data. The forecasting model is based on past data and takes into account trends and seasonality.

[0321] Step 3:

[0322] The server automatically generates an optimal delivery plan based on the prediction results, calculating which products to deliver to which stores and when, and creating an efficient schedule.

[0323] Step 4:

[0324] The server then combines the generated delivery plan into an optimal route and determines the final delivery route, thereby optimizing time and resources.

[0325] Step 5:

[0326] The device notifies the driver of the optimized delivery plan, and the driver carries out their work based on delivery information updated in real time.

[0327] Recognizing user emotions with an emotion engine

[0328] Step 1:

[0329] The device collects the user's voice data. When the user interacts with the device, the voice is picked up through the microphone.

[0330] Step 2:

[0331] The server analyzes the collected voice data, uses an emotion engine to recognize the user's emotional state from the voice data, and stores the analysis results in a database.

[0332] Step 3:

[0333] The device collects the user's facial expression data, which is acquired in real time via the device's camera.

[0334] Step 4:

[0335] The server analyzes the facial expression data, uses an emotion engine to recognize emotions from the user's facial expressions, and stores the analysis results in a database.

[0336] Step 5:

[0337] The server uses the accumulated emotional data to provide services that take into account the user's emotional state, enabling it to provide feedback to drivers and customize customer service.

[0338] Specific examples

[0339] Let's take the example of a driver checking a delivery plan before setting off on a certain day. First, the server calls a traffic information API to obtain and analyze congestion and accident information and determine the optimal delivery route. Next, the same server collects and analyzes inventory data, identifies products that urgently need replenishment, and reflects this in the delivery plan. Furthermore, the server performs demand forecasting using past sales data and optimizes the delivery plan based on the forecast results. Finally, as the driver checks the optimal route and delivery plan delivered to him via his device before setting off, the emotion engine analyzes the user's emotions and can respond flexibly if the driver is feeling stressed.

[0340] In this way, the system of the present invention can improve the efficiency of delivery operations and the user experience through cooperative operation between the server and terminals over multiple stages.

[0341] Example 2

[0342] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] Existing delivery planning systems manage elements such as traffic information, inventory data, and demand forecasts separately, but are unable to integrate these to generate efficient delivery plans. Furthermore, the emotional state of the user is not reflected in the delivery plan, making it difficult to sufficiently improve customer satisfaction.

[0344] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and analyzing traffic information, a means for collecting and analyzing inventory data, a means for performing demand forecasting, a means for recognizing user emotions, a means for automatically generating an optimal delivery plan based on the results of the analysis and prediction, and a means for outputting the delivery plan. This makes it possible to generate an optimal delivery plan by integrating traffic information, inventory data, demand forecasting, and user emotions, thereby improving customer satisfaction.

[0345] "Traffic information" refers to real-time data such as road congestion, accident information, and construction information.

[0346] "Inventory data" refers to data including the quantity, location, and status of products in each warehouse and store.

[0347] "Demand forecasting" is the prediction of future product demand based on past sales data and other relevant information.

[0348] "Emotion recognition" refers to the process of analyzing a user's voice and facial expressions to identify their emotional state.

[0349] A "delivery plan" is an optimal delivery route and schedule generated by integrating traffic information, inventory data, demand forecasts, and user emotion recognition results.

[0350] "API" is an abbreviation for Application Program Interface, a means by which different software applications communicate with each other.

[0351] A "server" is a central computer system that collects, analyzes, processes data, and provides information to client terminals.

[0352] A "terminal" is a device that a user can directly operate and receive information from, and includes smartphones, tablets, and the like.

[0353] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0354] An "algorithm" is a procedure or computational method for solving a particular problem.

[0355] A "machine learning model" is a mathematical model that uses data to learn patterns and make predictions or classifications.

[0356] An "emotion engine" is software for analyzing emotions from data such as voice and facial expressions.

[0357] This invention is a system that automatically generates efficient delivery plans by integrating traffic information, inventory data, demand forecasts, and user emotions. This system collects and analyzes traffic information, manages and analyzes inventory data, forecasts demand, generates and outputs delivery plans, and also has the ability to recognize user emotions.

[0358] Hardware and software used

[0359] Server: A central computer system that collects and analyzes data. An example product is a cloud server (e.g., Amazon Web Services (AWS)).

[0360] Terminal: A device for inputting and outputting data. In this example, a smartphone or tablet terminal (e.g., iPhone (registered trademark), Android device) is used.

[0361] Database: A system for storing, managing, and searching data. Relational databases such as PostgreSQL and MySQL (registered trademarks) are used.

[0362] Software API: An application program interface for retrieving and transmitting data. Examples include the Google Maps API and a REST API for an inventory management system.

[0363] Machine learning model: A model for learning from past data and making demand forecasts. TensorFlow is used.

[0364] Emotion Engine: A software engine for analyzing voice and facial expression data. Powered by IBM Watson (registered trademark).

[0365] Algorithm: A procedure for analyzing data and deriving the required results. Here, an algorithm implemented in Python is used.

[0366] System Implementation Method

[0367] 1. Collection and analysis of real-time traffic information

[0368] The server uses the Google Maps API to collect current traffic information (congestion, accidents, construction, etc.). The collected data is stored in a PostgreSQL database. Then, a Python algorithm calculates the travel time and congestion level for each route.

[0369] 2. Inventory data collection and analysis

[0370] The server retrieves inventory data from each warehouse and store's inventory management system via a REST API. This data is stored in a PostgreSQL database and analyzed by Python scripts to identify items that are running low or need to be replenished.

[0371] 3. Generate demand forecasts and delivery plans

[0372] The server retrieves past sales data, seasonal data, and event information from the database and uses TensorFlow's machine learning model to predict demand. Based on the predicted demand, an optimal delivery plan is generated.

[0373] 4. Flexible delivery response using emotion recognition

[0374] The device collects the user's voice and facial expression data. The voice data is sent to a server via a voice assistant such as Amazon Alexa and analyzed by IBM Watson's emotion engine. Facial expression data is also collected through the device's camera and similarly analyzed by the emotion engine. Based on this emotion data, the server can respond flexibly to delivery requests and improve user satisfaction.

[0375] Specific examples

[0376] For example, when a delivery company integrates traffic information, inventory data, and demand forecasts to plan optimal delivery routes, the server uses the Google Maps API to obtain the latest traffic data and uses a Python algorithm to calculate the optimal route. The server also collects inventory data from each warehouse and store via the API and automatically generates a delivery plan that prioritizes replenishing missing items. Furthermore, the IBM Watson emotion engine analyzes the user's voice input and facial expression data, allowing for flexibility in the delivery plan if the user is feeling stressed.

[0377] Prompt Sentence Examples

[0378] Based on the information below, generate a delivery plan for the next week and suggest improvements taking into account user sentiment data.

[0379] Sales data for the past month

[0380] Real-time traffic information

[0381] User voice and facial expression data

[0382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0383] Step 1: Collecting traffic information

[0384] The server sends a request to the Google Maps API to get the latest traffic information (congestion, accidents, construction, etc.). It sends the API request as input and receives traffic data in JSON format as output.

[0385] The traffic data acquired by the server is stored in a PostgreSQL database. Specifically, each item of traffic information (e.g., location, congestion level, required time, etc.) is stored in the corresponding database table.

[0386] Step 2: Analyze traffic data

[0387] The server analyzes the stored traffic data using a Python script, reading the traffic data stored in the database as input and calculating the travel time and congestion level for each route as output.

[0388] The server runs an algorithm to select the optimal delivery route, which calculates the shortest and most efficient route by taking into account information such as travel time and congestion.

[0389] Step 3: Collect inventory data

[0390] The server retrieves real-time inventory data from the inventory management systems of each warehouse and store using REST APIs. It sends API requests as input and receives inventory data as output.

[0391] The server stores the inventory data it obtains in a PostgreSQL database. Specifically, it stores information such as the quantity, location, and status of each product in a database table.

[0392] Step 4: Analyze inventory data

[0393] The server parses the stored inventory data using a Python script that reads the inventory data stored in the database as input and identifies items that are missing or need to be replenished as output.

[0394] The server extracts data to generate a delivery plan that prioritizes items that are in short supply. Specifically, it lists items with stock levels below a certain level.

[0395] Step 5: Perform demand forecasting

[0396] The server retrieves historical sales data from the database, along with seasonal and event information. It executes a database query as input and retrieves historical sales data in JSON format as output.

[0397] The server performs demand forecasting using TensorFlow machine learning models. Past data is input to the model, and future demand forecasts are generated as output.

[0398] Step 6: Generate an optimal transportation plan

[0399] The server generates a delivery plan based on predicted demand data, inventory data, and traffic data. The demand forecast results, inventory data, and traffic data are input into the algorithm, and the optimal delivery route and schedule are generated as output.

[0400] The server stores the generated delivery plan in a PostgreSQL database.

[0401] Step 7: Collect user voice data

[0402] The device collects user voice data using a voice assistant such as Amazon Alexa. The device captures the user's speech as input using a microphone and generates voice data as output.

[0403] The device sends the collected voice data to the server. Specifically, the voice data is transferred to the server via API.

[0404] Step 8: Analyzing the audio data

[0405] The server analyzes the voice data using IBM Watson's emotion engine, passing the voice data as input to the emotion engine and generating emotion recognition results as output.

[0406] The server stores the emotion recognition results in a PostgreSQL database.

[0407] Step 9: Collecting user facial expression data

[0408] The device collects the user's facial expression data in real time using a built-in camera. It receives video data from the camera as input and generates facial expression data as output.

[0409] The facial expression data collected by the device is sent to the server. Specifically, the facial expression data is transferred to the server via API.

[0410] Step 10: Analyze facial expression data

[0411] The server analyzes the facial expression data using IBM Watson's emotion engine, passing the facial expression data as input to the emotion engine and generating emotion recognition results as output.

[0412] The server stores the emotion recognition results in a PostgreSQL database.

[0413] Step 11: Optimizing delivery plans with sentiment data

[0414] The server responds flexibly to delivery requests based on the emotional data. The emotional data is passed as input to a delivery plan generation algorithm, and a delivery plan that takes the user's emotional state into consideration is generated as output.

[0415] The server notifies the device of the optimized delivery plan, specifically by transferring the plan to the device via API, and the device displays detailed information to the driver.

[0416] (Application example 2)

[0417] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0418] In conventional delivery operations, delivery plans are mainly based solely on traffic information, inventory data, and demand forecasts, and no flexible response is made that takes user emotions into consideration. As a result, delivery delays and out-of-stock items can cause stress for users, reducing customer satisfaction. The present invention aims to automatically generate more efficient and flexible delivery plans and improve customer satisfaction by combining real-time traffic information, inventory data, demand forecasts, and user emotion recognition.

[0419] 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.

[0420] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for recognizing user emotions, means for optimizing the delivery plan based on emotion data, and means for outputting the delivery plan. This enables not only efficient delivery plans based on real-time information but also flexible delivery responses that take user emotions into consideration.

[0421] "Traffic information" refers to data on traffic flow, such as road congestion, accident information, and construction information, collected in real time.

[0422] "Inventory data" is information regarding the quantity and status of products in each warehouse and store.

[0423] "Demand forecasting" is the process of predicting future demand based on past sales data, seasonal data, and event information.

[0424] "Delivery planning" is a plan that automatically generates optimal delivery routes and schedules based on traffic information, inventory data, and demand forecasts.

[0425] "User's emotions" refers to the user's psychological state as recognized from voice, facial expressions, etc.

[0426] "Emotion data" is information about a user's emotions collected by means of voice recognition and facial expression recognition.

[0427] "Flexible delivery response" refers to a dynamic response that modifies conventional fixed delivery plans based on user emotional data to reduce user stress and dissatisfaction.

[0428] The present invention combines a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts, with an emotion engine that recognizes user emotions. The following describes an embodiment of the present invention in detail.

[0429] Hardware and Software Configuration

[0430] 1. Server:

[0431] The server is set up to collect and analyze traffic information, inventory data, demand forecast data, and emotion data. Specifically, it uses the following APIs and libraries:

[0432] Traffic information: Traffic information APIs such as Google Maps API

[0433] Inventory data: API to retrieve data from inventory management systems at each warehouse and store

[0434] Demand forecasting: AI algorithms (e.g., Scikit-Learn) to forecast demand based on historical sales data, seasonal data, and event information.

[0435] Emotion data: Speech recognition libraries (e.g., SpeechRecognition) and facial expression recognition libraries (e.g., EmotionRecognizer)

[0436] 2. Terminal:

[0437] The terminals are smartphones used by delivery personnel or in-vehicle head-mounted displays, and are responsible for receiving and displaying optimal delivery routes, inventory replenishment plans, demand forecast results, and optimized delivery plans sent from the server. The terminals also have the ability to collect voice input and facial expression data from users.

[0438] 3. User:

[0439] When the user speaks to the device, voice data is collected, and facial expression data is also captured through the built-in camera. This data is sent to the server, where the emotion engine analyzes the user's emotions.

[0440] Process flow example

[0441] 1. Real-time traffic information collection and analysis:

[0442] The server uses a traffic information API to collect real-time traffic information. The traffic data is analyzed and the optimal route is selected. The results are sent to the terminal and notified to the delivery person as the optimal route.

[0443] 2. Inventory data collection and analysis:

[0444] The server collects and analyzes inventory data from the inventory management systems of each warehouse and store, identifying items that are low in stock and incorporating this information into delivery plans.

[0445] 3. Generate demand forecasts and delivery plans:

[0446] The server collects past sales data, seasonal data, and event information, and uses AI algorithms to predict demand. Based on the results, optimal delivery routes and replenishment plans are generated.

[0447] 4. Emotion engine recognizes user emotions:

[0448] The device collects the user's voice and facial expression data and sends it to the server. The emotion engine analyzes this data and recognizes the user's emotions. Based on the results, the delivery plan is optimized.

[0449] Specific examples

[0450] For example, if a food delivery company were to adopt this system, delivery personnel would receive real-time information on optimal routes on their smartphones and confirm plans to prioritize replenishment of low-stock items. Also, if a user expresses an emotion that "the product is delayed," that information would be reflected immediately and a rapid response would be made.

[0451] Prompt Sentence Examples

[0452] An example prompt for running a system using a generative AI model is as follows:

[0453] "Create a food delivery plan using user emotion recognition. Use the following data to generate optimal delivery routes and inventory replenishment plans, and adapt based on user emotions:

[0454] Real-time traffic information (API: Google Maps API)

[0455] Inventory data (API: Inventory Management API)

[0456] Demand forecast data (past sales information)

[0457] User emotion data (voice and facial expression analysis)

[0458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0459] Step 1:

[0460] The server collects traffic information.

[0461] Input: Real-time traffic data from traffic information API

[0462] Specific operation: The server calls the traffic information API and obtains real-time traffic data such as road congestion status, accident information, and construction information.

[0463] Output: Collected traffic data (e.g., congestion level, travel time)

[0464] Step 2:

[0465] The server analyzes the traffic data.

[0466] Input: Collected traffic data

[0467] How it works: The server uses an algorithm to analyze the collected traffic data, calculate the travel time and congestion level for each route, and then select the optimal delivery route.

[0468] Output: Optimal delivery route information

[0469] Step 3:

[0470] A server collects inventory data.

[0471] Input: Inventory data from inventory management systems for each warehouse and store

[0472] Specific operation: The server calls the inventory management API and obtains inventory data for each warehouse and store in real time.

[0473] Output: Collected inventory data (e.g., number of items in stock)

[0474] Step 4:

[0475] The server parses the inventory data.

[0476] Input: Collected inventory data

[0477] What happens: The server analyzes inventory data to identify items that are low or need to be replenished.

[0478] Output: Missing items list

[0479] Step 5:

[0480] The server performs demand forecasting.

[0481] Input: Historical sales data, seasonal data, event information

[0482] Specific operation: The server uses an AI algorithm (e.g., Scikit-Learn) to predict future demand based on past sales data, seasonal data, and event information.

[0483] Output: Demand forecast curve

[0484] Step 6:

[0485] The server generates an optimal delivery plan based on the demand forecast results.

[0486] Input: Optimal delivery route information, shortage product list, demand forecast curve

[0487] Specific operation: The server integrates these input data and automatically generates efficient delivery routes and replenishment plans.

[0488] Output: Delivery plan

[0489] Step 7:

[0490] The terminal notifies the driver of the delivery plan.

[0491] Input: Delivery plan

[0492] Specific operation: Based on the delivery plan information received by the terminal from the server, the driver is shown a detailed schedule and a product pick-up list.

[0493] Output: The trip plan displayed on the driver's device

[0494] Step 8:

[0495] The terminal collects the user's voice data.

[0496] Input: User's voice

[0497] Specific operation: When the user speaks into the device, voice data is collected by the device.

[0498] Output: Collected audio data

[0499] Step 9:

[0500] The server analyzes the audio data.

[0501] Input: Collected audio data

[0502] Specific operation: The server uses a speech recognition library (e.g., SpeechRecognition) to analyze the collected voice data and recognize the user's emotions.

[0503] Output: Recognized emotion data

[0504] Step 10:

[0505] The terminal collects facial expression data of the user.

[0506] Input: User's facial expression

[0507] Specific operation: Using the device's built-in camera, the user's facial expression data is collected in real time.

[0508] Output: Collected facial expression data

[0509] Step 11:

[0510] The server analyzes the facial expression data.

[0511] Input: Collected facial expression data

[0512] Specific operation: The server uses a facial expression recognition library (e.g., EmotionRecognizer) to analyze facial expression data and recognize the user's emotions.

[0513] Output: Recognized emotion data

[0514] Step 12:

[0515] The server uses emotion data to optimize delivery plans.

[0516] Input: Recognized emotion data, existing delivery plan

[0517] Specific operation: Based on the user's emotional data, the server generates an optimized delivery plan that reduces the user's stress and dissatisfaction by adding flexibility to the conventional delivery plan.

[0518] Output: Optimized delivery plan

[0519] Step 13:

[0520] The device notifies the driver of an optimized delivery plan.

[0521] Input: Optimized delivery plan

[0522] Specific operation: The device notifies the driver of the optimized delivery plan received from the server and displays detailed route information and schedule changes.

[0523] Output: Optimized trip plan displayed on the driver's device

[0524] 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.

[0525] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0526] 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.

[0527] [Second embodiment]

[0528] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0529] 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.

[0530] 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).

[0531] 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.

[0532] 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.

[0533] 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).

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0539] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0540] This invention relates to a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts. This system utilizes a server and terminals to improve overall delivery efficiency.

[0541] Explanation of program processing

[0542] Collection and analysis of real-time traffic information

[0543] 1. The server collects real-time traffic information.

[0544] The server calls the traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. This data is updated according to the frequency of distribution and stored on the server.

[0545] 2. The server analyzes the traffic data.

[0546] Using the collected traffic data, the server evaluates the required travel time and congestion level of each route, and then uses an algorithm to analyze this data and calculate the optimal delivery route.

[0547] 3. The device notifies the driver of the optimal route.

[0548] The server calculates the optimal route and delivers it to the device, which then notifies the driver's application in real time. The device then displays detailed route information via push notifications and in-app messages.

[0549] Inventory data collection and analysis

[0550] 1. The server collects inventory data.

[0551] The server calls an API to obtain inventory information from the inventory management systems of each warehouse and store, allowing for real-time inventory status.

[0552] 2. The server parses the inventory data.

[0553] Analyze collected inventory data to identify which items are low or need to be replenished. If necessary, create a list of urgent items.

[0554] 3. The server reflects this in the delivery plan.

[0555] Based on the results of the inventory data analysis, the server adds inventory replenishment routes to the delivery plan, which is reflected in the delivery route and sent to the terminal.

[0556] Generate demand forecasts and delivery plans

[0557] 1. The server collects past sales data.

[0558] The server retrieves past sales data and seasonal data from the database and uses this as the basis for demand forecasting.

[0559] 2. The server makes a demand forecast.

[0560] Using this data, AI algorithms predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[0561] 3. The server generates an optimal delivery plan.

[0562] Based on the demand forecast results, the system calculates how many products to deliver to which stores and when, and generates an efficient delivery schedule.

[0563] 4. The device notifies the driver of the delivery plan.

[0564] The generated delivery plan is sent to the terminal, where the driver can view it through the application. The terminal is updated in real time, optimizing the driver's behavior.

[0565] Specific examples

[0566] Consider a delivery company that needs to deliver products to multiple stores during the morning rush hour. First, the server collects real-time road data from a traffic information API and analyzes congestion levels. Next, it retrieves inventory information from warehouses and store inventory management systems to identify products that are low in stock. It then performs demand forecasting based on past sales data, predicting that certain products are likely to be in short supply ahead of a weekend sale.

[0567] Based on this data, the server generates optimal delivery routes and creates detailed delivery plans that take into account inventory replenishment and demand forecasts. The terminal then notifies the driver of this information, ensuring efficient delivery. In this way, the system of the present invention integrates real-time information and data analysis to achieve efficient logistics.

[0568] The processing flow will be explained below.

[0569] Collection and analysis of real-time traffic information

[0570] Step 1:

[0571] The server periodically calls the traffic information API to obtain the latest traffic data, including road congestion status, accident information, and construction information.

[0572] Step 2:

[0573] The server stores the acquired traffic data in a database, which is used in later analysis steps.

[0574] Step 3:

[0575] The server analyzes the traffic data and calculates the travel time and congestion level for each delivery route using algorithms and traffic prediction models.

[0576] Step 4:

[0577] The server calculates the optimal delivery route, compares the travel time of each route, and selects the most efficient route.

[0578] Step 5:

[0579] The device receives the optimal route information from the server and notifies the driver via push notification or in-app message, displaying detailed route information.

[0580] Inventory data collection and analysis

[0581] Step 1:

[0582] The server calls an API that collects inventory data from each warehouse or store's inventory management system, including product quantities and replenishment needs.

[0583] Step 2:

[0584] The server stores the collected inventory data in a database, which is updated in real time.

[0585] Step 3:

[0586] The server analyzes the inventory data to determine which items are low in stock and creates a list of items that are low in stock or need to be replenished.

[0587] Step 4:

[0588] The server automatically generates a delivery plan based on the items in short supply, prioritizing items with high urgency and adding those stores or warehouses to the delivery route.

[0589] Step 5:

[0590] The device notifies the driver of updated delivery plans, including schedules and pickup lists, which can be viewed within the app.

[0591] Generate demand forecasts and delivery plans

[0592] Step 1:

[0593] The server retrieves past sales data, seasonal data, and event information from the database.

[0594] Step 2:

[0595] Based on the data acquired by the server, demand forecasts are made using AI algorithms. The forecasting model learns from past data and calculates future demand.

[0596] Step 3:

[0597] The server automatically generates an optimal delivery plan based on the demand forecast results, calculating how many items to deliver to which stores and when.

[0598] Step 4:

[0599] The server then combines the delivery plan into an optimal route and finalizes the plan.

[0600] Step 5:

[0601] The device receives an optimized delivery plan from the server and notifies the driver, allowing the driver to make efficient deliveries based on information updated in real time.

[0602] Example 1

[0603] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0604] In the modern logistics industry, it is extremely important to create efficient delivery plans. However, it is difficult to collect and analyze a wide range of information, such as traffic information, inventory data, and demand forecasts, in real time, and integrate them to calculate optimal delivery routes. There is also a need for a method to quickly notify drivers of delivery plans that take this information into account. A system that can solve these problems is needed.

[0605] 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.

[0606] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for collecting traffic data in real time, means for calculating an optimal delivery route using the traffic data, means for acquiring data from inventory management systems of each warehouse and store, means for identifying shortages in inventory data and reflecting them in the delivery plan, means for collecting past sales data and performing demand forecasting, and means for notifying the terminal of the generated delivery plan. This enables real-time information collection and analysis, and efficient generation and notification of delivery plans.

[0607] "Traffic information" refers to data relating to traffic conditions such as road congestion, accident information, and construction information.

[0608] "Inventory data" is information regarding the inventory status of products at each warehouse and store.

[0609] "Demand forecasting" refers to the algorithms and results that predict future demand based on past sales data and seasonal data.

[0610] "Delivery plan" refers to a schedule including the order and route of product delivery, which is automatically generated based on collected and analyzed data.

[0611] "Real-time" means collecting, analyzing, and processing data at the same speed as the real world.

[0612] "API" stands for Application Programming Interface, a mechanism for exchanging data and functions between software programs.

[0613] An "analytical algorithm" is a computational method for analyzing data and extracting useful information for a specific purpose.

[0614] A "terminal" is a device for inputting and outputting information, and in this system specifically refers to a device on which the application used by the driver is installed.

[0615] "Sales data" refers to data relating to past transactions and product sales.

[0616] This invention relates to a system that automatically generates efficient delivery plans based on real-time collection and analysis of traffic information, inventory data, demand forecasts, etc. This system mainly functions using a server and terminals.

[0617] The server first collects traffic information. Specifically, it uses a traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. Google Maps API can be used for this. The obtained traffic data is stored in a PostgreSQL database.

[0618] Next, the server analyzes the collected traffic data. Based on the traffic data, it evaluates the required time and congestion level of each route and calculates the optimal delivery route using the Dijkstra algorithm or A algorithm. The results of this analysis are saved in JSON format and later sent to the terminal.

[0619] The server also retrieves inventory data from each warehouse and store's inventory management system. Specifically, it uses APIs to collect real-time inventory status from systems such as SAP and Oracle SCM. The retrieved inventory data is analyzed to determine whether a specific item is out of stock. This creates a list of items that are in short supply.

[0620] Additionally, the server collects past sales data to forecast demand. To do this, it retrieves data from a database or a third-party sales database (e.g., Amazon Web Services or Google BigQuery). It then uses AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand from the past data. This prediction also takes into account the impact of seasonal fluctuations and specific events.

[0621] Based on the results of the analysis and predictions above, the server automatically generates an optimal delivery plan. The server calculates how many products to deliver to which stores and when, creating an efficient schedule. The generated delivery plan is sent to the terminal in real time.

[0622] The terminal is responsible for notifying the driver of the delivery plan. The optimal route information and delivery plan sent from the server are displayed by the terminal's application. The driver can use this information to make deliveries along the optimal route. The terminal also supports real-time updates, allowing it to quickly respond to changes in traffic and inventory conditions.

[0623] As a concrete example, consider the case where a delivery company makes deliveries during the morning rush hour. The company uses a server to collect traffic information from the Google Maps API, analyzes it, and calculates the optimal route. It obtains inventory data from SAP and Oracle SCM and identifies products that are in short supply. It also uses an AI algorithm to forecast demand based on past sales data, predicting that certain products are likely to be in short supply. Based on this data, the server generates an optimal delivery plan and sends it to the terminal. The driver can then follow the instructions on the terminal to make efficient deliveries.

[0624] Examples of prompts for a generative AI model include:

[0625] "Please give me some prompts for building an AI algorithm that automatically generates optimal delivery route plans using real-time traffic information, inventory data, and demand forecasts in a logistics delivery system."

[0626] In this way, the system of the present invention integrates real-time information and data analysis to achieve more efficient logistics.

[0627] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0628] Step 1:

[0629] Collection of traffic information

[0630] Input: Traffic request from Google Maps API

[0631] Specific operation: The server accesses the Google Maps API at specified intervals to obtain the latest road congestion information, accident information, construction information, etc.

[0632] Output: Traffic information dataset

[0633] A concrete example: A server calls the Google Maps API every minute and stores the collected traffic data in a PostgreSQL database.

[0634] Step 2:

[0635] Traffic data analysis

[0636] Input: Traffic information dataset collected in step 1

[0637] How it works: The server analyzes the stored traffic data and evaluates the travel time and congestion level of each route.

[0638] Output: Analyzed traffic information (travel time, congestion level, etc.)

[0639] Specific example: The server uses Dijkstra algorithm to calculate the shortest route for each delivery route and also evaluates the congestion level.

[0640] Step 3:

[0641] Calculating the best delivery route

[0642] Input: Traffic information parsed in step 2

[0643] Specific operation: The server uses algorithm A to calculate the optimal delivery route based on traffic data.

[0644] Output: Optimal delivery route information

[0645] Specific example: The server saves the calculation results in JSON format and delivers them to the device later.

[0646] Step 4:

[0647] Inventory data collection

[0648] Input: API requests from inventory management systems at each warehouse and store

[0649] Specific operation: The server uses the API of inventory management systems such as SAP and Oracle SCM to obtain real-time inventory data for each warehouse and store.

[0650] Output: Inventory dataset

[0651] Specific example: The server periodically collects data from each warehouse's system and stores it in a database.

[0652] Step 5:

[0653] Inventory data analysis

[0654] Input: Inventory dataset collected in step 4

[0655] What happens: The server analyzes the collected inventory data and identifies which items are in short supply.

[0656] Output: List of missing items

[0657] Specific example: The server checks the stock level of each product and generates a list of products that are below a threshold.

[0658] Step 6:

[0659] Demand forecasting

[0660] Input: Historical sales data from a sales database

[0661] How it works: The server collects past sales data and uses AI algorithms (e.g., TensorFlow) to predict future demand.

[0662] Output: Demand forecast data

[0663] Specific example: The server uses a TensorFlow model to predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[0664] Step 7:

[0665] Generate a delivery plan

[0666] Input: Optimal delivery route information in Step 3, Shortage product list in Step 5, Demand forecast data in Step 6

[0667] Specific operation: The server integrates this data and automatically generates an efficient delivery plan.

[0668] Output: Delivery plan

[0669] Specific example: The server calculates how many items to deliver to which stores and when, and saves the delivery plan as a list.

[0670] Step 8:

[0671] Delivery plan notification

[0672] Input: The shipping plan generated in step 7

[0673] Specific operation: The server sends the generated delivery plan to the terminal.

[0674] Output: Delivery plan notified to the terminal

[0675] A concrete example: Drivers can check their trip plans through an application on their device and receive real-time updates.

[0676] In this way, the system uses the data collected and analyzed at each step to automatically generate optimal delivery plans and achieve efficient logistics.

[0677] (Application example 1)

[0678] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0679] Conventional food delivery systems face challenges in streamlining delivery plans due to the difficulty of managing fluctuations in traffic information and inventory data in real time. Demand forecasts are also inadequate, leading to excess or shortages of inventory. This leads to problems such as reduced work efficiency for delivery drivers and lower customer satisfaction.

[0680] 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.

[0681] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for outputting the delivery plan, means for performing real-time delivery updates, and means for sending notification information to the terminal, thereby integrating real-time information and enabling the automatic generation of an efficient delivery plan.

[0682] "Traffic information" is data about current road conditions, such as road congestion, accident information, and construction information.

[0683] "Inventory data" refers to data about the current quantity of goods or materials in a warehouse or store.

[0684] "Demand forecasting" is a method of predicting future demand for products and services based on past sales data and seasonal data.

[0685] "Distribution planning" refers to the planning of routes and schedules for efficiently delivering products, taking into account demand forecasts and inventory status.

[0686] "Real-time updates" refers to the process of updating the system to reflect current situations and data immediately.

[0687] "Notification information" refers to information provided in real time, such as alerts and instructions sent from the server to the terminal.

[0688] A "terminal" is a device used to receive information, such as a smartphone or tablet.

[0689] A "server" is a computer system that collects, analyzes, stores, and provides the results to other devices.

[0690] "API" stands for Application Program Interface, a mechanism for exchanging data and functions between different software.

[0691] The system for implementing this invention is mainly composed of a server and a terminal. The server mainly collects data, analyzes it, makes predictions, and generates plans, while the terminal notifies the driver of this information.

[0692] Explanation of program processing

[0693] 1. Collection and analysis of real-time traffic information

[0694] The server uses Google Maps API and HERE API to collect real-time traffic information. The collected data includes road congestion, accident information, construction information, etc. This data is analyzed to evaluate the required time and congestion level for each route.

[0695] 2. Inventory data collection and analysis

[0696] The server retrieves inventory data from restaurant inventory management systems via an API. The collected data is used to understand the current inventory status and identify which menu items are in short supply.

[0697] 3. Demand forecasting

[0698] The server collects past order data and seasonal data and uses AI algorithms (e.g., TensorFlow) to forecast demand. This forecast predicts future demand and determines which products will be needed at what time.

[0699] 4. Generating and notifying a delivery plan

[0700] The server integrates traffic information, inventory data, and demand forecasts to generate an optimal delivery plan. The plan includes delivery schedules and routes to ensure efficient delivery. This plan is updated in real time and sent to the driver's device via push notifications and in-app messages.

[0701] Specific hardware and software names used

[0702] Hardware: Smartphone (iOS or Android device)

[0703] software:

[0704] Real-time traffic information API: Google Maps API, HERE API

[0705] Inventory Data Management: RESTful API

[0706] AI algorithm: TensorFlow (demand forecasting)

[0707] Database: Firebase or AWS RDS

[0708] Push notification service: Firebase Cloud Messaging

[0709] Specific examples

[0710] For example, when delivering pizza on a Friday night, the server operates as follows: First, the server obtains real-time traffic information from the Google Maps API and analyzes whether major roads are congested. At the same time, data obtained from the restaurant's inventory management system reveals that there is a shortage of pizza cheese. The AI ​​uses past data to forecast demand and predicts that demand for pizza will peak on Friday night.

[0711] Based on this information, the server generates optimal delivery routes and inventory replenishment routes and notifies the drivers. Drivers can then check the latest delivery routes and schedules on their smartphone apps, enabling them to deliver efficiently.

[0712] Prompt Sentence Examples

[0713] Program Name: FoodMaster

[0714] Use: Automatic generation of efficient delivery plans for food delivery

[0715] function:

[0716] 1. Collect and analyze real-time traffic information using Google Maps API

[0717] 2. Collect and analyze inventory data from restaurant inventory management systems

[0718] 3. Demand forecasting using past data using TensorFlow

[0719] 4. Automatically generate and notify optimal routes and delivery schedules using Firebase

[0720] 5. Push notifications and real-time updates in the app

[0721] Input data:

[0722] Traffic information API response data

[0723] Inventory information from restaurant inventory management systems

[0724] Historical Order Data

[0725] Output data:

[0726] Delivery route and schedule notifications

[0727] Inventory replenishment notifications to restaurants

[0728] prompt:

[0729] "Real-time traffic information," "Inventory management," "AI demand forecasting," "Optimal route calculation," "Firebase notifications"

[0730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0731] Step 1:

[0732] The server collects real-time traffic information using the Google Maps API and HERE API. Specifically, the server calls the API to obtain road congestion status, accident information, construction information, etc., and stores the response data. This data is used to evaluate the travel time and congestion level of each road segment.

[0733] Input: Traffic information API request

[0734] Output: Response data such as congestion status, accident information, construction information, etc.

[0735] Step 2:

[0736] The server analyzes the collected traffic information. Specifically, it uses algorithms to calculate the travel time and congestion level of each route. For example, if a road is congested, this information can be used to identify routes that drivers should avoid.

[0737] Input: Collected traffic information data

[0738] Output: Travel time and congestion data for each route

[0739] Step 3:

[0740] The server retrieves inventory data from the restaurant's inventory management system via an API. Specifically, the server sends a request to the restaurant's inventory system to understand the current inventory status and saves the response data. This allows the server to identify which menu items are in short supply.

[0741] Input: API request to inventory management system

[0742] Output: Stock status response data

[0743] Step 4:

[0744] The server analyzes the acquired inventory data and creates a list of items that need to be replenished. For example, if there is a shortage of pizza cheese, it adds that item to the list as a high-urgency item to be replenished.

[0745] Input: Retrieved inventory data

[0746] Output: A list of products that need to be replenished

[0747] Step 5:

[0748] The server performs demand forecasting based on past order data and seasonal data. Specifically, it uses AI algorithms (e.g., TensorFlow) to predict future demand. This forecast also takes into account seasonal fluctuations and the impact of specific events.

[0749] Input: Past order data, seasonal data

[0750] Output: Future demand forecast data

[0751] Step 6:

[0752] The server integrates traffic information, inventory data, and demand forecast results to generate an optimal delivery plan. Specifically, it uses algorithms to calculate optimal delivery routes and schedules.

[0753] Input: Traffic information, inventory data, demand forecast data

[0754] Output: Delivery plan (optimal delivery route and schedule)

[0755] Step 7:

[0756] The server updates the generated delivery plan in real time and sends a push notification to the driver's device using Firebase Cloud Messaging. The driver can then check the latest delivery plan in the app.

[0757] Input: Generated dispatch plan

[0758] Output: Notification data sent to the device (push notifications and in-app updates)

[0759] 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.

[0760] This invention combines a system that integrates real-time traffic information, inventory data, and demand forecasts to automatically generate efficient delivery plans, with an emotion engine that recognizes user emotions. In addition to the functions of collecting and analyzing traffic information, managing and analyzing inventory data, forecasting demand, and generating and outputting delivery plans, this system also recognizes user emotions, thereby improving the efficiency of delivery work and the user experience.

[0761] Explanation of program processing

[0762] Collection and analysis of real-time traffic information

[0763] 1. The server collects real-time traffic information.

[0764] The server calls the traffic information API, obtains the latest data such as road congestion, accident information, and construction information, and stores it in a database.

[0765] 2. The server analyzes the traffic data.

[0766] Based on the collected data, the required time and congestion level for each route are calculated, and the optimal delivery route is selected using an algorithm.

[0767] 3. The device notifies the driver of the optimal route.

[0768] The terminal notifies the driver of the optimal route information received from the server and displays detailed route information.

[0769] Inventory data collection and analysis

[0770] 1. The server collects inventory data.

[0771] Real-time inventory information is obtained from each warehouse and store's inventory management system via API and stored in a database.

[0772] 2. The server parses the inventory data.

[0773] Analyze collected inventory data to identify items that are low or need replenishing.

[0774] 3. The server reflects this in the delivery plan.

[0775] Based on the results of inventory data analysis, a delivery plan is automatically generated that prioritizes replenishing missing items and is incorporated into the optimal delivery route.

[0776] 4. The device notifies the driver of the updated delivery plan.

[0777] Drivers make efficient deliveries based on the schedule and product pickup list displayed on the terminal.

[0778] Generate demand forecasts and delivery plans

[0779] 1. The server collects past sales data.

[0780] Past sales data, seasonal data, and event information are retrieved from the database and input into the forecasting model.

[0781] 2. The server makes a demand forecast.

[0782] AI algorithms are used to predict future demand based on the acquired data.

[0783] 3. The server generates an optimal delivery plan based on the demand forecast results.

[0784] Routes for efficiently delivering products to each store are calculated based on predicted demand, and this is reflected in delivery plans.

[0785] 4. The device notifies the driver of the delivery plan.

[0786] The generated delivery plan is sent to the driver via the terminal, and delivery activities are carried out based on information updated in real time.

[0787] Recognizing user emotions with an emotion engine

[0788] 1. The device collects the user's voice data.

[0789] Voice data is collected when a user speaks into the terminal.

[0790] 2. The server analyzes the audio data.

[0791] The emotion engine recognizes the user's emotions from the collected voice data, and the analysis results are stored in a database and added to the user's data.

[0792] 3. The device collects the user's facial expression data.

[0793] The system uses the device's built-in camera to collect the user's facial expression data in real time.

[0794] 4. The server analyzes the facial expression data.

[0795] The emotion engine is used to recognize the user's emotions from facial expression data, and the results are also stored in the database.

[0796] 5. The server uses the emotion data to optimize the delivery plan.

[0797] We provide flexible delivery services that take into account the customer experience, including user emotional data.

[0798] Specific examples

[0799] For example, suppose a delivery company needs to plan efficient delivery routes based on real-time traffic information and then combine inventory data and demand forecasts to plan replenishment. In this case, the server collects and analyzes various data to automatically generate optimal delivery routes and replenishment plans. Furthermore, the terminal analyzes the user's voice input and facial expressions using an emotion engine. If the user is feeling stressed, the system can provide flexibility in the delivery plan, thereby improving user satisfaction. In this way, the system of the present invention integrates real-time information, data analysis, and emotion recognition to simultaneously improve logistics efficiency and customer satisfaction.

[0800] The processing flow will be explained below.

[0801] Collection and analysis of real-time traffic information

[0802] Step 1:

[0803] The server periodically calls the traffic information API to obtain real-time data such as road congestion, accident information, construction information, etc. The obtained data is stored in the server's database.

[0804] Step 2:

[0805] The server analyzes the stored traffic data and evaluates the travel time and congestion level of each delivery route, using traffic prediction models and algorithms.

[0806] Step 3:

[0807] Based on the analysis results, the server selects the most efficient route, taking into account delivery delays and fuel efficiency.

[0808] Step 4:

[0809] The device notifies the driver of the optimal route information received from the server, and provides detailed route information to the driver using push notifications and in-app messages.

[0810] Inventory data collection and analysis

[0811] Step 1:

[0812] The server collects inventory data from each warehouse and store's inventory management system via API, including product counts, location information, and replenishment needs.

[0813] Step 2:

[0814] The server collects inventory data, stores it in a database, and updates it in real time. The stored data is then analyzed.

[0815] Step 3:

[0816] The server analyzes inventory data to identify items that are in short supply or need urgent replenishment, and creates a list of high-priority items based on the analysis results.

[0817] Step 4:

[0818] The server automatically generates a delivery plan that reflects the analysis results, and the generated delivery plan includes routes that prioritize urgent products.

[0819] Step 5:

[0820] The terminal notifies the driver of the latest delivery plan, and the driver can check the schedule and product pickup list through the terminal application.

[0821] Generate demand forecasts and delivery plans

[0822] Step 1:

[0823] The server retrieves past sales data, seasonal data, and event data from the database. This data serves as the basis for demand forecasting.

[0824] Step 2:

[0825] The server uses AI algorithms to predict future demand based on the acquired data. The forecasting model is based on past data and takes into account trends and seasonality.

[0826] Step 3:

[0827] The server automatically generates an optimal delivery plan based on the prediction results, calculating which products to deliver to which stores and when, and creating an efficient schedule.

[0828] Step 4:

[0829] The server then combines the generated delivery plan into an optimal route and determines the final delivery route, thereby optimizing time and resources.

[0830] Step 5:

[0831] The device notifies the driver of the optimized delivery plan, and the driver carries out their work based on delivery information updated in real time.

[0832] Recognizing user emotions with an emotion engine

[0833] Step 1:

[0834] The device collects the user's voice data. When the user interacts with the device, the voice is picked up through the microphone.

[0835] Step 2:

[0836] The server analyzes the collected voice data, uses an emotion engine to recognize the user's emotional state from the voice data, and stores the analysis results in a database.

[0837] Step 3:

[0838] The device collects the user's facial expression data, which is acquired in real time via the device's camera.

[0839] Step 4:

[0840] The server analyzes the facial expression data, uses an emotion engine to recognize emotions from the user's facial expressions, and stores the analysis results in a database.

[0841] Step 5:

[0842] The server uses the accumulated emotional data to provide services that take into account the user's emotional state, enabling it to provide feedback to drivers and customize customer service.

[0843] Specific examples

[0844] Let's take the example of a driver checking a delivery plan before setting off on a certain day. First, the server calls a traffic information API to obtain and analyze congestion and accident information and determine the optimal delivery route. Next, the same server collects and analyzes inventory data, identifies products that urgently need replenishment, and reflects this in the delivery plan. Furthermore, the server performs demand forecasting using past sales data and optimizes the delivery plan based on the forecast results. Finally, as the driver checks the optimal route and delivery plan delivered to him via his device before setting off, the emotion engine analyzes the user's emotions and can respond flexibly if the driver is feeling stressed.

[0845] In this way, the system of the present invention can improve the efficiency of delivery operations and the user experience through cooperative operation between the server and terminals over multiple stages.

[0846] Example 2

[0847] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0848] Existing delivery planning systems manage elements such as traffic information, inventory data, and demand forecasts separately, but are unable to integrate these to generate efficient delivery plans. Furthermore, the emotional state of the user is not reflected in the delivery plan, making it difficult to sufficiently improve customer satisfaction.

[0849] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and analyzing traffic information, a means for collecting and analyzing inventory data, a means for performing demand forecasting, a means for recognizing user emotions, a means for automatically generating an optimal delivery plan based on the results of the analysis and prediction, and a means for outputting the delivery plan. This makes it possible to generate an optimal delivery plan by integrating traffic information, inventory data, demand forecasting, and user emotions, thereby improving customer satisfaction.

[0850] "Traffic information" refers to real-time data such as road congestion, accident information, and construction information.

[0851] "Inventory data" refers to data including the quantity, location, and status of products in each warehouse and store.

[0852] "Demand forecasting" is the prediction of future product demand based on past sales data and other relevant information.

[0853] "Emotion recognition" refers to the process of analyzing a user's voice and facial expressions to identify their emotional state.

[0854] A "delivery plan" is an optimal delivery route and schedule generated by integrating traffic information, inventory data, demand forecasts, and user emotion recognition results.

[0855] "API" is an abbreviation for Application Program Interface, a means by which different software applications communicate with each other.

[0856] A "server" is a central computer system that collects, analyzes, processes data, and provides information to client terminals.

[0857] A "terminal" is a device that a user can directly operate and receive information from, and includes smartphones, tablets, and the like.

[0858] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0859] An "algorithm" is a procedure or computational method for solving a particular problem.

[0860] A "machine learning model" is a mathematical model that uses data to learn patterns and make predictions or classifications.

[0861] An "emotion engine" is software for analyzing emotions from data such as voice and facial expressions.

[0862] This invention is a system that automatically generates efficient delivery plans by integrating traffic information, inventory data, demand forecasts, and user emotions. This system collects and analyzes traffic information, manages and analyzes inventory data, forecasts demand, generates and outputs delivery plans, and also has the ability to recognize user emotions.

[0863] Hardware and software used

[0864] Server: A central computer system that collects and analyzes data. An example product is a cloud server (e.g., Amazon Web Services (AWS)).

[0865] Terminal: A device for inputting and outputting data. In this example, we use smartphones and tablet terminals (e.g., iPhones and Android devices).

[0866] Database: A system for storing, managing, and searching data. Relational databases such as PostgreSQL and MySQL are used.

[0867] Software API: An application program interface for retrieving and transmitting data. Examples include the Google Maps API and a REST API for an inventory management system.

[0868] Machine learning model: A model for learning from past data and making demand forecasts. TensorFlow is used.

[0869] Emotion Engine: A software engine for analyzing voice and facial expression data. Powered by IBM Watson.

[0870] Algorithm: A procedure for analyzing data and deriving the required results. Here, an algorithm implemented in Python is used.

[0871] System Implementation Method

[0872] 1. Collection and analysis of real-time traffic information

[0873] The server uses the Google Maps API to collect current traffic information (congestion, accidents, construction, etc.). The collected data is stored in a PostgreSQL database. Then, a Python algorithm calculates the travel time and congestion level for each route.

[0874] 2. Inventory data collection and analysis

[0875] The server retrieves inventory data from each warehouse and store's inventory management system via a REST API. This data is stored in a PostgreSQL database and analyzed by Python scripts to identify items that are running low or need to be replenished.

[0876] 3. Generate demand forecasts and delivery plans

[0877] The server retrieves past sales data, seasonal data, and event information from the database and uses TensorFlow's machine learning model to predict demand. Based on the predicted demand, an optimal delivery plan is generated.

[0878] 4. Flexible delivery response using emotion recognition

[0879] The device collects the user's voice and facial expression data. The voice data is sent to a server via a voice assistant such as Amazon Alexa and analyzed by IBM Watson's emotion engine. Facial expression data is also collected through the device's camera and similarly analyzed by the emotion engine. Based on this emotion data, the server can respond flexibly to delivery requests and improve user satisfaction.

[0880] Specific examples

[0881] For example, when a delivery company integrates traffic information, inventory data, and demand forecasts to plan optimal delivery routes, the server uses the Google Maps API to obtain the latest traffic data and uses a Python algorithm to calculate the optimal route. The server also collects inventory data from each warehouse and store via the API and automatically generates a delivery plan that prioritizes replenishing missing items. Furthermore, the IBM Watson emotion engine analyzes the user's voice input and facial expression data, allowing for flexibility in the delivery plan if the user is feeling stressed.

[0882] Prompt Sentence Examples

[0883] Based on the information below, generate a delivery plan for the next week and suggest improvements taking into account user sentiment data.

[0884] Sales data for the past month

[0885] Real-time traffic information

[0886] User voice and facial expression data

[0887] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0888] Step 1: Collecting traffic information

[0889] The server sends a request to the Google Maps API to get the latest traffic information (congestion, accidents, construction, etc.). It sends the API request as input and receives traffic data in JSON format as output.

[0890] The traffic data acquired by the server is stored in a PostgreSQL database. Specifically, each item of traffic information (e.g., location, congestion level, required time, etc.) is stored in the corresponding database table.

[0891] Step 2: Analyze traffic data

[0892] The server analyzes the stored traffic data using a Python script, reading the traffic data stored in the database as input and calculating the travel time and congestion level for each route as output.

[0893] The server runs an algorithm to select the optimal delivery route, which calculates the shortest and most efficient route by taking into account information such as travel time and congestion.

[0894] Step 3: Collect inventory data

[0895] The server retrieves real-time inventory data from the inventory management systems of each warehouse and store using REST APIs. It sends API requests as input and receives inventory data as output.

[0896] The server stores the inventory data it obtains in a PostgreSQL database. Specifically, it stores information such as the quantity, location, and status of each product in a database table.

[0897] Step 4: Analyze inventory data

[0898] The server parses the stored inventory data using a Python script that reads the inventory data stored in the database as input and identifies items that are missing or need to be replenished as output.

[0899] The server extracts data to generate a delivery plan that prioritizes items that are in short supply. Specifically, it lists items with stock levels below a certain level.

[0900] Step 5: Perform demand forecasting

[0901] The server retrieves historical sales data from the database, along with seasonal and event information. It executes a database query as input and retrieves historical sales data in JSON format as output.

[0902] The server performs demand forecasting using TensorFlow machine learning models. Past data is input to the model, and future demand forecasts are generated as output.

[0903] Step 6: Generate an optimal transportation plan

[0904] The server generates a delivery plan based on predicted demand data, inventory data, and traffic data. The demand forecast results, inventory data, and traffic data are input into the algorithm, and the optimal delivery route and schedule are generated as output.

[0905] The server stores the generated delivery plan in a PostgreSQL database.

[0906] Step 7: Collect user voice data

[0907] The device collects user voice data using a voice assistant such as Amazon Alexa. The device captures the user's speech as input using a microphone and generates voice data as output.

[0908] The device sends the collected voice data to the server. Specifically, the voice data is transferred to the server via API.

[0909] Step 8: Analyzing the audio data

[0910] The server analyzes the voice data using IBM Watson's emotion engine, passing the voice data as input to the emotion engine and generating emotion recognition results as output.

[0911] The server stores the emotion recognition results in a PostgreSQL database.

[0912] Step 9: Collecting user facial expression data

[0913] The device collects the user's facial expression data in real time using a built-in camera. It receives video data from the camera as input and generates facial expression data as output.

[0914] The facial expression data collected by the device is sent to the server. Specifically, the facial expression data is transferred to the server via API.

[0915] Step 10: Analyze facial expression data

[0916] The server analyzes the facial expression data using IBM Watson's emotion engine, passing the facial expression data as input to the emotion engine and generating emotion recognition results as output.

[0917] The server stores the emotion recognition results in a PostgreSQL database.

[0918] Step 11: Optimizing delivery plans with sentiment data

[0919] The server responds flexibly to delivery requests based on the emotional data. The emotional data is passed as input to a delivery plan generation algorithm, and a delivery plan that takes the user's emotional state into consideration is generated as output.

[0920] The server notifies the device of the optimized delivery plan, specifically by transferring the plan to the device via API, and the device displays detailed information to the driver.

[0921] (Application example 2)

[0922] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0923] In conventional delivery operations, delivery plans are mainly based solely on traffic information, inventory data, and demand forecasts, and no flexible response is made that takes user emotions into consideration. As a result, delivery delays and out-of-stock items can cause stress for users, reducing customer satisfaction. The present invention aims to automatically generate more efficient and flexible delivery plans and improve customer satisfaction by combining real-time traffic information, inventory data, demand forecasts, and user emotion recognition.

[0924] 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.

[0925] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for recognizing user emotions, means for optimizing the delivery plan based on emotion data, and means for outputting the delivery plan. This enables not only efficient delivery plans based on real-time information but also flexible delivery responses that take user emotions into consideration.

[0926] "Traffic information" refers to data on traffic flow, such as road congestion, accident information, and construction information, collected in real time.

[0927] "Inventory data" is information regarding the quantity and status of products in each warehouse and store.

[0928] "Demand forecasting" is the process of predicting future demand based on past sales data, seasonal data, and event information.

[0929] "Delivery planning" is a plan that automatically generates optimal delivery routes and schedules based on traffic information, inventory data, and demand forecasts.

[0930] "User's emotions" refers to the user's psychological state as recognized from voice, facial expressions, etc.

[0931] "Emotion data" is information about a user's emotions collected by means of voice recognition and facial expression recognition.

[0932] "Flexible delivery response" refers to a dynamic response that modifies conventional fixed delivery plans based on user emotional data to reduce user stress and dissatisfaction.

[0933] The present invention combines a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts, with an emotion engine that recognizes user emotions. The following describes an embodiment of the present invention in detail.

[0934] Hardware and Software Configuration

[0935] 1. Server:

[0936] The server is set up to collect and analyze traffic information, inventory data, demand forecast data, and emotion data. Specifically, it uses the following APIs and libraries:

[0937] Traffic information: Traffic information APIs such as Google Maps API

[0938] Inventory data: API to retrieve data from inventory management systems at each warehouse and store

[0939] Demand forecasting: AI algorithms (e.g., Scikit-Learn) to forecast demand based on historical sales data, seasonal data, and event information.

[0940] Emotion data: Speech recognition libraries (e.g., SpeechRecognition) and facial expression recognition libraries (e.g., EmotionRecognizer)

[0941] 2. Terminal:

[0942] The terminals are smartphones used by delivery personnel or in-vehicle head-mounted displays, and are responsible for receiving and displaying optimal delivery routes, inventory replenishment plans, demand forecast results, and optimized delivery plans sent from the server. The terminals also have the ability to collect voice input and facial expression data from users.

[0943] 3. User:

[0944] When the user speaks to the device, voice data is collected, and facial expression data is also captured through the built-in camera. This data is sent to the server, where the emotion engine analyzes the user's emotions.

[0945] Process flow example

[0946] 1. Real-time traffic information collection and analysis:

[0947] The server uses a traffic information API to collect real-time traffic information. The traffic data is analyzed and the optimal route is selected. The results are sent to the terminal and notified to the delivery person as the optimal route.

[0948] 2. Inventory data collection and analysis:

[0949] The server collects and analyzes inventory data from the inventory management systems of each warehouse and store, identifying items that are low in stock and incorporating this information into delivery plans.

[0950] 3. Generate demand forecasts and delivery plans:

[0951] The server collects past sales data, seasonal data, and event information, and uses AI algorithms to predict demand. Based on the results, optimal delivery routes and replenishment plans are generated.

[0952] 4. Emotion engine recognizes user emotions:

[0953] The device collects the user's voice and facial expression data and sends it to the server. The emotion engine analyzes this data and recognizes the user's emotions. Based on the results, the delivery plan is optimized.

[0954] Specific examples

[0955] For example, if a food delivery company were to adopt this system, delivery personnel would receive real-time information on optimal routes on their smartphones and confirm plans to prioritize replenishment of low-stock items. Also, if a user expresses an emotion that "the product is delayed," that information would be reflected immediately and a rapid response would be made.

[0956] Prompt Sentence Examples

[0957] An example prompt for running a system using a generative AI model is as follows:

[0958] "Create a food delivery plan using user emotion recognition. Use the following data to generate optimal delivery routes and inventory replenishment plans, and adapt based on user emotions:

[0959] Real-time traffic information (API: Google Maps API)

[0960] Inventory data (API: Inventory Management API)

[0961] Demand forecast data (past sales information)

[0962] User emotion data (voice and facial expression analysis)

[0963] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0964] Step 1:

[0965] The server collects traffic information.

[0966] Input: Real-time traffic data from traffic information API

[0967] Specific operation: The server calls the traffic information API and obtains real-time traffic data such as road congestion status, accident information, and construction information.

[0968] Output: Collected traffic data (e.g., congestion level, travel time)

[0969] Step 2:

[0970] The server analyzes the traffic data.

[0971] Input: Collected traffic data

[0972] How it works: The server uses an algorithm to analyze the collected traffic data, calculate the travel time and congestion level for each route, and then select the optimal delivery route.

[0973] Output: Optimal delivery route information

[0974] Step 3:

[0975] A server collects inventory data.

[0976] Input: Inventory data from inventory management systems for each warehouse and store

[0977] Specific operation: The server calls the inventory management API and obtains inventory data for each warehouse and store in real time.

[0978] Output: Collected inventory data (e.g., number of items in stock)

[0979] Step 4:

[0980] The server parses the inventory data.

[0981] Input: Collected inventory data

[0982] What happens: The server analyzes inventory data to identify items that are low or need to be replenished.

[0983] Output: Missing items list

[0984] Step 5:

[0985] The server performs demand forecasting.

[0986] Input: Historical sales data, seasonal data, event information

[0987] Specific operation: The server uses an AI algorithm (e.g., Scikit-Learn) to predict future demand based on past sales data, seasonal data, and event information.

[0988] Output: Demand forecast curve

[0989] Step 6:

[0990] The server generates an optimal delivery plan based on the demand forecast results.

[0991] Input: Optimal delivery route information, shortage product list, demand forecast curve

[0992] Specific operation: The server integrates these input data and automatically generates efficient delivery routes and replenishment plans.

[0993] Output: Delivery plan

[0994] Step 7:

[0995] The terminal notifies the driver of the delivery plan.

[0996] Input: Delivery plan

[0997] Specific operation: Based on the delivery plan information received by the terminal from the server, the driver is shown a detailed schedule and a product pick-up list.

[0998] Output: The trip plan displayed on the driver's device

[0999] Step 8:

[1000] The terminal collects the user's voice data.

[1001] Input: User's voice

[1002] Specific operation: When the user speaks into the device, voice data is collected by the device.

[1003] Output: Collected audio data

[1004] Step 9:

[1005] The server analyzes the audio data.

[1006] Input: Collected audio data

[1007] Specific operation: The server uses a speech recognition library (e.g., SpeechRecognition) to analyze the collected voice data and recognize the user's emotions.

[1008] Output: Recognized emotion data

[1009] Step 10:

[1010] The terminal collects facial expression data of the user.

[1011] Input: User's facial expression

[1012] Specific operation: Using the device's built-in camera, the user's facial expression data is collected in real time.

[1013] Output: Collected facial expression data

[1014] Step 11:

[1015] The server analyzes the facial expression data.

[1016] Input: Collected facial expression data

[1017] Specific operation: The server uses a facial expression recognition library (e.g., EmotionRecognizer) to analyze facial expression data and recognize the user's emotions.

[1018] Output: Recognized emotion data

[1019] Step 12:

[1020] The server uses emotion data to optimize delivery plans.

[1021] Input: Recognized emotion data, existing delivery plan

[1022] Specific operation: Based on the user's emotional data, the server generates an optimized delivery plan that reduces the user's stress and dissatisfaction by adding flexibility to the conventional delivery plan.

[1023] Output: Optimized delivery plan

[1024] Step 13:

[1025] The device notifies the driver of an optimized delivery plan.

[1026] Input: Optimized delivery plan

[1027] Specific operation: The device notifies the driver of the optimized delivery plan received from the server and displays detailed route information and schedule changes.

[1028] Output: Optimized trip plan displayed on the driver's device

[1029] 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.

[1030] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1031] 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.

[1032] [Third embodiment]

[1033] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1034] 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.

[1035] 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).

[1036] 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.

[1037] 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.

[1038] 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).

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1045] This invention relates to a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts. This system utilizes a server and terminals to improve overall delivery efficiency.

[1046] Explanation of program processing

[1047] Collection and analysis of real-time traffic information

[1048] 1. The server collects real-time traffic information.

[1049] The server calls the traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. This data is updated according to the frequency of distribution and stored on the server.

[1050] 2. The server analyzes the traffic data.

[1051] Using the collected traffic data, the server evaluates the required travel time and congestion level of each route, and then uses an algorithm to analyze this data and calculate the optimal delivery route.

[1052] 3. The device notifies the driver of the optimal route.

[1053] The server calculates the optimal route and delivers it to the device, which then notifies the driver's application in real time. The device then displays detailed route information via push notifications and in-app messages.

[1054] Inventory data collection and analysis

[1055] 1. The server collects inventory data.

[1056] The server calls an API to obtain inventory information from the inventory management systems of each warehouse and store, allowing for real-time inventory status.

[1057] 2. The server parses the inventory data.

[1058] Analyze collected inventory data to identify which items are low or need to be replenished. If necessary, create a list of urgent items.

[1059] 3. The server reflects this in the delivery plan.

[1060] Based on the results of the inventory data analysis, the server adds inventory replenishment routes to the delivery plan, which is reflected in the delivery route and sent to the terminal.

[1061] Generate demand forecasts and delivery plans

[1062] 1. The server collects past sales data.

[1063] The server retrieves past sales data and seasonal data from the database and uses this as the basis for demand forecasting.

[1064] 2. The server makes a demand forecast.

[1065] Using this data, AI algorithms predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[1066] 3. The server generates an optimal delivery plan.

[1067] Based on the demand forecast results, the system calculates how many products to deliver to which stores and when, and generates an efficient delivery schedule.

[1068] 4. The device notifies the driver of the delivery plan.

[1069] The generated delivery plan is sent to the terminal, where the driver can view it through the application. The terminal is updated in real time, optimizing the driver's behavior.

[1070] Specific examples

[1071] Consider a delivery company that needs to deliver products to multiple stores during the morning rush hour. First, the server collects real-time road data from a traffic information API and analyzes congestion levels. Next, it retrieves inventory information from warehouses and store inventory management systems to identify products that are low in stock. It then performs demand forecasting based on past sales data, predicting that certain products are likely to be in short supply ahead of a weekend sale.

[1072] Based on this data, the server generates optimal delivery routes and creates detailed delivery plans that take into account inventory replenishment and demand forecasts. The terminal then notifies the driver of this information, ensuring efficient delivery. In this way, the system of the present invention integrates real-time information and data analysis to achieve efficient logistics.

[1073] The processing flow will be explained below.

[1074] Collection and analysis of real-time traffic information

[1075] Step 1:

[1076] The server periodically calls the traffic information API to obtain the latest traffic data, including road congestion status, accident information, and construction information.

[1077] Step 2:

[1078] The server stores the acquired traffic data in a database, which is used in later analysis steps.

[1079] Step 3:

[1080] The server analyzes the traffic data and calculates the travel time and congestion level for each delivery route using algorithms and traffic prediction models.

[1081] Step 4:

[1082] The server calculates the optimal delivery route, compares the travel time of each route, and selects the most efficient route.

[1083] Step 5:

[1084] The device receives the optimal route information from the server and notifies the driver via push notification or in-app message, displaying detailed route information.

[1085] Inventory data collection and analysis

[1086] Step 1:

[1087] The server calls an API that collects inventory data from each warehouse or store's inventory management system, including product quantities and replenishment needs.

[1088] Step 2:

[1089] The server stores the collected inventory data in a database, which is updated in real time.

[1090] Step 3:

[1091] The server analyzes the inventory data to determine which items are low in stock and creates a list of items that are low in stock or need to be replenished.

[1092] Step 4:

[1093] The server automatically generates a delivery plan based on the items in short supply, prioritizing items with high urgency and adding those stores or warehouses to the delivery route.

[1094] Step 5:

[1095] The device notifies the driver of updated delivery plans, including schedules and pickup lists, which can be viewed within the app.

[1096] Generate demand forecasts and delivery plans

[1097] Step 1:

[1098] The server retrieves past sales data, seasonal data, and event information from the database.

[1099] Step 2:

[1100] Based on the data acquired by the server, demand forecasts are made using AI algorithms. The forecasting model learns from past data and calculates future demand.

[1101] Step 3:

[1102] The server automatically generates an optimal delivery plan based on the demand forecast results, calculating how many items to deliver to which stores and when.

[1103] Step 4:

[1104] The server then combines the delivery plan into an optimal route and finalizes the plan.

[1105] Step 5:

[1106] The device receives an optimized delivery plan from the server and notifies the driver, allowing the driver to make efficient deliveries based on information updated in real time.

[1107] Example 1

[1108] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1109] In the modern logistics industry, it is extremely important to create efficient delivery plans. However, it is difficult to collect and analyze a wide range of information, such as traffic information, inventory data, and demand forecasts, in real time, and integrate them to calculate optimal delivery routes. There is also a need for a method to quickly notify drivers of delivery plans that take this information into account. A system that can solve these problems is needed.

[1110] 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.

[1111] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for collecting traffic data in real time, means for calculating an optimal delivery route using the traffic data, means for acquiring data from inventory management systems of each warehouse and store, means for identifying shortages in inventory data and reflecting them in the delivery plan, means for collecting past sales data and performing demand forecasting, and means for notifying the terminal of the generated delivery plan. This enables real-time information collection and analysis, and efficient generation and notification of delivery plans.

[1112] "Traffic information" refers to data relating to traffic conditions such as road congestion, accident information, and construction information.

[1113] "Inventory data" is information regarding the inventory status of products at each warehouse and store.

[1114] "Demand forecasting" refers to the algorithms and results that predict future demand based on past sales data and seasonal data.

[1115] "Delivery plan" refers to a schedule including the order and route of product delivery, which is automatically generated based on collected and analyzed data.

[1116] "Real-time" means collecting, analyzing, and processing data at the same speed as the real world.

[1117] "API" stands for Application Programming Interface, a mechanism for exchanging data and functions between software programs.

[1118] An "analytical algorithm" is a computational method for analyzing data and extracting useful information for a specific purpose.

[1119] A "terminal" is a device for inputting and outputting information, and in this system specifically refers to a device on which the application used by the driver is installed.

[1120] "Sales data" refers to data relating to past transactions and product sales.

[1121] This invention relates to a system that automatically generates efficient delivery plans based on real-time collection and analysis of traffic information, inventory data, demand forecasts, etc. This system mainly functions using a server and terminals.

[1122] The server first collects traffic information. Specifically, it uses a traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. Google Maps API can be used for this. The obtained traffic data is stored in a PostgreSQL database.

[1123] Next, the server analyzes the collected traffic data. Based on the traffic data, it evaluates the required time and congestion level of each route and calculates the optimal delivery route using the Dijkstra algorithm or A algorithm. The results of this analysis are saved in JSON format and later sent to the terminal.

[1124] The server also retrieves inventory data from each warehouse and store's inventory management system. Specifically, it uses APIs to collect real-time inventory status from systems such as SAP and Oracle SCM. The retrieved inventory data is analyzed to determine whether a specific item is out of stock. This creates a list of items that are in short supply.

[1125] Additionally, the server collects past sales data to forecast demand. To do this, it retrieves data from a database or a third-party sales database (e.g., Amazon Web Services or Google BigQuery). It then uses AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand from the past data. This prediction also takes into account the impact of seasonal fluctuations and specific events.

[1126] Based on the results of the analysis and predictions above, the server automatically generates an optimal delivery plan. The server calculates how many products to deliver to which stores and when, creating an efficient schedule. The generated delivery plan is sent to the terminal in real time.

[1127] The terminal is responsible for notifying the driver of the delivery plan. The optimal route information and delivery plan sent from the server are displayed by the terminal's application. The driver can use this information to make deliveries along the optimal route. The terminal also supports real-time updates, allowing it to quickly respond to changes in traffic and inventory conditions.

[1128] As a concrete example, consider the case where a delivery company makes deliveries during the morning rush hour. The company uses a server to collect traffic information from the Google Maps API, analyzes it, and calculates the optimal route. It obtains inventory data from SAP and Oracle SCM and identifies products that are in short supply. It also uses an AI algorithm to forecast demand based on past sales data, predicting that certain products are likely to be in short supply. Based on this data, the server generates an optimal delivery plan and sends it to the terminal. The driver can then follow the instructions on the terminal to make efficient deliveries.

[1129] Examples of prompts for a generative AI model include:

[1130] "Please give me some prompts for building an AI algorithm that automatically generates optimal delivery route plans using real-time traffic information, inventory data, and demand forecasts in a logistics delivery system."

[1131] In this way, the system of the present invention integrates real-time information and data analysis to achieve more efficient logistics.

[1132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1133] Step 1:

[1134] Collection of traffic information

[1135] Input: Traffic request from Google Maps API

[1136] Specific operation: The server accesses the Google Maps API at specified intervals to obtain the latest road congestion information, accident information, construction information, etc.

[1137] Output: Traffic information dataset

[1138] A concrete example: A server calls the Google Maps API every minute and stores the collected traffic data in a PostgreSQL database.

[1139] Step 2:

[1140] Traffic data analysis

[1141] Input: Traffic information dataset collected in step 1

[1142] How it works: The server analyzes the stored traffic data and evaluates the travel time and congestion level of each route.

[1143] Output: Analyzed traffic information (travel time, congestion level, etc.)

[1144] Specific example: The server uses Dijkstra algorithm to calculate the shortest route for each delivery route and also evaluates the congestion level.

[1145] Step 3:

[1146] Calculating the best delivery route

[1147] Input: Traffic information parsed in step 2

[1148] Specific operation: The server uses algorithm A to calculate the optimal delivery route based on traffic data.

[1149] Output: Optimal delivery route information

[1150] Specific example: The server saves the calculation results in JSON format and delivers them to the device later.

[1151] Step 4:

[1152] Inventory data collection

[1153] Input: API requests from inventory management systems at each warehouse and store

[1154] Specific operation: The server uses the API of inventory management systems such as SAP and Oracle SCM to obtain real-time inventory data for each warehouse and store.

[1155] Output: Inventory dataset

[1156] Specific example: The server periodically collects data from each warehouse's system and stores it in a database.

[1157] Step 5:

[1158] Inventory data analysis

[1159] Input: Inventory dataset collected in step 4

[1160] What happens: The server analyzes the collected inventory data and identifies which items are in short supply.

[1161] Output: List of missing items

[1162] Specific example: The server checks the stock level of each product and generates a list of products that are below a threshold.

[1163] Step 6:

[1164] Demand forecasting

[1165] Input: Historical sales data from a sales database

[1166] How it works: The server collects past sales data and uses AI algorithms (e.g., TensorFlow) to predict future demand.

[1167] Output: Demand forecast data

[1168] Specific example: The server uses a TensorFlow model to predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[1169] Step 7:

[1170] Generate a delivery plan

[1171] Input: Optimal delivery route information in Step 3, Shortage product list in Step 5, Demand forecast data in Step 6

[1172] Specific operation: The server integrates this data and automatically generates an efficient delivery plan.

[1173] Output: Delivery plan

[1174] Specific example: The server calculates how many items to deliver to which stores and when, and saves the delivery plan as a list.

[1175] Step 8:

[1176] Delivery plan notification

[1177] Input: The shipping plan generated in step 7

[1178] Specific operation: The server sends the generated delivery plan to the terminal.

[1179] Output: Delivery plan notified to the terminal

[1180] A concrete example: Drivers can check their trip plans through an application on their device and receive real-time updates.

[1181] In this way, the system uses the data collected and analyzed at each step to automatically generate optimal delivery plans and achieve efficient logistics.

[1182] (Application example 1)

[1183] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1184] Conventional food delivery systems face challenges in streamlining delivery plans due to the difficulty of managing fluctuations in traffic information and inventory data in real time. Demand forecasts are also inadequate, leading to excess or shortages of inventory. This leads to problems such as reduced work efficiency for delivery drivers and lower customer satisfaction.

[1185] 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.

[1186] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for outputting the delivery plan, means for performing real-time delivery updates, and means for sending notification information to the terminal, thereby integrating real-time information and enabling the automatic generation of an efficient delivery plan.

[1187] "Traffic information" is data about current road conditions, such as road congestion, accident information, and construction information.

[1188] "Inventory data" refers to data about the current quantity of goods or materials in a warehouse or store.

[1189] "Demand forecasting" is a method of predicting future demand for products and services based on past sales data and seasonal data.

[1190] "Distribution planning" refers to the planning of routes and schedules for efficiently delivering products, taking into account demand forecasts and inventory status.

[1191] "Real-time updates" refers to the process of updating the system to reflect current situations and data immediately.

[1192] "Notification information" refers to information provided in real time, such as alerts and instructions sent from the server to the terminal.

[1193] A "terminal" is a device used to receive information, such as a smartphone or tablet.

[1194] A "server" is a computer system that collects, analyzes, stores, and provides the results to other devices.

[1195] "API" stands for Application Program Interface, a mechanism for exchanging data and functions between different software.

[1196] The system for implementing this invention is mainly composed of a server and a terminal. The server mainly collects data, analyzes it, makes predictions, and generates plans, while the terminal notifies the driver of this information.

[1197] Explanation of program processing

[1198] 1. Collection and analysis of real-time traffic information

[1199] The server uses Google Maps API and HERE API to collect real-time traffic information. The collected data includes road congestion, accident information, construction information, etc. This data is analyzed to evaluate the required time and congestion level for each route.

[1200] 2. Inventory data collection and analysis

[1201] The server retrieves inventory data from restaurant inventory management systems via an API. The collected data is used to understand the current inventory status and identify which menu items are in short supply.

[1202] 3. Demand forecasting

[1203] The server collects past order data and seasonal data and uses AI algorithms (e.g., TensorFlow) to forecast demand. This forecast predicts future demand and determines which products will be needed at what time.

[1204] 4. Generating and notifying a delivery plan

[1205] The server integrates traffic information, inventory data, and demand forecasts to generate an optimal delivery plan. The plan includes delivery schedules and routes to ensure efficient delivery. This plan is updated in real time and sent to the driver's device via push notifications and in-app messages.

[1206] Specific hardware and software names used

[1207] Hardware: Smartphone (iOS or Android device)

[1208] software:

[1209] Real-time traffic information API: Google Maps API, HERE API

[1210] Inventory Data Management: RESTful API

[1211] AI algorithm: TensorFlow (demand forecasting)

[1212] Database: Firebase or AWS RDS

[1213] Push notification service: Firebase Cloud Messaging

[1214] Specific examples

[1215] For example, when delivering pizza on a Friday night, the server operates as follows: First, the server obtains real-time traffic information from the Google Maps API and analyzes whether major roads are congested. At the same time, data obtained from the restaurant's inventory management system reveals that there is a shortage of pizza cheese. The AI ​​uses past data to forecast demand and predicts that demand for pizza will peak on Friday night.

[1216] Based on this information, the server generates optimal delivery routes and inventory replenishment routes and notifies the drivers. Drivers can then check the latest delivery routes and schedules on their smartphone apps, enabling them to deliver efficiently.

[1217] Prompt Sentence Examples

[1218] Program Name: FoodMaster

[1219] Use: Automatic generation of efficient delivery plans for food delivery

[1220] function:

[1221] 1. Collect and analyze real-time traffic information using Google Maps API

[1222] 2. Collect and analyze inventory data from restaurant inventory management systems

[1223] 3. Demand forecasting using past data using TensorFlow

[1224] 4. Automatically generate and notify optimal routes and delivery schedules using Firebase

[1225] 5. Push notifications and real-time updates in the app

[1226] Input data:

[1227] Traffic information API response data

[1228] Inventory information from restaurant inventory management systems

[1229] Historical Order Data

[1230] Output data:

[1231] Delivery route and schedule notifications

[1232] Inventory replenishment notifications to restaurants

[1233] prompt:

[1234] "Real-time traffic information," "Inventory management," "AI demand forecasting," "Optimal route calculation," "Firebase notifications"

[1235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1236] Step 1:

[1237] The server collects real-time traffic information using the Google Maps API and HERE API. Specifically, the server calls the API to obtain road congestion status, accident information, construction information, etc., and stores the response data. This data is used to evaluate the travel time and congestion level of each road segment.

[1238] Input: Traffic information API request

[1239] Output: Response data such as congestion status, accident information, construction information, etc.

[1240] Step 2:

[1241] The server analyzes the collected traffic information. Specifically, it uses algorithms to calculate the travel time and congestion level of each route. For example, if a road is congested, this information can be used to identify routes that drivers should avoid.

[1242] Input: Collected traffic information data

[1243] Output: Travel time and congestion data for each route

[1244] Step 3:

[1245] The server retrieves inventory data from the restaurant's inventory management system via an API. Specifically, the server sends a request to the restaurant's inventory system to understand the current inventory status and saves the response data. This allows the server to identify which menu items are in short supply.

[1246] Input: API request to inventory management system

[1247] Output: Stock status response data

[1248] Step 4:

[1249] The server analyzes the acquired inventory data and creates a list of items that need to be replenished. For example, if there is a shortage of pizza cheese, it adds that item to the list as a high-urgency item to be replenished.

[1250] Input: Retrieved inventory data

[1251] Output: A list of products that need to be replenished

[1252] Step 5:

[1253] The server performs demand forecasting based on past order data and seasonal data. Specifically, it uses AI algorithms (e.g., TensorFlow) to predict future demand. This forecast also takes into account seasonal fluctuations and the impact of specific events.

[1254] Input: Past order data, seasonal data

[1255] Output: Future demand forecast data

[1256] Step 6:

[1257] The server integrates traffic information, inventory data, and demand forecast results to generate an optimal delivery plan. Specifically, it uses algorithms to calculate optimal delivery routes and schedules.

[1258] Input: Traffic information, inventory data, demand forecast data

[1259] Output: Delivery plan (optimal delivery route and schedule)

[1260] Step 7:

[1261] The server updates the generated delivery plan in real time and sends a push notification to the driver's device using Firebase Cloud Messaging. The driver can then check the latest delivery plan in the app.

[1262] Input: Generated dispatch plan

[1263] Output: Notification data sent to the device (push notifications and in-app updates)

[1264] 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.

[1265] This invention combines a system that integrates real-time traffic information, inventory data, and demand forecasts to automatically generate efficient delivery plans, with an emotion engine that recognizes user emotions. In addition to the functions of collecting and analyzing traffic information, managing and analyzing inventory data, forecasting demand, and generating and outputting delivery plans, this system also recognizes user emotions, thereby improving the efficiency of delivery work and the user experience.

[1266] Explanation of program processing

[1267] Collection and analysis of real-time traffic information

[1268] 1. The server collects real-time traffic information.

[1269] The server calls the traffic information API, obtains the latest data such as road congestion, accident information, and construction information, and stores it in a database.

[1270] 2. The server analyzes the traffic data.

[1271] Based on the collected data, the required time and congestion level for each route are calculated, and the optimal delivery route is selected using an algorithm.

[1272] 3. The device notifies the driver of the optimal route.

[1273] The terminal notifies the driver of the optimal route information received from the server and displays detailed route information.

[1274] Inventory data collection and analysis

[1275] 1. The server collects inventory data.

[1276] Real-time inventory information is obtained from each warehouse and store's inventory management system via API and stored in a database.

[1277] 2. The server parses the inventory data.

[1278] Analyze collected inventory data to identify items that are low or need replenishing.

[1279] 3. The server reflects this in the delivery plan.

[1280] Based on the results of inventory data analysis, a delivery plan is automatically generated that prioritizes replenishing missing items and is incorporated into the optimal delivery route.

[1281] 4. The device notifies the driver of the updated delivery plan.

[1282] Drivers make efficient deliveries based on the schedule and product pickup list displayed on the terminal.

[1283] Generate demand forecasts and delivery plans

[1284] 1. The server collects past sales data.

[1285] Past sales data, seasonal data, and event information are retrieved from the database and input into the forecasting model.

[1286] 2. The server makes a demand forecast.

[1287] AI algorithms are used to predict future demand based on the acquired data.

[1288] 3. The server generates an optimal delivery plan based on the demand forecast results.

[1289] Routes for efficiently delivering products to each store are calculated based on predicted demand, and this is reflected in delivery plans.

[1290] 4. The device notifies the driver of the delivery plan.

[1291] The generated delivery plan is sent to the driver via the terminal, and delivery activities are carried out based on information updated in real time.

[1292] Recognizing user emotions with an emotion engine

[1293] 1. The device collects the user's voice data.

[1294] Voice data is collected when a user speaks into the terminal.

[1295] 2. The server analyzes the audio data.

[1296] The emotion engine recognizes the user's emotions from the collected voice data, and the analysis results are stored in a database and added to the user's data.

[1297] 3. The device collects the user's facial expression data.

[1298] The system uses the device's built-in camera to collect the user's facial expression data in real time.

[1299] 4. The server analyzes the facial expression data.

[1300] The emotion engine is used to recognize the user's emotions from facial expression data, and the results are also stored in the database.

[1301] 5. The server uses the emotion data to optimize the delivery plan.

[1302] We provide flexible delivery services that take into account the customer experience, including user emotional data.

[1303] Specific examples

[1304] For example, suppose a delivery company needs to plan efficient delivery routes based on real-time traffic information and then combine inventory data and demand forecasts to plan replenishment. In this case, the server collects and analyzes various data to automatically generate optimal delivery routes and replenishment plans. Furthermore, the terminal analyzes the user's voice input and facial expressions using an emotion engine. If the user is feeling stressed, the system can provide flexibility in the delivery plan, thereby improving user satisfaction. In this way, the system of the present invention integrates real-time information, data analysis, and emotion recognition to simultaneously improve logistics efficiency and customer satisfaction.

[1305] The processing flow will be explained below.

[1306] Collection and analysis of real-time traffic information

[1307] Step 1:

[1308] The server periodically calls the traffic information API to obtain real-time data such as road congestion, accident information, construction information, etc. The obtained data is stored in the server's database.

[1309] Step 2:

[1310] The server analyzes the stored traffic data and evaluates the travel time and congestion level of each delivery route, using traffic prediction models and algorithms.

[1311] Step 3:

[1312] Based on the analysis results, the server selects the most efficient route, taking into account delivery delays and fuel efficiency.

[1313] Step 4:

[1314] The device notifies the driver of the optimal route information received from the server, and provides detailed route information to the driver using push notifications and in-app messages.

[1315] Inventory data collection and analysis

[1316] Step 1:

[1317] The server collects inventory data from each warehouse and store's inventory management system via API, including product counts, location information, and replenishment needs.

[1318] Step 2:

[1319] The server collects inventory data, stores it in a database, and updates it in real time. The stored data is then analyzed.

[1320] Step 3:

[1321] The server analyzes inventory data to identify items that are in short supply or need urgent replenishment, and creates a list of high-priority items based on the analysis results.

[1322] Step 4:

[1323] The server automatically generates a delivery plan that reflects the analysis results, and the generated delivery plan includes routes that prioritize urgent products.

[1324] Step 5:

[1325] The terminal notifies the driver of the latest delivery plan, and the driver can check the schedule and product pickup list through the terminal application.

[1326] Generate demand forecasts and delivery plans

[1327] Step 1:

[1328] The server retrieves past sales data, seasonal data, and event data from the database. This data serves as the basis for demand forecasting.

[1329] Step 2:

[1330] The server uses AI algorithms to predict future demand based on the acquired data. The forecasting model is based on past data and takes into account trends and seasonality.

[1331] Step 3:

[1332] The server automatically generates an optimal delivery plan based on the prediction results, calculating which products to deliver to which stores and when, and creating an efficient schedule.

[1333] Step 4:

[1334] The server then combines the generated delivery plan into an optimal route and determines the final delivery route, thereby optimizing time and resources.

[1335] Step 5:

[1336] The device notifies the driver of the optimized delivery plan, and the driver carries out their work based on delivery information updated in real time.

[1337] Recognizing user emotions with an emotion engine

[1338] Step 1:

[1339] The device collects the user's voice data. When the user interacts with the device, the voice is picked up through the microphone.

[1340] Step 2:

[1341] The server analyzes the collected voice data, uses an emotion engine to recognize the user's emotional state from the voice data, and stores the analysis results in a database.

[1342] Step 3:

[1343] The device collects the user's facial expression data, which is acquired in real time via the device's camera.

[1344] Step 4:

[1345] The server analyzes the facial expression data, uses an emotion engine to recognize emotions from the user's facial expressions, and stores the analysis results in a database.

[1346] Step 5:

[1347] The server uses the accumulated emotional data to provide services that take into account the user's emotional state, enabling it to provide feedback to drivers and customize customer service.

[1348] Specific examples

[1349] Let's take the example of a driver checking a delivery plan before setting off on a certain day. First, the server calls a traffic information API to obtain and analyze congestion and accident information and determine the optimal delivery route. Next, the same server collects and analyzes inventory data, identifies products that urgently need replenishment, and reflects this in the delivery plan. Furthermore, the server performs demand forecasting using past sales data and optimizes the delivery plan based on the forecast results. Finally, as the driver checks the optimal route and delivery plan delivered to him via his device before setting off, the emotion engine analyzes the user's emotions and can respond flexibly if the driver is feeling stressed.

[1350] In this way, the system of the present invention can improve the efficiency of delivery operations and the user experience through cooperative operation between the server and terminals over multiple stages.

[1351] Example 2

[1352] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1353] Existing delivery planning systems manage elements such as traffic information, inventory data, and demand forecasts separately, but are unable to integrate these to generate efficient delivery plans. Furthermore, the emotional state of the user is not reflected in the delivery plan, making it difficult to sufficiently improve customer satisfaction.

[1354] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and analyzing traffic information, a means for collecting and analyzing inventory data, a means for performing demand forecasting, a means for recognizing user emotions, a means for automatically generating an optimal delivery plan based on the results of the analysis and prediction, and a means for outputting the delivery plan. This makes it possible to generate an optimal delivery plan by integrating traffic information, inventory data, demand forecasting, and user emotions, thereby improving customer satisfaction.

[1355] "Traffic information" refers to real-time data such as road congestion, accident information, and construction information.

[1356] "Inventory data" refers to data including the quantity, location, and status of products in each warehouse and store.

[1357] "Demand forecasting" is the prediction of future product demand based on past sales data and other relevant information.

[1358] "Emotion recognition" refers to the process of analyzing a user's voice and facial expressions to identify their emotional state.

[1359] A "delivery plan" is an optimal delivery route and schedule generated by integrating traffic information, inventory data, demand forecasts, and user emotion recognition results.

[1360] "API" is an abbreviation for Application Program Interface, a means by which different software applications communicate with each other.

[1361] A "server" is a central computer system that collects, analyzes, processes data, and provides information to client terminals.

[1362] A "terminal" is a device that a user can directly operate and receive information from, and includes smartphones, tablets, and the like.

[1363] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1364] An "algorithm" is a procedure or computational method for solving a particular problem.

[1365] A "machine learning model" is a mathematical model that uses data to learn patterns and make predictions or classifications.

[1366] An "emotion engine" is software for analyzing emotions from data such as voice and facial expressions.

[1367] This invention is a system that automatically generates efficient delivery plans by integrating traffic information, inventory data, demand forecasts, and user emotions. This system collects and analyzes traffic information, manages and analyzes inventory data, forecasts demand, generates and outputs delivery plans, and also has the ability to recognize user emotions.

[1368] Hardware and software used

[1369] Server: A central computer system that collects and analyzes data. An example product is a cloud server (e.g., Amazon Web Services (AWS)).

[1370] Terminal: A device for inputting and outputting data. In this example, we use smartphones and tablet terminals (e.g., iPhones and Android devices).

[1371] Database: A system for storing, managing, and searching data. Relational databases such as PostgreSQL and MySQL are used.

[1372] Software API: An application program interface for retrieving and transmitting data. Examples include the Google Maps API and a REST API for an inventory management system.

[1373] Machine learning model: A model for learning from past data and making demand forecasts. TensorFlow is used.

[1374] Emotion Engine: A software engine for analyzing voice and facial expression data. Powered by IBM Watson.

[1375] Algorithm: A procedure for analyzing data and deriving the required results. Here, an algorithm implemented in Python is used.

[1376] System Implementation Method

[1377] 1. Collection and analysis of real-time traffic information

[1378] The server uses the Google Maps API to collect current traffic information (congestion, accidents, construction, etc.). The collected data is stored in a PostgreSQL database. Then, a Python algorithm calculates the travel time and congestion level for each route.

[1379] 2. Inventory data collection and analysis

[1380] The server retrieves inventory data from each warehouse and store's inventory management system via a REST API. This data is stored in a PostgreSQL database and analyzed by Python scripts to identify items that are running low or need to be replenished.

[1381] 3. Generate demand forecasts and delivery plans

[1382] The server retrieves past sales data, seasonal data, and event information from the database and uses TensorFlow's machine learning model to predict demand. Based on the predicted demand, an optimal delivery plan is generated.

[1383] 4. Flexible delivery response using emotion recognition

[1384] The device collects the user's voice and facial expression data. The voice data is sent to a server via a voice assistant such as Amazon Alexa and analyzed by IBM Watson's emotion engine. Facial expression data is also collected through the device's camera and similarly analyzed by the emotion engine. Based on this emotion data, the server can respond flexibly to delivery requests and improve user satisfaction.

[1385] Specific examples

[1386] For example, when a delivery company integrates traffic information, inventory data, and demand forecasts to plan optimal delivery routes, the server uses the Google Maps API to obtain the latest traffic data and uses a Python algorithm to calculate the optimal route. The server also collects inventory data from each warehouse and store via the API and automatically generates a delivery plan that prioritizes replenishing missing items. Furthermore, the IBM Watson emotion engine analyzes the user's voice input and facial expression data, allowing for flexibility in the delivery plan if the user is feeling stressed.

[1387] Prompt Sentence Examples

[1388] Based on the information below, generate a delivery plan for the next week and suggest improvements taking into account user sentiment data.

[1389] Sales data for the past month

[1390] Real-time traffic information

[1391] User voice and facial expression data

[1392] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1393] Step 1: Collecting traffic information

[1394] The server sends a request to the Google Maps API to get the latest traffic information (congestion, accidents, construction, etc.). It sends the API request as input and receives traffic data in JSON format as output.

[1395] The traffic data acquired by the server is stored in a PostgreSQL database. Specifically, each item of traffic information (e.g., location, congestion level, required time, etc.) is stored in the corresponding database table.

[1396] Step 2: Analyze traffic data

[1397] The server analyzes the stored traffic data using a Python script, reading the traffic data stored in the database as input and calculating the travel time and congestion level for each route as output.

[1398] The server runs an algorithm to select the optimal delivery route, which calculates the shortest and most efficient route by taking into account information such as travel time and congestion.

[1399] Step 3: Collect inventory data

[1400] The server retrieves real-time inventory data from the inventory management systems of each warehouse and store using REST APIs. It sends API requests as input and receives inventory data as output.

[1401] The server stores the inventory data it obtains in a PostgreSQL database. Specifically, it stores information such as the quantity, location, and status of each product in a database table.

[1402] Step 4: Analyze inventory data

[1403] The server parses the stored inventory data using a Python script that reads the inventory data stored in the database as input and identifies items that are missing or need to be replenished as output.

[1404] The server extracts data to generate a delivery plan that prioritizes items that are in short supply. Specifically, it lists items with stock levels below a certain level.

[1405] Step 5: Perform demand forecasting

[1406] The server retrieves historical sales data from the database, along with seasonal and event information. It executes a database query as input and retrieves historical sales data in JSON format as output.

[1407] The server performs demand forecasting using TensorFlow machine learning models. Past data is input to the model, and future demand forecasts are generated as output.

[1408] Step 6: Generate an optimal transportation plan

[1409] The server generates a delivery plan based on predicted demand data, inventory data, and traffic data. The demand forecast results, inventory data, and traffic data are input into the algorithm, and the optimal delivery route and schedule are generated as output.

[1410] The server stores the generated delivery plan in a PostgreSQL database.

[1411] Step 7: Collect user voice data

[1412] The device collects user voice data using a voice assistant such as Amazon Alexa. The device captures the user's speech as input using a microphone and generates voice data as output.

[1413] The device sends the collected voice data to the server. Specifically, the voice data is transferred to the server via API.

[1414] Step 8: Analyzing the audio data

[1415] The server analyzes the voice data using IBM Watson's emotion engine, passing the voice data as input to the emotion engine and generating emotion recognition results as output.

[1416] The server stores the emotion recognition results in a PostgreSQL database.

[1417] Step 9: Collecting user facial expression data

[1418] The device collects the user's facial expression data in real time using a built-in camera. It receives video data from the camera as input and generates facial expression data as output.

[1419] The facial expression data collected by the device is sent to the server. Specifically, the facial expression data is transferred to the server via API.

[1420] Step 10: Analyze facial expression data

[1421] The server analyzes the facial expression data using IBM Watson's emotion engine, passing the facial expression data as input to the emotion engine and generating emotion recognition results as output.

[1422] The server stores the emotion recognition results in a PostgreSQL database.

[1423] Step 11: Optimizing delivery plans with sentiment data

[1424] The server responds flexibly to delivery requests based on the emotional data. The emotional data is passed as input to a delivery plan generation algorithm, and a delivery plan that takes the user's emotional state into consideration is generated as output.

[1425] The server notifies the device of the optimized delivery plan, specifically by transferring the plan to the device via API, and the device displays detailed information to the driver.

[1426] (Application example 2)

[1427] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1428] In conventional delivery operations, delivery plans are mainly based solely on traffic information, inventory data, and demand forecasts, and no flexible response is made that takes user emotions into consideration. As a result, delivery delays and out-of-stock items can cause stress for users, reducing customer satisfaction. The present invention aims to automatically generate more efficient and flexible delivery plans and improve customer satisfaction by combining real-time traffic information, inventory data, demand forecasts, and user emotion recognition.

[1429] 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.

[1430] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for recognizing user emotions, means for optimizing the delivery plan based on emotion data, and means for outputting the delivery plan. This enables not only efficient delivery plans based on real-time information but also flexible delivery responses that take user emotions into consideration.

[1431] "Traffic information" refers to data on traffic flow, such as road congestion, accident information, and construction information, collected in real time.

[1432] "Inventory data" is information regarding the quantity and status of products in each warehouse and store.

[1433] "Demand forecasting" is the process of predicting future demand based on past sales data, seasonal data, and event information.

[1434] "Delivery planning" is a plan that automatically generates optimal delivery routes and schedules based on traffic information, inventory data, and demand forecasts.

[1435] "User's emotions" refers to the user's psychological state as recognized from voice, facial expressions, etc.

[1436] "Emotion data" is information about a user's emotions collected by means of voice recognition and facial expression recognition.

[1437] "Flexible delivery response" refers to a dynamic response that modifies conventional fixed delivery plans based on user emotional data to reduce user stress and dissatisfaction.

[1438] The present invention combines a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts, with an emotion engine that recognizes user emotions. The following describes an embodiment of the present invention in detail.

[1439] Hardware and Software Configuration

[1440] 1. Server:

[1441] The server is set up to collect and analyze traffic information, inventory data, demand forecast data, and emotion data. Specifically, it uses the following APIs and libraries:

[1442] Traffic information: Traffic information APIs such as Google Maps API

[1443] Inventory data: API to retrieve data from inventory management systems at each warehouse and store

[1444] Demand forecasting: AI algorithms (e.g., Scikit-Learn) to forecast demand based on historical sales data, seasonal data, and event information.

[1445] Emotion data: Speech recognition libraries (e.g., SpeechRecognition) and facial expression recognition libraries (e.g., EmotionRecognizer)

[1446] 2. Terminal:

[1447] The terminals are smartphones used by delivery personnel or in-vehicle head-mounted displays, and are responsible for receiving and displaying optimal delivery routes, inventory replenishment plans, demand forecast results, and optimized delivery plans sent from the server. The terminals also have the ability to collect voice input and facial expression data from users.

[1448] 3. User:

[1449] When the user speaks to the device, voice data is collected, and facial expression data is also captured through the built-in camera. This data is sent to the server, where the emotion engine analyzes the user's emotions.

[1450] Process flow example

[1451] 1. Real-time traffic information collection and analysis:

[1452] The server uses a traffic information API to collect real-time traffic information. The traffic data is analyzed and the optimal route is selected. The results are sent to the terminal and notified to the delivery person as the optimal route.

[1453] 2. Inventory data collection and analysis:

[1454] The server collects and analyzes inventory data from the inventory management systems of each warehouse and store, identifying items that are low in stock and incorporating this information into delivery plans.

[1455] 3. Generate demand forecasts and delivery plans:

[1456] The server collects past sales data, seasonal data, and event information, and uses AI algorithms to predict demand. Based on the results, optimal delivery routes and replenishment plans are generated.

[1457] 4. Emotion engine recognizes user emotions:

[1458] The device collects the user's voice and facial expression data and sends it to the server. The emotion engine analyzes this data and recognizes the user's emotions. Based on the results, the delivery plan is optimized.

[1459] Specific examples

[1460] For example, if a food delivery company were to adopt this system, delivery personnel would receive real-time information on optimal routes on their smartphones and confirm plans to prioritize replenishment of low-stock items. Also, if a user expresses an emotion that "the product is delayed," that information would be reflected immediately and a rapid response would be made.

[1461] Prompt Sentence Examples

[1462] An example prompt for running a system using a generative AI model is as follows:

[1463] "Create a food delivery plan using user emotion recognition. Use the following data to generate optimal delivery routes and inventory replenishment plans, and adapt based on user emotions:

[1464] Real-time traffic information (API: Google Maps API)

[1465] Inventory data (API: Inventory Management API)

[1466] Demand forecast data (past sales information)

[1467] User emotion data (voice and facial expression analysis)

[1468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1469] Step 1:

[1470] The server collects traffic information.

[1471] Input: Real-time traffic data from traffic information API

[1472] Specific operation: The server calls the traffic information API and obtains real-time traffic data such as road congestion status, accident information, and construction information.

[1473] Output: Collected traffic data (e.g., congestion level, travel time)

[1474] Step 2:

[1475] The server analyzes the traffic data.

[1476] Input: Collected traffic data

[1477] How it works: The server uses an algorithm to analyze the collected traffic data, calculate the travel time and congestion level for each route, and then select the optimal delivery route.

[1478] Output: Optimal delivery route information

[1479] Step 3:

[1480] A server collects inventory data.

[1481] Input: Inventory data from inventory management systems for each warehouse and store

[1482] Specific operation: The server calls the inventory management API and obtains inventory data for each warehouse and store in real time.

[1483] Output: Collected inventory data (e.g., number of items in stock)

[1484] Step 4:

[1485] The server parses the inventory data.

[1486] Input: Collected inventory data

[1487] What happens: The server analyzes inventory data to identify items that are low or need to be replenished.

[1488] Output: Missing items list

[1489] Step 5:

[1490] The server performs demand forecasting.

[1491] Input: Historical sales data, seasonal data, event information

[1492] Specific operation: The server uses an AI algorithm (e.g., Scikit-Learn) to predict future demand based on past sales data, seasonal data, and event information.

[1493] Output: Demand forecast curve

[1494] Step 6:

[1495] The server generates an optimal delivery plan based on the demand forecast results.

[1496] Input: Optimal delivery route information, shortage product list, demand forecast curve

[1497] Specific operation: The server integrates these input data and automatically generates efficient delivery routes and replenishment plans.

[1498] Output: Delivery plan

[1499] Step 7:

[1500] The terminal notifies the driver of the delivery plan.

[1501] Input: Delivery plan

[1502] Specific operation: Based on the delivery plan information received by the terminal from the server, the driver is shown a detailed schedule and a product pick-up list.

[1503] Output: The trip plan displayed on the driver's device

[1504] Step 8:

[1505] The terminal collects the user's voice data.

[1506] Input: User's voice

[1507] Specific operation: When the user speaks into the device, voice data is collected by the device.

[1508] Output: Collected audio data

[1509] Step 9:

[1510] The server analyzes the audio data.

[1511] Input: Collected audio data

[1512] Specific operation: The server uses a speech recognition library (e.g., SpeechRecognition) to analyze the collected voice data and recognize the user's emotions.

[1513] Output: Recognized emotion data

[1514] Step 10:

[1515] The terminal collects facial expression data of the user.

[1516] Input: User's facial expression

[1517] Specific operation: Using the device's built-in camera, the user's facial expression data is collected in real time.

[1518] Output: Collected facial expression data

[1519] Step 11:

[1520] The server analyzes the facial expression data.

[1521] Input: Collected facial expression data

[1522] Specific operation: The server uses a facial expression recognition library (e.g., EmotionRecognizer) to analyze facial expression data and recognize the user's emotions.

[1523] Output: Recognized emotion data

[1524] Step 12:

[1525] The server uses emotion data to optimize delivery plans.

[1526] Input: Recognized emotion data, existing delivery plan

[1527] Specific operation: Based on the user's emotional data, the server generates an optimized delivery plan that reduces the user's stress and dissatisfaction by adding flexibility to the conventional delivery plan.

[1528] Output: Optimized delivery plan

[1529] Step 13:

[1530] The device notifies the driver of an optimized delivery plan.

[1531] Input: Optimized delivery plan

[1532] Specific operation: The device notifies the driver of the optimized delivery plan received from the server and displays detailed route information and schedule changes.

[1533] Output: Optimized trip plan displayed on the driver's device

[1534] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1535] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1536] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1537] [Fourth embodiment]

[1538] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1539] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1540] 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).

[1541] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1542] 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.

[1543] 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).

[1544] 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.

[1545] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1546] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1547] 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.

[1548] 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.

[1549] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1550] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] This invention relates to a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts. This system utilizes a server and terminals to improve overall delivery efficiency.

[1552] Explanation of program processing

[1553] Collection and analysis of real-time traffic information

[1554] 1. The server collects real-time traffic information.

[1555] The server calls the traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. This data is updated according to the frequency of distribution and stored on the server.

[1556] 2. The server analyzes the traffic data.

[1557] Using the collected traffic data, the server evaluates the required travel time and congestion level of each route, and then uses an algorithm to analyze this data and calculate the optimal delivery route.

[1558] 3. The device notifies the driver of the optimal route.

[1559] The server calculates the optimal route and delivers it to the device, which then notifies the driver's application in real time. The device then displays detailed route information via push notifications and in-app messages.

[1560] Inventory data collection and analysis

[1561] 1. The server collects inventory data.

[1562] The server calls an API to obtain inventory information from the inventory management systems of each warehouse and store, allowing for real-time inventory status.

[1563] 2. The server parses the inventory data.

[1564] Analyze collected inventory data to identify which items are low or need to be replenished. If necessary, create a list of urgent items.

[1565] 3. The server reflects this in the delivery plan.

[1566] Based on the results of the inventory data analysis, the server adds inventory replenishment routes to the delivery plan, which is reflected in the delivery route and sent to the terminal.

[1567] Generate demand forecasts and delivery plans

[1568] 1. The server collects past sales data.

[1569] The server retrieves past sales data and seasonal data from the database and uses this as the basis for demand forecasting.

[1570] 2. The server makes a demand forecast.

[1571] Using this data, AI algorithms predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[1572] 3. The server generates an optimal delivery plan.

[1573] Based on the demand forecast results, the system calculates how many products to deliver to which stores and when, and generates an efficient delivery schedule.

[1574] 4. The device notifies the driver of the delivery plan.

[1575] The generated delivery plan is sent to the terminal, where the driver can view it through the application. The terminal is updated in real time, optimizing the driver's behavior.

[1576] Specific examples

[1577] Consider a delivery company that needs to deliver products to multiple stores during the morning rush hour. First, the server collects real-time road data from a traffic information API and analyzes congestion levels. Next, it retrieves inventory information from warehouses and store inventory management systems to identify products that are low in stock. It then performs demand forecasting based on past sales data, predicting that certain products are likely to be in short supply ahead of a weekend sale.

[1578] Based on this data, the server generates optimal delivery routes and creates detailed delivery plans that take into account inventory replenishment and demand forecasts. The terminal then notifies the driver of this information, ensuring efficient delivery. In this way, the system of the present invention integrates real-time information and data analysis to achieve efficient logistics.

[1579] The processing flow will be explained below.

[1580] Collection and analysis of real-time traffic information

[1581] Step 1:

[1582] The server periodically calls the traffic information API to obtain the latest traffic data, including road congestion status, accident information, and construction information.

[1583] Step 2:

[1584] The server stores the acquired traffic data in a database, which is used in later analysis steps.

[1585] Step 3:

[1586] The server analyzes the traffic data and calculates the travel time and congestion level for each delivery route using algorithms and traffic prediction models.

[1587] Step 4:

[1588] The server calculates the optimal delivery route, compares the travel time of each route, and selects the most efficient route.

[1589] Step 5:

[1590] The device receives the optimal route information from the server and notifies the driver via push notification or in-app message, displaying detailed route information.

[1591] Inventory data collection and analysis

[1592] Step 1:

[1593] The server calls an API that collects inventory data from each warehouse or store's inventory management system, including product quantities and replenishment needs.

[1594] Step 2:

[1595] The server stores the collected inventory data in a database, which is updated in real time.

[1596] Step 3:

[1597] The server analyzes the inventory data to determine which items are low in stock and creates a list of items that are low in stock or need to be replenished.

[1598] Step 4:

[1599] The server automatically generates a delivery plan based on the items in short supply, prioritizing items with high urgency and adding those stores or warehouses to the delivery route.

[1600] Step 5:

[1601] The device notifies the driver of updated delivery plans, including schedules and pickup lists, which can be viewed within the app.

[1602] Generate demand forecasts and delivery plans

[1603] Step 1:

[1604] The server retrieves past sales data, seasonal data, and event information from the database.

[1605] Step 2:

[1606] Based on the data acquired by the server, demand forecasts are made using AI algorithms. The forecasting model learns from past data and calculates future demand.

[1607] Step 3:

[1608] The server automatically generates an optimal delivery plan based on the demand forecast results, calculating how many items to deliver to which stores and when.

[1609] Step 4:

[1610] The server then combines the delivery plan into an optimal route and finalizes the plan.

[1611] Step 5:

[1612] The device receives an optimized delivery plan from the server and notifies the driver, allowing the driver to make efficient deliveries based on information updated in real time.

[1613] Example 1

[1614] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1615] In the modern logistics industry, it is extremely important to create efficient delivery plans. However, it is difficult to collect and analyze a wide range of information, such as traffic information, inventory data, and demand forecasts, in real time, and integrate them to calculate optimal delivery routes. There is also a need for a method to quickly notify drivers of delivery plans that take this information into account. A system that can solve these problems is needed.

[1616] 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.

[1617] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for collecting traffic data in real time, means for calculating an optimal delivery route using the traffic data, means for acquiring data from inventory management systems of each warehouse and store, means for identifying shortages in inventory data and reflecting them in the delivery plan, means for collecting past sales data and performing demand forecasting, and means for notifying the terminal of the generated delivery plan. This enables real-time information collection and analysis, and efficient generation and notification of delivery plans.

[1618] "Traffic information" refers to data relating to traffic conditions such as road congestion, accident information, and construction information.

[1619] "Inventory data" is information regarding the inventory status of products at each warehouse and store.

[1620] "Demand forecasting" refers to the algorithms and results that predict future demand based on past sales data and seasonal data.

[1621] "Delivery plan" refers to a schedule including the order and route of product delivery, which is automatically generated based on collected and analyzed data.

[1622] "Real-time" means collecting, analyzing, and processing data at the same speed as the real world.

[1623] "API" stands for Application Programming Interface, a mechanism for exchanging data and functions between software programs.

[1624] An "analytical algorithm" is a computational method for analyzing data and extracting useful information for a specific purpose.

[1625] A "terminal" is a device for inputting and outputting information, and in this system specifically refers to a device on which the application used by the driver is installed.

[1626] "Sales data" refers to data relating to past transactions and product sales.

[1627] This invention relates to a system that automatically generates efficient delivery plans based on real-time collection and analysis of traffic information, inventory data, demand forecasts, etc. This system mainly functions using a server and terminals.

[1628] The server first collects traffic information. Specifically, it uses a traffic information API to obtain the latest data on road congestion, accident information, construction information, etc. Google Maps API can be used for this. The obtained traffic data is stored in a PostgreSQL database.

[1629] Next, the server analyzes the collected traffic data. Based on the traffic data, it evaluates the required time and congestion level of each route and calculates the optimal delivery route using the Dijkstra algorithm or A algorithm. The results of this analysis are saved in JSON format and later sent to the terminal.

[1630] The server also retrieves inventory data from each warehouse and store's inventory management system. Specifically, it uses APIs to collect real-time inventory status from systems such as SAP and Oracle SCM. The retrieved inventory data is analyzed to determine whether a specific item is out of stock. This creates a list of items that are in short supply.

[1631] Additionally, the server collects past sales data to forecast demand. To do this, it retrieves data from a database or a third-party sales database (e.g., Amazon Web Services or Google BigQuery). It then uses AI algorithms (e.g., TensorFlow or PyTorch) to predict future demand from the past data. This prediction also takes into account the impact of seasonal fluctuations and specific events.

[1632] Based on the results of the analysis and predictions above, the server automatically generates an optimal delivery plan. The server calculates how many products to deliver to which stores and when, creating an efficient schedule. The generated delivery plan is sent to the terminal in real time.

[1633] The terminal is responsible for notifying the driver of the delivery plan. The optimal route information and delivery plan sent from the server are displayed by the terminal's application. The driver can use this information to make deliveries along the optimal route. The terminal also supports real-time updates, allowing it to quickly respond to changes in traffic and inventory conditions.

[1634] As a concrete example, consider the case where a delivery company makes deliveries during the morning rush hour. The company uses a server to collect traffic information from the Google Maps API, analyzes it, and calculates the optimal route. It obtains inventory data from SAP and Oracle SCM and identifies products that are in short supply. It also uses an AI algorithm to forecast demand based on past sales data, predicting that certain products are likely to be in short supply. Based on this data, the server generates an optimal delivery plan and sends it to the terminal. The driver can then follow the instructions on the terminal to make efficient deliveries.

[1635] Examples of prompts for a generative AI model include:

[1636] "Please give me some prompts for building an AI algorithm that automatically generates optimal delivery route plans using real-time traffic information, inventory data, and demand forecasts in a logistics delivery system."

[1637] In this way, the system of the present invention integrates real-time information and data analysis to achieve more efficient logistics.

[1638] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1639] Step 1:

[1640] Collection of traffic information

[1641] Input: Traffic request from Google Maps API

[1642] Specific operation: The server accesses the Google Maps API at specified intervals to obtain the latest road congestion information, accident information, construction information, etc.

[1643] Output: Traffic information dataset

[1644] A concrete example: A server calls the Google Maps API every minute and stores the collected traffic data in a PostgreSQL database.

[1645] Step 2:

[1646] Traffic data analysis

[1647] Input: Traffic information dataset collected in step 1

[1648] How it works: The server analyzes the stored traffic data and evaluates the travel time and congestion level of each route.

[1649] Output: Analyzed traffic information (travel time, congestion level, etc.)

[1650] Specific example: The server uses Dijkstra algorithm to calculate the shortest route for each delivery route and also evaluates the congestion level.

[1651] Step 3:

[1652] Calculating the best delivery route

[1653] Input: Traffic information parsed in step 2

[1654] Specific operation: The server uses algorithm A to calculate the optimal delivery route based on traffic data.

[1655] Output: Optimal delivery route information

[1656] Specific example: The server saves the calculation results in JSON format and delivers them to the device later.

[1657] Step 4:

[1658] Inventory data collection

[1659] Input: API requests from inventory management systems at each warehouse and store

[1660] Specific operation: The server uses the API of inventory management systems such as SAP and Oracle SCM to obtain real-time inventory data for each warehouse and store.

[1661] Output: Inventory dataset

[1662] Specific example: The server periodically collects data from each warehouse's system and stores it in a database.

[1663] Step 5:

[1664] Inventory data analysis

[1665] Input: Inventory dataset collected in step 4

[1666] What happens: The server analyzes the collected inventory data and identifies which items are in short supply.

[1667] Output: List of missing items

[1668] Specific example: The server checks the stock level of each product and generates a list of products that are below a threshold.

[1669] Step 6:

[1670] Demand forecasting

[1671] Input: Historical sales data from a sales database

[1672] How it works: The server collects past sales data and uses AI algorithms (e.g., TensorFlow) to predict future demand.

[1673] Output: Demand forecast data

[1674] Specific example: The server uses a TensorFlow model to predict future demand, taking into account seasonal fluctuations and the impact of specific events.

[1675] Step 7:

[1676] Generate a delivery plan

[1677] Input: Optimal delivery route information in Step 3, Shortage product list in Step 5, Demand forecast data in Step 6

[1678] Specific operation: The server integrates this data and automatically generates an efficient delivery plan.

[1679] Output: Delivery plan

[1680] Specific example: The server calculates how many items to deliver to which stores and when, and saves the delivery plan as a list.

[1681] Step 8:

[1682] Delivery plan notification

[1683] Input: The shipping plan generated in step 7

[1684] Specific operation: The server sends the generated delivery plan to the terminal.

[1685] Output: Delivery plan notified to the terminal

[1686] A concrete example: Drivers can check their trip plans through an application on their device and receive real-time updates.

[1687] In this way, the system uses the data collected and analyzed at each step to automatically generate optimal delivery plans and achieve efficient logistics.

[1688] (Application example 1)

[1689] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1690] Conventional food delivery systems face challenges in streamlining delivery plans due to the difficulty of managing fluctuations in traffic information and inventory data in real time. Demand forecasts are also inadequate, leading to excess or shortages of inventory. This leads to problems such as reduced work efficiency for delivery drivers and lower customer satisfaction.

[1691] 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.

[1692] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for outputting the delivery plan, means for performing real-time delivery updates, and means for sending notification information to the terminal, thereby integrating real-time information and enabling the automatic generation of an efficient delivery plan.

[1693] "Traffic information" is data about current road conditions, such as road congestion, accident information, and construction information.

[1694] "Inventory data" refers to data about the current quantity of goods or materials in a warehouse or store.

[1695] "Demand forecasting" is a method of predicting future demand for products and services based on past sales data and seasonal data.

[1696] "Distribution planning" refers to the planning of routes and schedules for efficiently delivering products, taking into account demand forecasts and inventory status.

[1697] "Real-time updates" refers to the process of updating the system to reflect current situations and data immediately.

[1698] "Notification information" refers to information provided in real time, such as alerts and instructions sent from the server to the terminal.

[1699] A "terminal" is a device used to receive information, such as a smartphone or tablet.

[1700] A "server" is a computer system that collects, analyzes, stores, and provides the results to other devices.

[1701] "API" stands for Application Program Interface, a mechanism for exchanging data and functions between different software.

[1702] The system for implementing this invention is mainly composed of a server and a terminal. The server mainly collects data, analyzes it, makes predictions, and generates plans, while the terminal notifies the driver of this information.

[1703] Explanation of program processing

[1704] 1. Collection and analysis of real-time traffic information

[1705] The server uses Google Maps API and HERE API to collect real-time traffic information. The collected data includes road congestion, accident information, construction information, etc. This data is analyzed to evaluate the required time and congestion level for each route.

[1706] 2. Inventory data collection and analysis

[1707] The server retrieves inventory data from restaurant inventory management systems via an API. The collected data is used to understand the current inventory status and identify which menu items are in short supply.

[1708] 3. Demand forecasting

[1709] The server collects past order data and seasonal data and uses AI algorithms (e.g., TensorFlow) to forecast demand. This forecast predicts future demand and determines which products will be needed at what time.

[1710] 4. Generating and notifying a delivery plan

[1711] The server integrates traffic information, inventory data, and demand forecasts to generate an optimal delivery plan. The plan includes delivery schedules and routes to ensure efficient delivery. This plan is updated in real time and sent to the driver's device via push notifications and in-app messages.

[1712] Specific hardware and software names used

[1713] Hardware: Smartphone (iOS or Android device)

[1714] software:

[1715] Real-time traffic information API: Google Maps API, HERE API

[1716] Inventory Data Management: RESTful API

[1717] AI algorithm: TensorFlow (demand forecasting)

[1718] Database: Firebase or AWS RDS

[1719] Push notification service: Firebase Cloud Messaging

[1720] Specific examples

[1721] For example, when delivering pizza on a Friday night, the server operates as follows: First, the server obtains real-time traffic information from the Google Maps API and analyzes whether major roads are congested. At the same time, data obtained from the restaurant's inventory management system reveals that there is a shortage of pizza cheese. The AI ​​uses past data to forecast demand and predicts that demand for pizza will peak on Friday night.

[1722] Based on this information, the server generates optimal delivery routes and inventory replenishment routes and notifies the drivers. Drivers can then check the latest delivery routes and schedules on their smartphone apps, enabling them to deliver efficiently.

[1723] Prompt Sentence Examples

[1724] Program Name: FoodMaster

[1725] Use: Automatic generation of efficient delivery plans for food delivery

[1726] function:

[1727] 1. Collect and analyze real-time traffic information using Google Maps API

[1728] 2. Collect and analyze inventory data from restaurant inventory management systems

[1729] 3. Demand forecasting using past data using TensorFlow

[1730] 4. Automatically generate and notify optimal routes and delivery schedules using Firebase

[1731] 5. Push notifications and real-time updates in the app

[1732] Input data:

[1733] Traffic information API response data

[1734] Inventory information from restaurant inventory management systems

[1735] Historical Order Data

[1736] Output data:

[1737] Delivery route and schedule notifications

[1738] Inventory replenishment notifications to restaurants

[1739] prompt:

[1740] "Real-time traffic information," "Inventory management," "AI demand forecasting," "Optimal route calculation," "Firebase notifications"

[1741] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1742] Step 1:

[1743] The server collects real-time traffic information using the Google Maps API and HERE API. Specifically, the server calls the API to obtain road congestion status, accident information, construction information, etc., and stores the response data. This data is used to evaluate the travel time and congestion level of each road segment.

[1744] Input: Traffic information API request

[1745] Output: Response data such as congestion status, accident information, construction information, etc.

[1746] Step 2:

[1747] The server analyzes the collected traffic information. Specifically, it uses algorithms to calculate the travel time and congestion level of each route. For example, if a road is congested, this information can be used to identify routes that drivers should avoid.

[1748] Input: Collected traffic information data

[1749] Output: Travel time and congestion data for each route

[1750] Step 3:

[1751] The server retrieves inventory data from the restaurant's inventory management system via an API. Specifically, the server sends a request to the restaurant's inventory system to understand the current inventory status and saves the response data. This allows the server to identify which menu items are in short supply.

[1752] Input: API request to inventory management system

[1753] Output: Stock status response data

[1754] Step 4:

[1755] The server analyzes the acquired inventory data and creates a list of items that need to be replenished. For example, if there is a shortage of pizza cheese, it adds that item to the list as a high-urgency item to be replenished.

[1756] Input: Retrieved inventory data

[1757] Output: A list of products that need to be replenished

[1758] Step 5:

[1759] The server performs demand forecasting based on past order data and seasonal data. Specifically, it uses AI algorithms (e.g., TensorFlow) to predict future demand. This forecast also takes into account seasonal fluctuations and the impact of specific events.

[1760] Input: Past order data, seasonal data

[1761] Output: Future demand forecast data

[1762] Step 6:

[1763] The server integrates traffic information, inventory data, and demand forecast results to generate an optimal delivery plan. Specifically, it uses algorithms to calculate optimal delivery routes and schedules.

[1764] Input: Traffic information, inventory data, demand forecast data

[1765] Output: Delivery plan (optimal delivery route and schedule)

[1766] Step 7:

[1767] The server updates the generated delivery plan in real time and sends a push notification to the driver's device using Firebase Cloud Messaging. The driver can then check the latest delivery plan in the app.

[1768] Input: Generated dispatch plan

[1769] Output: Notification data sent to the device (push notifications and in-app updates)

[1770] 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.

[1771] This invention combines a system that integrates real-time traffic information, inventory data, and demand forecasts to automatically generate efficient delivery plans, with an emotion engine that recognizes user emotions. In addition to the functions of collecting and analyzing traffic information, managing and analyzing inventory data, forecasting demand, and generating and outputting delivery plans, this system also recognizes user emotions, thereby improving the efficiency of delivery work and the user experience.

[1772] Explanation of program processing

[1773] Collection and analysis of real-time traffic information

[1774] 1. The server collects real-time traffic information.

[1775] The server calls the traffic information API, obtains the latest data such as road congestion, accident information, and construction information, and stores it in a database.

[1776] 2. The server analyzes the traffic data.

[1777] Based on the collected data, the required time and congestion level for each route are calculated, and the optimal delivery route is selected using an algorithm.

[1778] 3. The device notifies the driver of the optimal route.

[1779] The terminal notifies the driver of the optimal route information received from the server and displays detailed route information.

[1780] Inventory data collection and analysis

[1781] 1. The server collects inventory data.

[1782] Real-time inventory information is obtained from each warehouse and store's inventory management system via API and stored in a database.

[1783] 2. The server parses the inventory data.

[1784] Analyze collected inventory data to identify items that are low or need replenishing.

[1785] 3. The server reflects this in the delivery plan.

[1786] Based on the results of inventory data analysis, a delivery plan is automatically generated that prioritizes replenishing missing items and is incorporated into the optimal delivery route.

[1787] 4. The device notifies the driver of the updated delivery plan.

[1788] Drivers make efficient deliveries based on the schedule and product pickup list displayed on the terminal.

[1789] Generate demand forecasts and delivery plans

[1790] 1. The server collects past sales data.

[1791] Past sales data, seasonal data, and event information are retrieved from the database and input into the forecasting model.

[1792] 2. The server makes a demand forecast.

[1793] AI algorithms are used to predict future demand based on the acquired data.

[1794] 3. The server generates an optimal delivery plan based on the demand forecast results.

[1795] Routes for efficiently delivering products to each store are calculated based on predicted demand, and this is reflected in delivery plans.

[1796] 4. The device notifies the driver of the delivery plan.

[1797] The generated delivery plan is sent to the driver via the terminal, and delivery activities are carried out based on information updated in real time.

[1798] Recognizing user emotions with an emotion engine

[1799] 1. The device collects the user's voice data.

[1800] Voice data is collected when a user speaks into the terminal.

[1801] 2. The server analyzes the audio data.

[1802] The emotion engine recognizes the user's emotions from the collected voice data, and the analysis results are stored in a database and added to the user's data.

[1803] 3. The device collects the user's facial expression data.

[1804] The system uses the device's built-in camera to collect the user's facial expression data in real time.

[1805] 4. The server analyzes the facial expression data.

[1806] The emotion engine is used to recognize the user's emotions from facial expression data, and the results are also stored in the database.

[1807] 5. The server uses the emotion data to optimize the delivery plan.

[1808] We provide flexible delivery services that take into account the customer experience, including user emotional data.

[1809] Specific examples

[1810] For example, suppose a delivery company needs to plan efficient delivery routes based on real-time traffic information and then combine inventory data and demand forecasts to plan replenishment. In this case, the server collects and analyzes various data to automatically generate optimal delivery routes and replenishment plans. Furthermore, the terminal analyzes the user's voice input and facial expressions using an emotion engine. If the user is feeling stressed, the system can provide flexibility in the delivery plan, thereby improving user satisfaction. In this way, the system of the present invention integrates real-time information, data analysis, and emotion recognition to simultaneously improve logistics efficiency and customer satisfaction.

[1811] The processing flow will be explained below.

[1812] Collection and analysis of real-time traffic information

[1813] Step 1:

[1814] The server periodically calls the traffic information API to obtain real-time data such as road congestion, accident information, construction information, etc. The obtained data is stored in the server's database.

[1815] Step 2:

[1816] The server analyzes the stored traffic data and evaluates the travel time and congestion level of each delivery route, using traffic prediction models and algorithms.

[1817] Step 3:

[1818] Based on the analysis results, the server selects the most efficient route, taking into account delivery delays and fuel efficiency.

[1819] Step 4:

[1820] The device notifies the driver of the optimal route information received from the server, and provides detailed route information to the driver using push notifications and in-app messages.

[1821] Inventory data collection and analysis

[1822] Step 1:

[1823] The server collects inventory data from each warehouse and store's inventory management system via API, including product counts, location information, and replenishment needs.

[1824] Step 2:

[1825] The server collects inventory data, stores it in a database, and updates it in real time. The stored data is then analyzed.

[1826] Step 3:

[1827] The server analyzes inventory data to identify items that are in short supply or need urgent replenishment, and creates a list of high-priority items based on the analysis results.

[1828] Step 4:

[1829] The server automatically generates a delivery plan that reflects the analysis results, and the generated delivery plan includes routes that prioritize urgent products.

[1830] Step 5:

[1831] The terminal notifies the driver of the latest delivery plan, and the driver can check the schedule and product pickup list through the terminal application.

[1832] Generate demand forecasts and delivery plans

[1833] Step 1:

[1834] The server retrieves past sales data, seasonal data, and event data from the database. This data serves as the basis for demand forecasting.

[1835] Step 2:

[1836] The server uses AI algorithms to predict future demand based on the acquired data. The forecasting model is based on past data and takes into account trends and seasonality.

[1837] Step 3:

[1838] The server automatically generates an optimal delivery plan based on the prediction results, calculating which products to deliver to which stores and when, and creating an efficient schedule.

[1839] Step 4:

[1840] The server then combines the generated delivery plan into an optimal route and determines the final delivery route, thereby optimizing time and resources.

[1841] Step 5:

[1842] The device notifies the driver of the optimized delivery plan, and the driver carries out their work based on delivery information updated in real time.

[1843] Recognizing user emotions with an emotion engine

[1844] Step 1:

[1845] The device collects the user's voice data. When the user interacts with the device, the voice is picked up through the microphone.

[1846] Step 2:

[1847] The server analyzes the collected voice data, uses an emotion engine to recognize the user's emotional state from the voice data, and stores the analysis results in a database.

[1848] Step 3:

[1849] The device collects the user's facial expression data, which is acquired in real time via the device's camera.

[1850] Step 4:

[1851] The server analyzes the facial expression data, uses an emotion engine to recognize emotions from the user's facial expressions, and stores the analysis results in a database.

[1852] Step 5:

[1853] The server uses the accumulated emotional data to provide services that take into account the user's emotional state, enabling it to provide feedback to drivers and customize customer service.

[1854] Specific examples

[1855] Let's take the example of a driver checking a delivery plan before setting off on a certain day. First, the server calls a traffic information API to obtain and analyze congestion and accident information and determine the optimal delivery route. Next, the same server collects and analyzes inventory data, identifies products that urgently need replenishment, and reflects this in the delivery plan. Furthermore, the server performs demand forecasting using past sales data and optimizes the delivery plan based on the forecast results. Finally, as the driver checks the optimal route and delivery plan delivered to him via his device before setting off, the emotion engine analyzes the user's emotions and can respond flexibly if the driver is feeling stressed.

[1856] In this way, the system of the present invention can improve the efficiency of delivery operations and the user experience through cooperative operation between the server and terminals over multiple stages.

[1857] Example 2

[1858] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1859] Existing delivery planning systems manage elements such as traffic information, inventory data, and demand forecasts separately, but are unable to integrate these to generate efficient delivery plans. Furthermore, the emotional state of the user is not reflected in the delivery plan, making it difficult to sufficiently improve customer satisfaction.

[1860] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and analyzing traffic information, a means for collecting and analyzing inventory data, a means for performing demand forecasting, a means for recognizing user emotions, a means for automatically generating an optimal delivery plan based on the results of the analysis and prediction, and a means for outputting the delivery plan. This makes it possible to generate an optimal delivery plan by integrating traffic information, inventory data, demand forecasting, and user emotions, thereby improving customer satisfaction.

[1861] "Traffic information" refers to real-time data such as road congestion, accident information, and construction information.

[1862] "Inventory data" refers to data including the quantity, location, and status of products in each warehouse and store.

[1863] "Demand forecasting" is the prediction of future product demand based on past sales data and other relevant information.

[1864] "Emotion recognition" refers to the process of analyzing a user's voice and facial expressions to identify their emotional state.

[1865] A "delivery plan" is an optimal delivery route and schedule generated by integrating traffic information, inventory data, demand forecasts, and user emotion recognition results.

[1866] "API" is an abbreviation for Application Program Interface, a means by which different software applications communicate with each other.

[1867] A "server" is a central computer system that collects, analyzes, processes data, and provides information to client terminals.

[1868] A "terminal" is a device that a user can directly operate and receive information from, and includes smartphones, tablets, and the like.

[1869] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1870] An "algorithm" is a procedure or computational method for solving a particular problem.

[1871] A "machine learning model" is a mathematical model that uses data to learn patterns and make predictions or classifications.

[1872] An "emotion engine" is software for analyzing emotions from data such as voice and facial expressions.

[1873] This invention is a system that automatically generates efficient delivery plans by integrating traffic information, inventory data, demand forecasts, and user emotions. This system collects and analyzes traffic information, manages and analyzes inventory data, forecasts demand, generates and outputs delivery plans, and also has the ability to recognize user emotions.

[1874] Hardware and software used

[1875] Server: A central computer system that collects and analyzes data. An example product is a cloud server (e.g., Amazon Web Services (AWS)).

[1876] Terminal: A device for inputting and outputting data. In this example, we use smartphones and tablet terminals (e.g., iPhones and Android devices).

[1877] Database: A system for storing, managing, and searching data. Relational databases such as PostgreSQL and MySQL are used.

[1878] Software API: An application program interface for retrieving and transmitting data. Examples include the Google Maps API and a REST API for an inventory management system.

[1879] Machine learning model: A model for learning from past data and making demand forecasts. TensorFlow is used.

[1880] Emotion Engine: A software engine for analyzing voice and facial expression data. Powered by IBM Watson.

[1881] Algorithm: A procedure for analyzing data and deriving the required results. Here, an algorithm implemented in Python is used.

[1882] System Implementation Method

[1883] 1. Collection and analysis of real-time traffic information

[1884] The server uses the Google Maps API to collect current traffic information (congestion, accidents, construction, etc.). The collected data is stored in a PostgreSQL database. Then, a Python algorithm calculates the travel time and congestion level for each route.

[1885] 2. Inventory data collection and analysis

[1886] The server retrieves inventory data from each warehouse and store's inventory management system via a REST API. This data is stored in a PostgreSQL database and analyzed by Python scripts to identify items that are running low or need to be replenished.

[1887] 3. Generate demand forecasts and delivery plans

[1888] The server retrieves past sales data, seasonal data, and event information from the database and uses TensorFlow's machine learning model to predict demand. Based on the predicted demand, an optimal delivery plan is generated.

[1889] 4. Flexible delivery response using emotion recognition

[1890] The device collects the user's voice and facial expression data. The voice data is sent to a server via a voice assistant such as Amazon Alexa and analyzed by IBM Watson's emotion engine. Facial expression data is also collected through the device's camera and similarly analyzed by the emotion engine. Based on this emotion data, the server can respond flexibly to delivery requests and improve user satisfaction.

[1891] Specific examples

[1892] For example, when a delivery company integrates traffic information, inventory data, and demand forecasts to plan optimal delivery routes, the server uses the Google Maps API to obtain the latest traffic data and uses a Python algorithm to calculate the optimal route. The server also collects inventory data from each warehouse and store via the API and automatically generates a delivery plan that prioritizes replenishing missing items. Furthermore, the IBM Watson emotion engine analyzes the user's voice input and facial expression data, allowing for flexibility in the delivery plan if the user is feeling stressed.

[1893] Prompt Sentence Examples

[1894] Based on the information below, generate a delivery plan for the next week and suggest improvements taking into account user sentiment data.

[1895] Sales data for the past month

[1896] Real-time traffic information

[1897] User voice and facial expression data

[1898] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1899] Step 1: Collecting traffic information

[1900] The server sends a request to the Google Maps API to get the latest traffic information (congestion, accidents, construction, etc.). It sends the API request as input and receives traffic data in JSON format as output.

[1901] The traffic data acquired by the server is stored in a PostgreSQL database. Specifically, each item of traffic information (e.g., location, congestion level, required time, etc.) is stored in the corresponding database table.

[1902] Step 2: Analyze traffic data

[1903] The server analyzes the stored traffic data using a Python script, reading the traffic data stored in the database as input and calculating the travel time and congestion level for each route as output.

[1904] The server runs an algorithm to select the optimal delivery route, which calculates the shortest and most efficient route by taking into account information such as travel time and congestion.

[1905] Step 3: Collect inventory data

[1906] The server retrieves real-time inventory data from the inventory management systems of each warehouse and store using REST APIs. It sends API requests as input and receives inventory data as output.

[1907] The server stores the inventory data it obtains in a PostgreSQL database. Specifically, it stores information such as the quantity, location, and status of each product in a database table.

[1908] Step 4: Analyze inventory data

[1909] The server parses the stored inventory data using a Python script that reads the inventory data stored in the database as input and identifies items that are missing or need to be replenished as output.

[1910] The server extracts data to generate a delivery plan that prioritizes items that are in short supply. Specifically, it lists items with stock levels below a certain level.

[1911] Step 5: Perform demand forecasting

[1912] The server retrieves historical sales data from the database, along with seasonal and event information. It executes a database query as input and retrieves historical sales data in JSON format as output.

[1913] The server performs demand forecasting using TensorFlow machine learning models. Past data is input to the model, and future demand forecasts are generated as output.

[1914] Step 6: Generate an optimal transportation plan

[1915] The server generates a delivery plan based on predicted demand data, inventory data, and traffic data. The demand forecast results, inventory data, and traffic data are input into the algorithm, and the optimal delivery route and schedule are generated as output.

[1916] The server stores the generated delivery plan in a PostgreSQL database.

[1917] Step 7: Collect user voice data

[1918] The device collects user voice data using a voice assistant such as Amazon Alexa. The device captures the user's speech as input using a microphone and generates voice data as output.

[1919] The device sends the collected voice data to the server. Specifically, the voice data is transferred to the server via API.

[1920] Step 8: Analyzing the audio data

[1921] The server analyzes the voice data using IBM Watson's emotion engine, passing the voice data as input to the emotion engine and generating emotion recognition results as output.

[1922] The server stores the emotion recognition results in a PostgreSQL database.

[1923] Step 9: Collecting user facial expression data

[1924] The device collects the user's facial expression data in real time using a built-in camera. It receives video data from the camera as input and generates facial expression data as output.

[1925] The facial expression data collected by the device is sent to the server. Specifically, the facial expression data is transferred to the server via API.

[1926] Step 10: Analyze facial expression data

[1927] The server analyzes the facial expression data using IBM Watson's emotion engine, passing the facial expression data as input to the emotion engine and generating emotion recognition results as output.

[1928] The server stores the emotion recognition results in a PostgreSQL database.

[1929] Step 11: Optimizing delivery plans with sentiment data

[1930] The server responds flexibly to delivery requests based on the emotional data. The emotional data is passed as input to a delivery plan generation algorithm, and a delivery plan that takes the user's emotional state into consideration is generated as output.

[1931] The server notifies the device of the optimized delivery plan, specifically by transferring the plan to the device via API, and the device displays detailed information to the driver.

[1932] (Application example 2)

[1933] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1934] In conventional delivery operations, delivery plans are mainly based solely on traffic information, inventory data, and demand forecasts, and no flexible response is made that takes user emotions into consideration. As a result, delivery delays and out-of-stock items can cause stress for users, reducing customer satisfaction. The present invention aims to automatically generate more efficient and flexible delivery plans and improve customer satisfaction by combining real-time traffic information, inventory data, demand forecasts, and user emotion recognition.

[1935] 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.

[1936] In this invention, the server includes means for collecting and analyzing traffic information, means for collecting and analyzing inventory data, means for performing demand forecasting, means for automatically generating an optimal delivery plan based on the results of the analysis and forecasting, means for recognizing user emotions, means for optimizing the delivery plan based on emotion data, and means for outputting the delivery plan. This enables not only efficient delivery plans based on real-time information but also flexible delivery responses that take user emotions into consideration.

[1937] "Traffic information" refers to data on traffic flow, such as road congestion, accident information, and construction information, collected in real time.

[1938] "Inventory data" is information regarding the quantity and status of products in each warehouse and store.

[1939] "Demand forecasting" is the process of predicting future demand based on past sales data, seasonal data, and event information.

[1940] "Delivery planning" is a plan that automatically generates optimal delivery routes and schedules based on traffic information, inventory data, and demand forecasts.

[1941] "User's emotions" refers to the user's psychological state as recognized from voice, facial expressions, etc.

[1942] "Emotion data" is information about a user's emotions collected by means of voice recognition and facial expression recognition.

[1943] "Flexible delivery response" refers to a dynamic response that modifies conventional fixed delivery plans based on user emotional data to reduce user stress and dissatisfaction.

[1944] The present invention combines a system that automatically generates efficient delivery plans by integrating real-time traffic information, inventory data, and demand forecasts, with an emotion engine that recognizes user emotions. The following describes an embodiment of the present invention in detail.

[1945] Hardware and Software Configuration

[1946] 1. Server:

[1947] The server is set up to collect and analyze traffic information, inventory data, demand forecast data, and emotion data. Specifically, it uses the following APIs and libraries:

[1948] Traffic information: Traffic information APIs such as Google Maps API

[1949] Inventory data: API to retrieve data from inventory management systems at each warehouse and store

[1950] Demand forecasting: AI algorithms (e.g., Scikit-Learn) to forecast demand based on historical sales data, seasonal data, and event information.

[1951] Emotion data: Speech recognition libraries (e.g., SpeechRecognition) and facial expression recognition libraries (e.g., EmotionRecognizer)

[1952] 2. Terminal:

[1953] The terminals are smartphones used by delivery personnel or in-vehicle head-mounted displays, and are responsible for receiving and displaying optimal delivery routes, inventory replenishment plans, demand forecast results, and optimized delivery plans sent from the server. The terminals also have the ability to collect voice input and facial expression data from users.

[1954] 3. User:

[1955] When the user speaks to the device, voice data is collected, and facial expression data is also captured through the built-in camera. This data is sent to the server, where the emotion engine analyzes the user's emotions.

[1956] Process flow example

[1957] 1. Real-time traffic information collection and analysis:

[1958] The server uses a traffic information API to collect real-time traffic information. The traffic data is analyzed and the optimal route is selected. The results are sent to the terminal and notified to the delivery person as the optimal route.

[1959] 2. Inventory data collection and analysis:

[1960] The server collects and analyzes inventory data from the inventory management systems of each warehouse and store, identifying items that are low in stock and incorporating this information into delivery plans.

[1961] 3. Generate demand forecasts and delivery plans:

[1962] The server collects past sales data, seasonal data, and event information, and uses AI algorithms to predict demand. Based on the results, optimal delivery routes and replenishment plans are generated.

[1963] 4. Emotion engine recognizes user emotions:

[1964] The device collects the user's voice and facial expression data and sends it to the server. The emotion engine analyzes this data and recognizes the user's emotions. Based on the results, the delivery plan is optimized.

[1965] Specific examples

[1966] For example, if a food delivery company were to adopt this system, delivery personnel would receive real-time information on optimal routes on their smartphones and confirm plans to prioritize replenishment of low-stock items. Also, if a user expresses an emotion that "the product is delayed," that information would be reflected immediately and a rapid response would be made.

[1967] Prompt Sentence Examples

[1968] An example prompt for running a system using a generative AI model is as follows:

[1969] "Create a food delivery plan using user emotion recognition. Use the following data to generate optimal delivery routes and inventory replenishment plans, and adapt based on user emotions:

[1970] Real-time traffic information (API: Google Maps API)

[1971] Inventory data (API: Inventory Management API)

[1972] Demand forecast data (past sales information)

[1973] User emotion data (voice and facial expression analysis)

[1974] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1975] Step 1:

[1976] The server collects traffic information.

[1977] Input: Real-time traffic data from traffic information API

[1978] Specific operation: The server calls the traffic information API and obtains real-time traffic data such as road congestion status, accident information, and construction information.

[1979] Output: Collected traffic data (e.g., congestion level, travel time)

[1980] Step 2:

[1981] The server analyzes the traffic data.

[1982] Input: Collected traffic data

[1983] How it works: The server uses an algorithm to analyze the collected traffic data, calculate the travel time and congestion level for each route, and then select the optimal delivery route.

[1984] Output: Optimal delivery route information

[1985] Step 3:

[1986] A server collects inventory data.

[1987] Input: Inventory data from inventory management systems for each warehouse and store

[1988] Specific operation: The server calls the inventory management API and obtains inventory data for each warehouse and store in real time.

[1989] Output: Collected inventory data (e.g., number of items in stock)

[1990] Step 4:

[1991] The server parses the inventory data.

[1992] Input: Collected inventory data

[1993] What happens: The server analyzes inventory data to identify items that are low or need to be replenished.

[1994] Output: Missing items list

[1995] Step 5:

[1996] The server performs demand forecasting.

[1997] Input: Historical sales data, seasonal data, event information

[1998] Specific operation: The server uses an AI algorithm (e.g., Scikit-Learn) to predict future demand based on past sales data, seasonal data, and event information.

[1999] Output: Demand forecast curve

[2000] Step 6:

[2001] The server generates an optimal delivery plan based on the demand forecast results.

[2002] Input: Optimal delivery route information, shortage product list, demand forecast curve

[2003] Specific operation: The server integrates these input data and automatically generates efficient delivery routes and replenishment plans.

[2004] Output: Delivery plan

[2005] Step 7:

[2006] The terminal notifies the driver of the delivery plan.

[2007] Input: Delivery plan

[2008] Specific operation: Based on the delivery plan information received by the terminal from the server, the driver is shown a detailed schedule and a product pick-up list.

[2009] Output: The trip plan displayed on the driver's device

[2010] Step 8:

[2011] The terminal collects the user's voice data.

[2012] Input: User's voice

[2013] Specific operation: When the user speaks into the device, voice data is collected by the device.

[2014] Output: Collected audio data

[2015] Step 9:

[2016] The server analyzes the audio data.

[2017] Input: Collected audio data

[2018] Specific operation: The server uses a speech recognition library (e.g., SpeechRecognition) to analyze the collected voice data and recognize the user's emotions.

[2019] Output: Recognized emotion data

[2020] Step 10:

[2021] The terminal collects facial expression data of the user.

[2022] Input: User's facial expression

[2023] Specific operation: Using the device's built-in camera, the user's facial expression data is collected in real time.

[2024] Output: Collected facial expression data

[2025] Step 11:

[2026] The server analyzes the facial expression data.

[2027] Input: Collected facial expression data

[2028] Specific operation: The server uses a facial expression recognition library (e.g., EmotionRecognizer) to analyze facial expression data and recognize the user's emotions.

[2029] Output: Recognized emotion data

[2030] Step 12:

[2031] The server uses emotion data to optimize delivery plans.

[2032] Input: Recognized emotion data, existing delivery plan

[2033] Specific operation: Based on the user's emotional data, the server generates an optimized delivery plan that reduces the user's stress and dissatisfaction by adding flexibility to the conventional delivery plan.

[2034] Output: Optimized delivery plan

[2035] Step 13:

[2036] The device notifies the driver of an optimized delivery plan.

[2037] Input: Optimized delivery plan

[2038] Specific operation: The device notifies the driver of the optimized delivery plan received from the server and displays detailed route information and schedule changes.

[2039] Output: Optimized trip plan displayed on the driver's device

[2040] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2041] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2042] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2043] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2044] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2045] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2046] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2047] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2048] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2049] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2050] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2051] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2052] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2053] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2054] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2055] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2056] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2057] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2058] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2059] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2060] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2061] The following is further disclosed regarding the above embodiment.

[2062] (Claim 1)

[2063] a means for collecting and analyzing traffic information;

[2064] a means of collecting and analyzing inventory data;

[2065] a means for performing a demand forecast;

[2066] A means for automatically generating an optimal delivery plan based on the analysis and prediction results;

[2067] A means for outputting a delivery plan;

[2068] A system including:

[2069] (Claim 2)

[2070] 2. The system of claim 1, wherein the means for obtaining traffic information utilizes an API that collects traffic data in real time.

[2071] (Claim 3)

[2072] The system of claim 1, wherein the means for collecting inventory data utilizes an API that obtains data from the inventory management systems of each warehouse and store.

[2073] "Example 1"

[2074] (Claim 1)

[2075] a means for collecting and analyzing traffic information;

[2076] a means of collecting and analyzing inventory data;

[2077] a means for performing a demand forecast;

[2078] A means for automatically generating an optimal delivery plan based on the analysis and prediction results;

[2079] a means of collecting traffic data in real time;

[2080] A means for calculating optimal delivery routes using traffic data;

[2081] A means of obtaining data from inventory management systems at each warehouse and store;

[2082] A means to identify shortages in inventory data and reflect them in delivery plans;

[2083] A means of collecting past sales data and making demand forecasts;

[2084] a means for notifying a terminal of the generated delivery plan;

[2085] A system including:

[2086] (Claim 2)

[2087] 2. The system of claim 1, wherein the means for collecting traffic data in real time utilizes an API for obtaining traffic information.

[2088] (Claim 3)

[2089] 2. The system of claim 1, wherein the means for collecting inventory data utilizes an API for obtaining data from the inventory management systems of each warehouse and store.

[2090] "Application Example 1"

[2091] (Claim 1)

[2092] a means for collecting and analyzing traffic information;

[2093] a means of collecting and analyzing inventory data;

[2094] a means for performing a demand forecast;

[2095] A means for automatically generating an optimal delivery plan based on the analysis and prediction results;

[2096] A means for outputting a delivery plan;

[2097] A means of providing real-time updates on delivery;

[2098] means for transmitting notification information to a terminal;

[2099] A system including:

[2100] (Claim 2)

[2101] 2. The system of claim 1, wherein the means for obtaining traffic information utilizes an API that collects traffic data in real time.

[2102] (Claim 3)

[2103] The system of claim 1, wherein the means for collecting inventory data utilizes an API that obtains data from the inventory management systems of each distribution center and store.

[2104] "Example 2: Combining Emotion Engines"

[2105] (Claim 1)

[2106] a means for collecting and analyzing traffic information;

[2107] a means of collecting and analyzing inventory data;

[2108] a means for performing a demand forecast;

[2109] means for recognizing a user's emotion;

[2110] A means for automatically generating an optimal delivery plan based on the analysis and prediction results;

[2111] A means for outputting a delivery plan;

[2112] A system including:

[2113] (Claim 2)

[2114] 2. The system of claim 1, wherein the means for obtaining traffic information utilizes an API that collects traffic data in real time.

[2115] (Claim 3)

[2116] The system of claim 1, wherein the means for collecting inventory data utilizes an API that obtains data from the inventory management systems of each warehouse and store.

[2117] "Application example 2 when combining emotion engines"

[2118] (Claim 1)

[2119] a means for collecting and analyzing traffic information;

[2120] a means of collecting and analyzing inventory data;

[2121] a means for performing a demand forecast;

[2122] A means for automatically generating an optimal delivery plan based on the analysis and prediction results;

[2123] means for recognizing a user's emotion;

[2124] A means for optimizing delivery plans based on sentiment data;

[2125] A means for outputting a delivery plan;

[2126] A system including:

[2127] (Claim 2)

[2128] 2. The system of claim 1, wherein the means for obtaining traffic information utilizes an API that collects traffic data in real time.

[2129] (Claim 3)

[2130] The system of claim 1, wherein the means for collecting inventory data utilizes an API that obtains data from the inventory management systems of each warehouse and store.

[2131] (Claim 4)

[2132] 2. The system of claim 1, wherein the means for recognizing the user's emotions uses voice recognition and facial expression recognition methods.

[2133] (Claim 5)

[2134] 2. The system according to claim 1, wherein the means for optimizing the delivery plan based on emotion data is configured to provide flexible delivery responses according to the user's emotional state. [Explanation of symbols]

[2135] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting and analyzing traffic information; a means of collecting and analyzing inventory data; a means for performing a demand forecast; A means for automatically generating an optimal delivery plan based on the analysis and prediction results; A means for outputting a delivery plan; A system including:

2. 2. The system of claim 1, wherein the means for acquiring traffic information utilizes an API that collects traffic data in real time.

3. 2. The system according to claim 1, wherein the means for collecting inventory data utilizes an API that acquires data from inventory management systems of each warehouse and store.

Images