system

Abstract

We provide the system. [Solution] Means for collecting past delivery data, customer schedule information, regional characteristics information, and digital activity history, A means for anonymizing the aforementioned collected data, A method for training a generative AI model based on anonymized data to predict the times when customers are most likely to be at home, A means of generating and delivering an optimal delivery schedule to a terminal based on the predicted time when the customer will be at home, A means for receiving feedback on delivery results and adding it to a database to improve the accuracy of the generated AI model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present invention focuses on the problem that the high rate of redelivery in the home delivery service is an issue. In particular, redelivery due to the customer being absent is a significant burden on the delivery operator and a factor hindering efficient delivery. Also, the increase in redelivery increases the burden on drivers and makes it difficult to solve the labor shortage. Furthermore, the wasteful use of vehicles due to redelivery also leads to an increase in environmental load. Against this background, how to predict the time periods when the customer is at home and propose an optimal delivery schedule has become an important issue.

Means for Solving the Problems

[0005] This invention provides a system that predicts the times when customers are most likely to be at home by collecting and anonymizing past delivery data, customer schedule information, regional characteristics information, and digital activity history, and then learning from this data using a generative AI model. Based on the predicted times when customers are at home, the system generates an optimal delivery schedule and distributes it to the delivery company's terminal. Furthermore, by receiving feedback on delivery results, the prediction accuracy of the generative AI model can be improved, and delivery efficiency can be continuously enhanced. This makes it possible to reduce redeliveries and improve satisfaction for both delivery companies and customers.

[0006] "Past delivery data" refers to the history of deliveries made to date, including details such as the delivery date, time, and outcome.

[0007] "Customer schedule information" refers to data that shows the appointments set by the customer themselves, including calendar appointments and pre-registered absence information.

[0008] "Regional characteristics information" refers to data about the attributes and features of a specific region, including information such as local lifestyles, event information, and traffic conditions.

[0009] "Digital activity history" refers to a record of activities performed by a customer using their device, and is data that shows their online behavior history and usage.

[0010] A "generative AI model" is an artificial intelligence model that learns from large amounts of data, identifies patterns from new data, and makes predictions.

[0011] "Anonymization" is the process of removing or transforming identifiable information from data so that individuals cannot be identified.

[0012] A "delivery schedule" is a detailed plan outlining the delivery schedule based on time and order, serving as a plan for efficient delivery.

[0013] "Feedback" refers to the results and evaluation information obtained upon completion of a delivery, and this data is used to improve future delivery plans.

[0014] A "terminal" is a digital device carried by delivery personnel, used for receiving delivery schedules and sending status reports. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of a data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that utilizes AI technology to improve the efficiency of delivery services. The system is designed to reduce the burden of redeliveries for delivery companies and improve customer convenience.

[0037] Data collection and anonymization

[0038] First, the server retrieves past delivery data, including date, time, delivery destination, and delivery result. Next, the server collects schedule information provided by the customer, which is entered by the user through partner apps and online platforms. In addition, the server collects local characteristic information from public institutions and local services, and digital activity history is collected with permission. All data is anonymized by the server to protect privacy.

[0039] Performing predictions using generative AI

[0040] The collected data is trained on commercially available or custom-built generative AI models within the server. The server uses these models to accurately predict when customers are likely to be at home. The models analyze the day of the week, time of day, and past customer behavior patterns to calculate the optimal delivery time for each customer.

[0041] Generating a delivery schedule

[0042] Next, the server generates an optimized delivery schedule for the driver based on the predicted time spent at home, efficiently combining multiple delivery destinations. The generated schedule is sent to the terminal, which the driver can view in real time.

[0043] Optimization through feedback

[0044] Once a delivery is complete, the terminal feeds the delivery results back to the server. This information includes the success rate of the delivery and the difference between the predicted time the recipient was home and the actual time of delivery. This allows the server to continuously improve the accuracy of its model and optimize future predictions.

[0045] Specific example

[0046] For example, if past data reveals that customer A, who is busy on weekdays, tends to be home on Saturday afternoons, the server will use this information to select Saturday afternoons as the recommended delivery time. Drivers can receive this information via their terminals and plan their deliveries accordingly, reducing the risk of redeliveries and increasing efficiency.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from various data sources. Since each piece of data may contain personal information, it is immediately anonymized after acquisition and converted into a form that does not identify individuals.

[0050] Step 2:

[0051] The server trains a generative AI model using anonymized data. This model extracts patterns from the input data and is used to learn the times of day when customers are most likely to be at home. This learning process incorporates algorithms that take into account schedule characteristics and regional trends.

[0052] Step 3:

[0053] The server uses a trained model to predict the optimal delivery time for each customer. This prediction reflects information tailored to each customer's location and individual needs. It also generates an overall schedule to create efficient delivery routes for drivers.

[0054] Step 4:

[0055] The terminal receives the optimal delivery schedule sent from the server and notifies the driver. Based on this information, the driver prepares to execute the daily delivery plan and adjusts their actions to complete deliveries by the specified time.

[0056] Step 5:

[0057] The user (driver) performs the delivery and sends the results to the server via their terminal upon completion. This result includes details such as whether the delivery was successful or if the recipient was absent.

[0058] Step 6:

[0059] The server receives and stores feedback data after delivery. This feedback is used to update and improve the model in the next update, contributing to increased prediction accuracy. This ensures continuously efficient delivery operations.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In modern delivery services, the increase in redeliveries and the decline in delivery efficiency due to customer absence are significant problems. This increases costs for delivery companies and diminishes customer convenience. There is a need to improve this situation, enhance delivery efficiency, and increase customer satisfaction.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for collecting past delivery information, user schedule information, regional characteristic information, and communication activity history; means for anonymizing the collected information; and means for training an inference AI model based on the anonymized information to predict times when the user is most likely to be at home. This makes it possible to predict the time periods when the user is most likely to be at home and to create an optimal delivery plan based on those times.

[0065] "Past delivery information" refers to records of past deliveries, including the date and time, recipient's address, and delivery status.

[0066] "User schedule information" refers to data that includes schedules for times and days specified by the user, and suggests the possibility of them being at home or away.

[0067] "Regional characteristic information" refers to data that shows the geographical, social, and economic characteristics of a region, including road conditions, traffic patterns, and people's behavioral characteristics.

[0068] "Communication activity history" refers to information about online behavior and communication obtained with the user's permission, including app usage and visit history.

[0069] "Anonymization" is a process that removes elements that can identify an individual from collected information in order to protect individual privacy.

[0070] An "inference AI model" is an artificial intelligence algorithm or computational model built to analyze data and make specific predictions.

[0071] A "delivery plan" is a delivery schedule created based on predicted times when recipients will be at home, in order to improve the efficiency of delivery operations.

[0072] "Data storage means" refers to databases and recording media used to store collected data and utilize it for future predictions and analysis.

[0073] This invention utilizes a server-centered system to improve the efficiency of delivery services. A specific embodiment of this system is described below.

[0074] The server first collects past delivery information from delivery companies. This information includes delivery date and time, recipient's address, and delivery status. The server also collects schedule information provided by users from mobile devices, etc. For example, it obtains information such as "I am home after 6 PM from Monday to Friday." Furthermore, to obtain regional characteristic information, it collects data from public institutions and communication activity history authorized by users.

[0075] After acquiring this information, the server anonymizes it to prevent the identification of individuals. The anonymized data is then used to train a generative AI model. This generative AI model uses commercially available software and proprietary algorithms to make predictions that take into account the day of the week, time of day, and regional characteristics.

[0076] Based on this prediction, the server creates the optimal delivery plan. For example, if the generating AI model predicts that "customer A is likely to be home on Saturday afternoon," the server will schedule the delivery for Saturday afternoon. The created delivery plan is sent to the driver's terminal and can be viewed in real time.

[0077] When a delivery is completed, the terminal feeds the results back to the server. This includes information such as "delivery successful" or "delivery missed." The server uses this feedback information to improve the generated AI model and adds it to a database to make future predictions more accurate.

[0078] As a concrete example, the prompt, "Analyze customer A's weekday and weekend home patterns and predict the optimal delivery time. Consider past delivery data and schedule information," can be used to help create efficient delivery schedules.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects past delivery information, user schedule information, regional characteristics information, and communication activity history. The server obtains this information from a database or through direct input from users. Specifically, data collection is done using APIs, and users input their schedules via an app on their mobile devices. This input data includes delivery date and time, address, past delivery results, and scheduled time spent at home, and this is stored as input in the server's data storage.

[0082] Step 2:

[0083] The server anonymizes the collected information. This involves encrypting or ID-ifying personally identifiable data and replacing it with a unique identifier. The input is the unanonymized data collected in step 1, and the output is anonymized data with privacy protection. Specifically, this involves deleting personal information from the database and masking identifying information.

[0084] Step 3:

[0085] The server trains a generative AI model using anonymized data. The anonymized data obtained in step 2 is used as input. The server uses commercially available or custom-developed AI software to analyze user home patterns from data such as day of the week, time, and regional characteristics. The output is a prediction of the time periods when each user is most likely to be at home. Specifically, the AI ​​applies machine learning algorithms to identify patterns based on the user's past behavior history.

[0086] Step 4:

[0087] The server generates an optimal delivery plan based on the output of the AI ​​model. This plan is optimized to schedule deliveries at times when users are most likely to be at home. The input is the predicted time spent at home obtained in step 3. The output is the detailed delivery route and schedule to be given to the driver. The server calculates the shortest path based on the algorithm and determines an efficient delivery order.

[0088] Step 5:

[0089] The terminal receives the delivery plan sent from the server and presents it to the driver in real time. The driver can check the next delivery destination and route information through this terminal. The input is the delivery plan data generated from the server in step 4, and the output is a visual map and schedule displayed on the terminal screen. The driver uses this to carry out deliveries.

[0090] Step 6:

[0091] After delivery, the terminal reports the delivery results to the server. The input is delivery result data entered by the driver, including status such as success or absence. The server receives this feedback data, adds it to the database, and uses it to continuously improve the generated AI model. The output is the next prediction with improved model accuracy. This further improves the accuracy of the next delivery plan.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In modern delivery services, efficient delivery is essential, but the increase in redeliveries due to attempts to deliver during times when customers are absent is a significant challenge that leads to wasted time and resources. Furthermore, to optimize deliveries to multiple customers, it is essential to analyze various data in real time and calculate the optimal route and time. In addition, a system for continuously improving delivery accuracy is required.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for collecting past delivery information, user activity schedule information, regional characteristics information, and electronic activity history; means for anonymizing the collected information; and means for training a generation AI model based on the anonymized information to predict the time when the user is most likely to arrive. This makes it possible to formulate an efficient delivery plan and reduce the risk of redelivery. Furthermore, the system can receive feedback on delivery results and continuously improve delivery accuracy, thereby enhancing the overall service quality.

[0097] "Delivery information" refers to data related to past deliveries, including information such as the date and time, delivery destination, and delivery result.

[0098] "User activity plan information" refers to the user's plans and schedules for using the service, and is provided through partner apps and online platforms.

[0099] "Regional characteristic information" refers to information about the unique characteristics of a region, collected from public institutions and local services, and includes things like traffic conditions and weather conditions.

[0100] "Electronic activity history" refers to the history of activities performed by users in the digital environment, and is information that is useful for optimizing services.

[0101] "Anonymization" is a processing technique that removes personally identifiable information to protect privacy.

[0102] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes specific predictions or classifications.

[0103] A "delivery plan" is a delivery schedule based on the predicted arrival time of the user, and includes efficient delivery routes.

[0104] "Information equipment" refers to electronic devices that allow drivers and users to receive information in real time.

[0105] A "recording medium" is a storage device used to store data and for system learning and improvement.

[0106] This system requires the application of multiple hardware and software components to enable the efficient planning and execution of delivery schedules.

[0107] First, the server collects past delivery information, user activity schedules, regional characteristics, and electronic activity history. This information is anonymized after collection to protect privacy. For this purpose, the server uses a data anonymization library (e.g., PySyft).

[0108] Based on anonymized information, the server trains a generative AI model to predict the most likely times for users to arrive. This process utilizes machine learning libraries such as TENSORFLOW® and PyTorch. The model performs predictive calculations that take into account time, day of the week, and regional characteristics.

[0109] Next, the server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. This information device is a smartphone or other electronic device that receives the optimized route and delivery schedule in real time. This process reduces the risk of redelivery and increases delivery efficiency.

[0110] After delivery is complete, the terminal feeds the delivery results back to the server. Based on this feedback, the server adds data to the storage medium and improves the accuracy of the generated AI model. This cycle promotes continuous improvement of service quality.

[0111] For example, suppose a user enters their schedule into a partner app. Based on this information and past data, the server predicts with high accuracy when the user will be at home and delivers this information to the driver in real time. The system may use prompts such as: "Analyze the user's order history for the past 6 months and predict the optimal delivery time."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server collects delivery information, user activity schedule information, regional characteristics information, and electronic activity history. Inputs include a historical delivery database, user schedule input, and regional public data sources. The output is an initial, unanonymized dataset. This dataset is then anonymized through the following process.

[0115] Step 2:

[0116] The server anonymizes the collected information. In this process, the server uses a data anonymization library (e.g., PySyft). The unanonymized dataset obtained in step 1 is used as input, and a privacy-protected anonymized dataset is generated as output. The anonymized data is then provided to the generative AI model as training data.

[0117] Step 3:

[0118] The server trains a generative AI model based on anonymized data. The anonymized dataset obtained in step 2 is used as input. TensorFlow or PyTorch is used for the generative AI model, and a prediction algorithm that takes into account time, day of the week, and regional characteristics predicts the arrival time of users. The output is the optimal predicted arrival time for each user, which is useful for integrated delivery planning.

[0119] Step 4:

[0120] The server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. The input is the predicted arrival time of the user obtained in step 3. This information is transmitted to information devices such as smartphones and tablets via a real-time delivery algorithm for the device. The output is an optimized delivery route and schedule for each driver.

[0121] Step 5:

[0122] Once a delivery is complete, the terminal feeds the delivery results back to the server. The input used is delivery performance information from the terminal (success, failure, time delay, etc.). The server saves this feedback to a storage medium and uses it as data for the next training cycle. The output is an updated dataset for improving model accuracy.

[0123] Through these steps, servers, terminals, and users can work together to improve the accuracy and efficiency of deliveries.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention is a system that combines AI technology and emotion recognition capabilities with the aim of improving delivery efficiency and customer satisfaction in home delivery services. This system not only uses data collection and generation AI models for prediction, but also utilizes an emotion engine to analyze user emotions and optimize delivery schedules based on those emotions.

[0126] Data collection and anonymization

[0127] First, the server collects past delivery data, customer schedule information, regional characteristics information, and digital activity history. This data is anonymized and cannot be used to identify individuals.

[0128] Utilizing the Emotion Engine

[0129] The server inputs the collected digital activity history into an emotion engine to analyze the user's emotional state. This emotion engine analyzes social media posts, messaging app interactions, and other data to detect changes in emotions.

[0130] Prediction using generative AI models

[0131] Taking sentiment analysis into account, the server uses a generative AI model to predict when users are most likely to be at home. This prediction is integrated with the user's schedule and local characteristics information to create an optimal delivery schedule.

[0132] Generating and adjusting delivery schedules

[0133] The server generates a delivery schedule that reflects the emotional state of the customer and delivers it to the terminal. The driver then carries out deliveries based on this optimized schedule.

[0134] example

[0135] For example, if a user is feeling stressed online, the emotion engine detects this state and, out of consideration, predicts a time when they are more likely to relax. Based on this, the server sets the delivery time to suit the user's comfort level and notifies the driver via the terminal.

[0136] Feedback and continuous improvement

[0137] After delivery is complete, the device sends the results and feedback to the server. This feedback data is used to further improve the accuracy of the generative AI model and emotion engine.

[0138] In this way, by introducing an emotion engine, this system aims to improve delivery efficiency and customer satisfaction by providing a more detailed delivery service that takes into account the user's emotional state.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from multiple data sources. During this collection phase, the data is immediately anonymized to protect privacy and make it impossible to identify individuals.

[0142] Step 2:

[0143] The server inputs anonymized digital activity history into the emotion engine to analyze the user's emotional state. The emotion engine has the ability to identify emotions such as positive, negative, and neutral from the user's text data and online activity patterns.

[0144] Step 3:

[0145] The server integrates the results of the emotion engine with other collected data and includes them in the generative AI model's dataset. The generative AI model then learns from this integrated data to predict the times when each customer is most likely to be at home. This prediction takes into account the user's emotional state, in addition to time of day, day of the week, regional characteristics, and schedule information.

[0146] Step 4:

[0147] The server creates an optimal delivery schedule based on predictions of when customers will be home, calculated by a generative AI model. This schedule is optimized by referencing data from multiple customers and is designed to allow drivers to work at their most efficient pace.

[0148] Step 5:

[0149] The terminal receives the optimal delivery schedule sent from the server and notifies the driver in real time. The driver plans the route for deliveries based on this schedule and travels according to the instructions.

[0150] Step 6:

[0151] The user (driver) performs the scheduled delivery and reports feedback on the delivery completion and results to the server via a terminal. This feedback includes information such as delivery success, details of missed deliveries, and user reactions.

[0152] Step 7:

[0153] The server receives feedback from drivers and uses it for subsequent data analysis. Based on this feedback, the accuracy of the generative AI model and emotion engine is further enhanced, improving the accuracy of future delivery plans.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In home delivery services, achieving both improved delivery efficiency and customer satisfaction simultaneously is not easy. Accurately predicting customer availability and creating efficient delivery schedules is necessary, but conventional methods have struggled to make highly accurate predictions that take emotional states into account. This invention aims to solve this problem and enable more flexible and customer-centric delivery.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for aggregating past delivery history, customer schedule information, regional characteristic information, and electronic activity records; means for modifying the aggregated information so that personal information cannot be identified; means for predicting times when the user is most likely to be at home using a generative AI model based on the modified information; means for adjusting the delivery time and transmitting an optimized delivery plan to the terminal using emotional intelligence that analyzes the user's emotional state; and means for adding the results received after the delivery to the information storage device in order to improve the accuracy of the generative AI model and emotional intelligence. This significantly improves delivery efficiency and enables the provision of flexible delivery services that take customer comfort into consideration.

[0159] "Past delivery history" refers to records of deliveries made in the past, including data such as the date, time, location, and destination.

[0160] "Customer schedule information" refers to information including schedules and activity plans that customers have registered in advance.

[0161] "Regional characteristic information" refers to information that shows geographical, demographic, and traffic conditions specific to the delivery area.

[0162] "Electronic activity records" refer to data that shows a customer's actions and communication history on their digital devices.

[0163] "Modifying data so that personal information cannot be identified" refers to technical measures that anonymize data by removing or encrypting personally identifiable elements.

[0164] A "generative AI model" is a type of machine learning algorithm created to perform specific tasks using artificial intelligence techniques.

[0165] "The time when users are most likely to be at home" refers to the time period predicted by the AI ​​model as having the highest probability of customers being at home.

[0166] "Emotional intelligence" refers to the technology or function of mechanically analyzing a person's emotional state and using that analysis to select appropriate judgments and actions.

[0167] An "optimized delivery plan" is a schedule designed to be executed effectively and efficiently, taking into account delivery efficiency and customer preferences to the fullest extent.

[0168] An "information storage device" refers to a physical or virtual facility or system for recording and storing data.

[0169] This invention is a system aimed at improving efficiency and customer satisfaction in delivery services. At the heart of the system are a generative AI model and emotional intelligence, which operate on a server.

[0170] The server first aggregates past delivery history, customer schedule information, regional characteristics, and electronic activity records. APIs and database connection technologies are used for data collection, and encryption algorithms are applied to securely anonymize this data. Next, a generative AI model is used based on the collected data to predict the times when customers are most likely to be at home. Here, a representative machine learning algorithm is used, and the AI ​​model is instructed with prompts such as, "Predict the optimal delivery time while considering the user's emotional state."

[0171] Furthermore, the emotional intelligence analyzes the user's electronic activity log and determines their emotional state based on social media posts and messaging app content. This analysis utilizes an API equipped with natural language processing technology. The server comprehensively considers the predicted time spent at home and the emotional state to generate an optimal delivery schedule and send it to the device.

[0172] The terminal notifies the driver of the delivery schedule received from the server. Specifically, an application running on the mobile device is used to show the driver the optimal delivery route and time.

[0173] For example, if a user's online activity reveals signs of stress, the server analyzes this information and schedules delivery for a time when the user can relax. In this way, the implementation of this invention makes it possible to provide a detailed service that takes into account the individual user's state.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server collects past delivery history, customer schedule information, regional characteristics information, and electronic activity records. It retrieves information from various APIs and databases as input and integrates it as digital data. As output, the collected data is stored after anonymization algorithms have been applied.

[0177] Step 2:

[0178] The server trains a generative AI model using anonymized data. It receives a prompt message, "Predict the optimal delivery time while considering the user's emotional state," and the AI ​​model predicts the time slots when the user is most likely to be at home. As a result, predicted time slots are extracted.

[0179] Step 3:

[0180] The server provides electronic activity logs to emotional intelligence to analyze the user's emotional state. As input, it analyzes social media posts and messaging app history, and uses natural language processing techniques to detect changes in emotion. As output, it estimates the user's current emotional state.

[0181] Step 4:

[0182] The server integrates predicted time spent at home and emotional state to generate an optimal delivery schedule. The input uses the data obtained in steps 2 and 3. Specifically, the generated schedule is optimized by a time management algorithm. The output is a specific delivery schedule for the driver.

[0183] Step 5:

[0184] The terminal receives an optimized delivery schedule sent from the server and notifies the driver. It receives the generated schedule data as input and provides visual instructions on the mobile device. As output, the driver receives real-time route and time information.

[0185] Step 6:

[0186] The terminal sends feedback to the server after delivery is complete. The input includes delivery results and driver comments, which are added to the server's database. As output, the feedback is used to further improve the accuracy of generative AI models and emotional intelligence.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0189] Current delivery services create delivery schedules that only consider the user's location, without taking into account the user's emotional state. This leads to problems such as deliveries occurring under stressful circumstances and service that doesn't suit the user's feelings. Furthermore, achieving both efficient delivery routes and emotionally responsive service simultaneously is difficult, posing a challenge to improving customer satisfaction.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for acquiring past delivery-related information, user schedule information, regional characteristics information, and digital behavior history; means for training a generative artificial intelligence model based on anonymized information to estimate the times when the user is most likely to be present; and means for integrating an emotion recognition function for analyzing the user's emotional state. This makes it possible to provide an optimal delivery schedule and service that takes into account the user's location and emotional state.

[0192] "Past delivery-related information" refers to all data related to past deliveries, including information such as delivery date and time, delivery destination, and positive feedback.

[0193] "User schedule information" refers to information about activities and schedules that the user has set or anticipates, including, for example, appointments and public holiday information in calendar applications.

[0194] "Regional characteristics information" refers to data about the characteristics of a specific region, including elements unique to that region, such as climate conditions, traffic conditions, and local events.

[0195] "Digital behavioral history" refers to data based on a user's online behavior, including, for example, statements made on social media and internet usage history.

[0196] A "generative artificial intelligence model" is a statistical model that uses AI technology to learn from collected data and make specific predictions or classifications.

[0197] "User location probability" is a concept that predicts the probability that a user is in a certain location during a specific time period.

[0198] "Emotion recognition functionality" refers to technology that analyzes a user's digital behavior history to identify their emotions at any given time.

[0199] An "optimal delivery schedule" is a delivery plan designed to maximize delivery efficiency and customer satisfaction, taking into account the user's location, emotions, and regional characteristics.

[0200] An "information terminal" refers to a device used to receive delivery schedules and other information, such as a smartphone or tablet.

[0201] An "information recording device" is a system or device for storing data over a long period of time. Examples include cloud-based data storage services.

[0202] The server acquires past delivery-related information, user schedule information, regional characteristics information, and digital behavior history. This information is collected through applications on the user's smartphone or tablet and anonymized to protect privacy. In this process, the aforementioned information is analyzed on a keyword basis and converted into a format that does not identify individual users. The anonymized data is securely stored in an information recording device, for example, on a cloud service. This stored information is used as foundational data to train a generative artificial intelligence model. This AI model is used to predict the user's location and emotional state, with its emotion recognition function analyzing statements from social media and messaging apps.

[0203] The generative artificial intelligence model utilizes technologies such as OpenAI® to determine when users are most relaxed, taking into account time, regional characteristics, and effective emotional indicators. Based on these predictions, the server generates an optimal delivery schedule, adjusting it to reflect the user's emotional state. This information is delivered to drivers in real time, enabling efficient and satisfying deliveries.

[0204] For example, if the server detects data indicating a user is experiencing stress during an online meeting using its emotion recognition function, it will identify a relaxing time in the evening and adjust the food delivery accordingly. The user receives this information via their smartphone and is offered a suitable menu (e.g., a herbal tea set).

[0205] An example of a prompt to input into the generating AI model is, "User A has recently been posting stressful comments on social media. At what time of day should we schedule a food delivery so that he can relax the most?" In this way, the entire service can comprehensively consider the user's location and emotions, enabling it to provide a highly satisfying delivery experience.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server collects past delivery-related information, user schedule information, regional characteristics information, and digital behavior history from users' smartphones and tablets. The input comes from the user's device, and this input data is stored in the database after an anonymization process. As part of the data processing, identifiers are removed and information is aggregated so that individual users cannot be identified.

[0209] Step 2:

[0210] The server uses anonymized data to train a pre-developed generative AI model. The input consists of anonymized delivery-related information and user behavior history. By inputting this into the model, a predictive algorithm is built to infer the user's likely location and emotional state. Statistical analysis and machine learning techniques are used for data computation to obtain the output.

[0211] Step 3:

[0212] The server integrates emotion recognition capabilities to analyze users' emotional states from their social media and messaging app posts. The input is text data from online platforms, which is then converted into numerical or categorical data corresponding to emotions using emotion analysis algorithms. This makes it possible to identify states where users are feeling stressed or relaxed.

[0213] Step 4:

[0214] The server creates the optimal delivery schedule for the user based on the results of the generative AI model and emotion recognition. The input is the output data from steps 2 and 3, which are integrated to determine the time when the user is at home and relaxed, thereby setting the delivery time.

[0215] Step 5:

[0216] The server delivers optimized delivery schedules to the delivery drivers' terminals. The input is the generated delivery schedule data, and the output is a real-time updated delivery plan sent to the drivers. This enables efficient deliveries.

[0217] Step 6:

[0218] Users provide feedback after delivery is complete, which the server receives to improve the accuracy of the generative artificial intelligence model and emotion recognition function. The input is user evaluation information, and this data is used to update the parameters of the AI ​​model. As part of the data calculation, model evaluation metrics and performance metrics are recalculated and used to plan future deliveries.

[0219] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0235] This invention is a system that utilizes AI technology to improve the efficiency of delivery services. The system is designed to reduce the burden of redeliveries for delivery companies and improve customer convenience.

[0236] Data collection and anonymization

[0237] First, the server retrieves past delivery data, including date, time, delivery destination, and delivery result. Next, the server collects schedule information provided by the customer, which is entered by the user through partner apps and online platforms. In addition, the server collects local characteristic information from public institutions and local services, and digital activity history is collected with permission. All data is anonymized by the server to protect privacy.

[0238] Performing predictions using generative AI

[0239] The collected data is trained on commercially available or custom-built generative AI models within the server. The server uses these models to accurately predict when customers are likely to be at home. The models analyze the day of the week, time of day, and past customer behavior patterns to calculate the optimal delivery time for each customer.

[0240] Generating a delivery schedule

[0241] Next, the server generates an optimized delivery schedule for the driver based on the predicted time spent at home, efficiently combining multiple delivery destinations. The generated schedule is sent to the terminal, which the driver can view in real time.

[0242] Optimization through feedback

[0243] Once a delivery is complete, the terminal feeds the delivery results back to the server. This information includes the success rate of the delivery and the difference between the predicted time the recipient was home and the actual time of delivery. This allows the server to continuously improve the accuracy of its model and optimize future predictions.

[0244] Specific example

[0245] For example, if past data reveals that customer A, who is busy on weekdays, tends to be home on Saturday afternoons, the server will use this information to select Saturday afternoons as the recommended delivery time. Drivers can receive this information via their terminals and plan their deliveries accordingly, reducing the risk of redeliveries and increasing efficiency.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from various data sources. Since each piece of data may contain personal information, it is immediately anonymized after acquisition and converted into a form that does not identify individuals.

[0249] Step 2:

[0250] The server trains a generative AI model using anonymized data. This model extracts patterns from the input data and is used to learn the times of day when customers are most likely to be at home. This learning process incorporates algorithms that take into account schedule characteristics and regional trends.

[0251] Step 3:

[0252] The server uses a trained model to predict the optimal delivery time for each customer. This prediction reflects information tailored to each customer's location and individual needs. It also generates an overall schedule to create efficient delivery routes for drivers.

[0253] Step 4:

[0254] The terminal receives the optimal delivery schedule sent from the server and notifies the driver. Based on this information, the driver prepares to execute the daily delivery plan and adjusts their actions to complete deliveries by the specified time.

[0255] Step 5:

[0256] The user (driver) performs the delivery and sends the results to the server via their terminal upon completion. This result includes details such as whether the delivery was successful or if the recipient was absent.

[0257] Step 6:

[0258] The server receives and stores feedback data after delivery. This feedback is used to update and improve the model in the next update, contributing to increased prediction accuracy. This ensures continuously efficient delivery operations.

[0259] (Example 1)

[0260] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] In modern delivery services, the increase in redeliveries and the decline in delivery efficiency due to customer absence are significant problems. This increases costs for delivery companies and diminishes customer convenience. There is a need to improve this situation, enhance delivery efficiency, and increase customer satisfaction.

[0262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0263] In this invention, the server includes means for collecting past delivery information, user schedule information, regional characteristic information, and communication activity history; means for anonymizing the collected information; and means for training an inference AI model based on the anonymized information to predict times when the user is most likely to be at home. This makes it possible to predict the time periods when the user is most likely to be at home and to create an optimal delivery plan based on those times.

[0264] "Past delivery information" refers to records of past deliveries, including the date and time, recipient's address, and delivery status.

[0265] "User schedule information" refers to data that includes schedules for times and days specified by the user, and suggests the possibility of them being at home or away.

[0266] "Regional characteristic information" refers to data that shows the geographical, social, and economic characteristics of a region, including road conditions, traffic patterns, and people's behavioral characteristics.

[0267] "Communication activity history" refers to information about online behavior and communication obtained with the user's permission, including app usage and visit history.

[0268] "Anonymization" is a process that removes elements that can identify an individual from collected information in order to protect individual privacy.

[0269] An "inference AI model" is an artificial intelligence algorithm or computational model built to analyze data and make specific predictions.

[0270] A "delivery plan" is a delivery schedule created based on predicted times when recipients will be at home, in order to improve the efficiency of delivery operations.

[0271] "Data storage means" refers to databases and recording media used to store collected data and utilize it for future predictions and analysis.

[0272] This invention utilizes a server-centered system to improve the efficiency of delivery services. A specific embodiment of this system is described below.

[0273] The server first collects past delivery information from delivery companies. This information includes delivery date and time, recipient's address, and delivery status. The server also collects schedule information provided by users from mobile devices, etc. For example, it obtains information such as "I am home after 6 PM from Monday to Friday." Furthermore, to obtain regional characteristic information, it collects data from public institutions and communication activity history authorized by users.

[0274] After acquiring this information, the server anonymizes it to prevent the identification of individuals. The anonymized data is then used to train a generative AI model. This generative AI model uses commercially available software and proprietary algorithms to make predictions that take into account the day of the week, time of day, and regional characteristics.

[0275] Based on this prediction, the server creates the optimal delivery plan. For example, if the generating AI model predicts that "customer A is likely to be home on Saturday afternoon," the server will schedule the delivery for Saturday afternoon. The created delivery plan is sent to the driver's terminal and can be viewed in real time.

[0276] When a delivery is completed, the terminal feeds the results back to the server. This includes information such as "delivery successful" or "delivery missed." The server uses this feedback information to improve the generated AI model and adds it to a database to make future predictions more accurate.

[0277] As a concrete example, the prompt, "Analyze customer A's weekday and weekend home patterns and predict the optimal delivery time. Consider past delivery data and schedule information," can be used to help create efficient delivery schedules.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server collects past delivery information, user schedule information, regional characteristic information, and communication activity history. The server obtains this information from a database or collects it through direct input from the user. Specific operations include data collection using an API and the user inputting schedules via an app from a mobile terminal. The input data includes delivery date and time, address, past delivery results, and scheduled home time, etc., which are saved as inputs in the server's data storage.

[0281] Step 2:

[0282] The server anonymizes the collected information. At this time, data that can identify an individual is encrypted or IDized and processed to replace it with a unique identifier. The input is the non-anonymized data collected in Step 1, and the output is anonymized data with privacy protection. Specific operations include deleting personal information in the database and performing a masking process on the identification information.

[0283] Step 3:

[0284] The server uses the anonymized data to train a generated AI model. As the input, the anonymized data obtained in Step 2 is used. The server uses commercially available or self-developed AI software to analyze the user's home patterns from data such as day of the week, time, and regional characteristics. The output is the result of predicting the time periods with a high probability of the user being at home. Specifically, based on the user's past behavior history, the AI applies a machine learning algorithm to find patterns.

[0285] Step 4:

[0286] The server generates an optimal delivery plan based on the output of the AI model. This plan is optimized to schedule deliveries at times when the user is likely to be at home. The input is the prediction of the time at home obtained in Step 3. The output is the detailed delivery route and schedule to be passed to the driver. The server calculates the shortest path based on an algorithm and determines an efficient delivery order.

[0287] Step 5:

[0288] The terminal receives the delivery plan sent from the server and presents it to the driver in real time. The driver can check the next delivery destination and route information through this terminal. The input is the delivery plan data generated by the server in Step 4, and the output is the visual map and schedule displayed on the terminal screen. The driver executes the delivery based on this.

[0289] Step 6:

[0290] After delivery, the terminal reports the delivery result to the server. The input is the delivery result data input by the driver, including status such as success or absence. The server receives this feedback data, adds it to the database, and utilizes it for the continuous improvement of the generated AI model. The output is the next prediction with improved model accuracy. This further improves the accuracy of the next delivery plan.

[0291] (Application Example 1)

[0292] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0293] In modern delivery services, efficient delivery is essential, but the increase in redeliveries due to attempts to deliver during times when customers are absent is a significant challenge that leads to wasted time and resources. Furthermore, to optimize deliveries to multiple customers, it is essential to analyze various data in real time and calculate the optimal route and time. In addition, a system for continuously improving delivery accuracy is required.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for collecting past delivery information, user activity schedule information, regional characteristics information, and electronic activity history; means for anonymizing the collected information; and means for training a generation AI model based on the anonymized information to predict the time when the user is most likely to arrive. This makes it possible to formulate an efficient delivery plan and reduce the risk of redelivery. Furthermore, the system can receive feedback on delivery results and continuously improve delivery accuracy, thereby enhancing the overall service quality.

[0296] "Delivery information" refers to data related to past deliveries, including information such as the date and time, delivery destination, and delivery result.

[0297] "User activity plan information" refers to the user's plans and schedules for using the service, and is provided through partner apps and online platforms.

[0298] "Regional characteristic information" refers to information about the unique characteristics of a region, collected from public institutions and local services, and includes things like traffic conditions and weather conditions.

[0299] "Electronic activity history" refers to the history of activities performed by users in the digital environment, and is information that is useful for optimizing services.

[0300] "Anonymization" is a processing technology for removing information that can identify an individual and protecting privacy.

[0301] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes specific predictions or classifications.

[0302] A "delivery plan" is a delivery schedule based on the predicted arrival times of users and includes an efficient delivery route.

[0303] An "information device" is an electronic device for a driver or user to receive information in real time.

[0304] A "recording medium" is a storage device that stores data and is used for system learning and improvement.

[0305] To implement this system, a plurality of hardware and software are applied to enable the formulation and execution of an efficient delivery plan.

[0306] First, the server collects past delivery information, user activity schedule information, regional characteristic information, and electronic activity history. This information is anonymized after collection to protect privacy. For this purpose, the server uses a library for data anonymization (e.g., PySyft).

[0307] Based on the anonymized information, the server trains a generative AI model to predict the times when users are likely to arrive. Machine learning libraries such as TensorFlow and PyTorch are used in this process. This model performs prediction operations considering time, day of the week, and regional characteristics.

[0308] Next, the server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. This information device is a smartphone or other electronic device that receives the optimized route and delivery schedule in real time. This process reduces the risk of redelivery and increases delivery efficiency.

[0309] After delivery is complete, the terminal feeds the delivery results back to the server. Based on this feedback, the server adds data to the storage medium and improves the accuracy of the generated AI model. This cycle promotes continuous improvement of service quality.

[0310] For example, suppose a user enters their schedule into a partner app. Based on this information and past data, the server predicts with high accuracy when the user will be at home and delivers this information to the driver in real time. The system may use prompts such as: "Analyze the user's order history for the past 6 months and predict the optimal delivery time."

[0311] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0312] Step 1:

[0313] The server collects delivery information, user activity schedule information, regional characteristics information, and electronic activity history. Inputs include a historical delivery database, user schedule input, and regional public data sources. The output is an initial, unanonymized dataset. This dataset is then anonymized through the following process.

[0314] Step 2:

[0315] The server anonymizes the collected information. In this process, the server uses a data anonymization library (e.g., PySyft). The unanonymized dataset obtained in step 1 is used as input, and a privacy-protected anonymized dataset is generated as output. The anonymized data is then provided to the generative AI model as training data.

[0316] Step 3:

[0317] The server trains a generative AI model based on anonymized data. The anonymized dataset obtained in step 2 is used as input. TensorFlow or PyTorch is used for the generative AI model, and a prediction algorithm that takes into account time, day of the week, and regional characteristics predicts the arrival time of users. The output is the optimal predicted arrival time for each user, which is useful for integrated delivery planning.

[0318] Step 4:

[0319] The server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. The input is the predicted arrival time of the user obtained in step 3. This information is transmitted to information devices such as smartphones and tablets via a real-time delivery algorithm for the device. The output is an optimized delivery route and schedule for each driver.

[0320] Step 5:

[0321] Once a delivery is complete, the terminal feeds the delivery results back to the server. The input used is delivery performance information from the terminal (success, failure, time delay, etc.). The server saves this feedback to a storage medium and uses it as data for the next training cycle. The output is an updated dataset for improving model accuracy.

[0322] Through these steps, servers, terminals, and users can work together to improve the accuracy and efficiency of deliveries.

[0323] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0324] This invention is a system that combines AI technology and emotion recognition capabilities with the aim of improving delivery efficiency and customer satisfaction in home delivery services. This system not only uses data collection and generation AI models for prediction, but also utilizes an emotion engine to analyze user emotions and optimize delivery schedules based on those emotions.

[0325] Data collection and anonymization

[0326] First, the server collects past delivery data, customer schedule information, regional characteristics information, and digital activity history. This data is anonymized and cannot be used to identify individuals.

[0327] Utilizing the Emotion Engine

[0328] The server inputs the collected digital activity history into an emotion engine to analyze the user's emotional state. This emotion engine analyzes social media posts, messaging app interactions, and other data to detect changes in emotions.

[0329] Prediction using generative AI models

[0330] Taking sentiment analysis into account, the server uses a generative AI model to predict when users are most likely to be at home. This prediction is integrated with the user's schedule and local characteristics information to create an optimal delivery schedule.

[0331] Generating and adjusting delivery schedules

[0332] The server generates a delivery schedule that reflects the emotional state of the customer and delivers it to the terminal. The driver then carries out deliveries based on this optimized schedule.

[0333] example

[0334] For example, if a user is feeling stressed online, the emotion engine detects this state and, out of consideration, predicts a time when they are more likely to relax. Based on this, the server sets the delivery time to suit the user's comfort level and notifies the driver via the terminal.

[0335] Feedback and continuous improvement

[0336] After delivery is complete, the device sends the results and feedback to the server. This feedback data is used to further improve the accuracy of the generative AI model and emotion engine.

[0337] In this way, by introducing an emotion engine, this system aims to improve delivery efficiency and customer satisfaction by providing a more detailed delivery service that takes into account the user's emotional state.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from multiple data sources. During this collection phase, the data is immediately anonymized to protect privacy and make it impossible to identify individuals.

[0341] Step 2:

[0342] The server inputs anonymized digital activity history into the emotion engine to analyze the user's emotional state. The emotion engine has the ability to identify emotions such as positive, negative, and neutral from the user's text data and online activity patterns.

[0343] Step 3:

[0344] The server integrates the results of the emotion engine with other collected data and includes them in the generative AI model's dataset. The generative AI model then learns from this integrated data to predict the times when each customer is most likely to be at home. This prediction takes into account the user's emotional state, in addition to time of day, day of the week, regional characteristics, and schedule information.

[0345] Step 4:

[0346] The server creates an optimal delivery schedule based on predictions of when customers will be home, calculated by a generative AI model. This schedule is optimized by referencing data from multiple customers and is designed to allow drivers to work at their most efficient pace.

[0347] Step 5:

[0348] The terminal receives the optimal delivery schedule sent from the server and notifies the driver in real time. The driver plans the route for deliveries based on this schedule and travels according to the instructions.

[0349] Step 6:

[0350] The user (driver) performs the scheduled delivery and reports feedback on the delivery completion and results to the server via a terminal. This feedback includes information such as delivery success, details of missed deliveries, and user reactions.

[0351] Step 7:

[0352] The server receives feedback from drivers and uses it for subsequent data analysis. Based on this feedback, the accuracy of the generative AI model and emotion engine is further enhanced, improving the accuracy of future delivery plans.

[0353] (Example 2)

[0354] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0355] In home delivery services, achieving both improved delivery efficiency and customer satisfaction simultaneously is not easy. Accurately predicting customer availability and creating efficient delivery schedules is necessary, but conventional methods have struggled to make highly accurate predictions that take emotional states into account. This invention aims to solve this problem and enable more flexible and customer-centric delivery.

[0356] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0357] In this invention, the server includes means for aggregating past delivery history, customer schedule information, regional characteristic information, and electronic activity records; means for modifying the aggregated information so that personal information cannot be identified; means for predicting times when the user is most likely to be at home using a generative AI model based on the modified information; means for adjusting the delivery time and transmitting an optimized delivery plan to the terminal using emotional intelligence that analyzes the user's emotional state; and means for adding the results received after the delivery to the information storage device in order to improve the accuracy of the generative AI model and emotional intelligence. This significantly improves delivery efficiency and enables the provision of flexible delivery services that take customer comfort into consideration.

[0358] "Past delivery history" refers to records of deliveries made in the past, including data such as the date, time, location, and destination.

[0359] "Customer schedule information" refers to information including schedules and activity plans that customers have registered in advance.

[0360] "Regional characteristic information" refers to information that shows geographical, demographic, and traffic conditions specific to the delivery area.

[0361] "Electronic activity records" refer to data that shows a customer's actions and communication history on their digital devices.

[0362] "Modifying data so that personal information cannot be identified" refers to technical measures that anonymize data by removing or encrypting personally identifiable elements.

[0363] A "generative AI model" is a type of machine learning algorithm created to perform specific tasks using artificial intelligence techniques.

[0364] "The time when users are most likely to be at home" refers to the time period predicted by the AI ​​model as having the highest probability of customers being at home.

[0365] "Emotional intelligence" refers to the technology or function of mechanically analyzing a person's emotional state and using that analysis to select appropriate judgments and actions.

[0366] An "optimized delivery plan" is a schedule designed to be executed effectively and efficiently, taking into account delivery efficiency and customer preferences to the fullest extent.

[0367] An "information storage device" refers to a physical or virtual facility or system for recording and storing data.

[0368] This invention is a system aimed at improving efficiency and customer satisfaction in delivery services. At the heart of the system are a generative AI model and emotional intelligence, which operate on a server.

[0369] The server first aggregates past delivery history, customer schedule information, regional characteristics, and electronic activity records. APIs and database connection technologies are used for data collection, and encryption algorithms are applied to securely anonymize this data. Next, a generative AI model is used based on the collected data to predict the times when customers are most likely to be at home. Here, a representative machine learning algorithm is used, and the AI ​​model is instructed with prompts such as, "Predict the optimal delivery time while considering the user's emotional state."

[0370] Furthermore, the emotional intelligence analyzes the user's electronic activity log and determines their emotional state based on social media posts and messaging app content. This analysis utilizes an API equipped with natural language processing technology. The server comprehensively considers the predicted time spent at home and the emotional state to generate an optimal delivery schedule and send it to the device.

[0371] The terminal notifies the driver of the delivery schedule received from the server. Specifically, an application running on the mobile device is used to show the driver the optimal delivery route and time.

[0372] For example, if a user's online activity reveals signs of stress, the server analyzes this information and schedules delivery for a time when the user can relax. In this way, the implementation of this invention makes it possible to provide a detailed service that takes into account the individual user's state.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The server collects past delivery history, customer schedule information, regional characteristics information, and electronic activity records. It retrieves information from various APIs and databases as input and integrates it as digital data. As output, the collected data is stored after anonymization algorithms have been applied.

[0376] Step 2:

[0377] The server trains a generative AI model using anonymized data. It receives a prompt message, "Predict the optimal delivery time while considering the user's emotional state," and the AI ​​model predicts the time slots when the user is most likely to be at home. As a result, predicted time slots are extracted.

[0378] Step 3:

[0379] The server provides electronic activity logs to emotional intelligence to analyze the user's emotional state. As input, it analyzes social media posts and messaging app history, and uses natural language processing techniques to detect changes in emotion. As output, it estimates the user's current emotional state.

[0380] Step 4:

[0381] The server integrates predicted time spent at home and emotional state to generate an optimal delivery schedule. The input uses the data obtained in steps 2 and 3. Specifically, the generated schedule is optimized by a time management algorithm. The output is a specific delivery schedule for the driver.

[0382] Step 5:

[0383] The terminal receives an optimized delivery schedule sent from the server and notifies the driver. It receives the generated schedule data as input and provides visual instructions on the mobile device. As output, the driver receives real-time route and time information.

[0384] Step 6:

[0385] The terminal sends feedback to the server after delivery is complete. The input includes delivery results and driver comments, which are added to the server's database. As output, the feedback is used to further improve the accuracy of generative AI models and emotional intelligence.

[0386] (Application Example 2)

[0387] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0388] Current delivery services create delivery schedules that only consider the user's location, without taking into account the user's emotional state. This leads to problems such as deliveries occurring under stressful circumstances and service that doesn't suit the user's feelings. Furthermore, achieving both efficient delivery routes and emotionally responsive service simultaneously is difficult, posing a challenge to improving customer satisfaction.

[0389] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0390] In this invention, the server includes means for acquiring past delivery-related information, user schedule information, regional characteristics information, and digital behavior history; means for training a generative artificial intelligence model based on anonymized information to estimate the times when the user is most likely to be present; and means for integrating an emotion recognition function for analyzing the user's emotional state. This makes it possible to provide an optimal delivery schedule and service that takes into account the user's location and emotional state.

[0391] "Past delivery-related information" refers to all data related to past deliveries, including information such as delivery date and time, delivery destination, and positive feedback.

[0392] "User schedule information" refers to information about activities and schedules that the user has set or anticipates, including, for example, appointments and public holiday information in calendar applications.

[0393] "Regional characteristics information" refers to data about the characteristics of a specific region, including elements unique to that region, such as climate conditions, traffic conditions, and local events.

[0394] "Digital behavioral history" refers to data based on a user's online behavior, including, for example, statements made on social media and internet usage history.

[0395] A "generative artificial intelligence model" is a statistical model that uses AI technology to learn from collected data and make specific predictions or classifications.

[0396] "User location probability" is a concept that predicts the probability that a user is in a certain location during a specific time period.

[0397] "Emotion recognition functionality" refers to technology that analyzes a user's digital behavior history to identify their emotions at any given time.

[0398] An "optimal delivery schedule" is a delivery plan designed to maximize delivery efficiency and customer satisfaction, taking into account the user's location, emotions, and regional characteristics.

[0399] An "information terminal" refers to a device used to receive delivery schedules and other information, such as a smartphone or tablet.

[0400] An "information recording device" is a system or device for storing data over a long period of time. Examples include cloud-based data storage services.

[0401] The server acquires past delivery-related information, user schedule information, regional characteristics information, and digital behavior history. This information is collected through applications on the user's smartphone or tablet and anonymized to protect privacy. In this process, the aforementioned information is analyzed on a keyword basis and converted into a format that does not identify individual users. The anonymized data is securely stored in an information recording device, for example, on a cloud service. This stored information is used as foundational data to train a generative artificial intelligence model. This AI model is used to predict the user's location and emotional state, with its emotion recognition function analyzing statements from social media and messaging apps.

[0402] The generative artificial intelligence model utilizes technologies like OpenAI to determine when users are most relaxed, taking into account time, regional characteristics, and effective emotional indicators. Based on these predictions, the server generates an optimal delivery schedule, adjusting it to reflect the user's emotional state. This information is delivered to drivers in real time, enabling efficient and satisfying deliveries.

[0403] For example, if the server detects data indicating a user is experiencing stress during an online meeting using its emotion recognition function, it will identify a relaxing time in the evening and adjust the food delivery accordingly. The user receives this information via their smartphone and is offered a suitable menu (e.g., a herbal tea set).

[0404] An example of a prompt to input into the generating AI model is, "User A has recently been posting stressful comments on social media. At what time of day should we schedule a food delivery so that he can relax the most?" In this way, the entire service can comprehensively consider the user's location and emotions, enabling it to provide a highly satisfying delivery experience.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server collects past delivery-related information, user schedule information, regional characteristics information, and digital behavior history from users' smartphones and tablets. The input comes from the user's device, and this input data is stored in the database after an anonymization process. As part of the data processing, identifiers are removed and information is aggregated so that individual users cannot be identified.

[0408] Step 2:

[0409] The server uses anonymized data to train a pre-developed generative AI model. The input consists of anonymized delivery-related information and user behavior history. By inputting this into the model, a predictive algorithm is built to infer the user's likely location and emotional state. Statistical analysis and machine learning techniques are used for data computation to obtain the output.

[0410] Step 3:

[0411] The server integrates emotion recognition capabilities to analyze users' emotional states from their social media and messaging app posts. The input is text data from online platforms, which is then converted into numerical or categorical data corresponding to emotions using emotion analysis algorithms. This makes it possible to identify states where users are feeling stressed or relaxed.

[0412] Step 4:

[0413] The server creates the optimal delivery schedule for the user based on the results of the generative AI model and emotion recognition. The input is the output data from steps 2 and 3, which are integrated to determine the time when the user is at home and relaxed, thereby setting the delivery time.

[0414] Step 5:

[0415] The server delivers optimized delivery schedules to the delivery drivers' terminals. The input is the generated delivery schedule data, and the output is a real-time updated delivery plan sent to the drivers. This enables efficient deliveries.

[0416] Step 6:

[0417] Users provide feedback after delivery is complete, which the server receives to improve the accuracy of the generative artificial intelligence model and emotion recognition function. The input is user evaluation information, and this data is used to update the parameters of the AI ​​model. As part of the data calculation, model evaluation metrics and performance metrics are recalculated and used to plan future deliveries.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] This invention is a system that utilizes AI technology to improve the efficiency of delivery services. The system is designed to reduce the burden of redeliveries for delivery companies and improve customer convenience.

[0435] Data collection and anonymization

[0436] First, the server retrieves past delivery data, including date, time, delivery destination, and delivery result. Next, the server collects schedule information provided by the customer, which is entered by the user through partner apps and online platforms. In addition, the server collects local characteristic information from public institutions and local services, and digital activity history is collected with permission. All data is anonymized by the server to protect privacy.

[0437] Performing predictions using generative AI

[0438] The collected data is trained on commercially available or custom-built generative AI models within the server. The server uses these models to accurately predict when customers are likely to be at home. The models analyze the day of the week, time of day, and past customer behavior patterns to calculate the optimal delivery time for each customer.

[0439] Generating a delivery schedule

[0440] Next, the server generates an optimized delivery schedule for the driver based on the predicted time spent at home, efficiently combining multiple delivery destinations. The generated schedule is sent to the terminal, which the driver can view in real time.

[0441] Optimization through feedback

[0442] Once a delivery is complete, the terminal feeds the delivery results back to the server. This information includes the success rate of the delivery and the difference between the predicted time the recipient was home and the actual time of delivery. This allows the server to continuously improve the accuracy of its model and optimize future predictions.

[0443] Specific example

[0444] For example, if past data reveals that customer A, who is busy on weekdays, tends to be home on Saturday afternoons, the server will use this information to select Saturday afternoons as the recommended delivery time. Drivers can receive this information via their terminals and plan their deliveries accordingly, reducing the risk of redeliveries and increasing efficiency.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from various data sources. Since each piece of data may contain personal information, it is immediately anonymized after acquisition and converted into a form that does not identify individuals.

[0448] Step 2:

[0449] The server trains a generative AI model using anonymized data. This model extracts patterns from the input data and is used to learn the times of day when customers are most likely to be at home. This learning process incorporates algorithms that take into account schedule characteristics and regional trends.

[0450] Step 3:

[0451] The server uses a trained model to predict the optimal delivery time for each customer. This prediction reflects information tailored to each customer's location and individual needs. It also generates an overall schedule to create efficient delivery routes for drivers.

[0452] Step 4:

[0453] The terminal receives the optimal delivery schedule sent from the server and notifies the driver. Based on this information, the driver prepares to execute the daily delivery plan and adjusts their actions to complete deliveries by the specified time.

[0454] Step 5:

[0455] The user (driver) performs the delivery and sends the results to the server via their terminal upon completion. This result includes details such as whether the delivery was successful or if the recipient was absent.

[0456] Step 6:

[0457] The server receives and stores feedback data after delivery. This feedback is used to update and improve the model in the next update, contributing to increased prediction accuracy. This ensures continuously efficient delivery operations.

[0458] (Example 1)

[0459] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0460] In modern delivery services, the increase in redeliveries and the decline in delivery efficiency due to customer absence are significant problems. This increases costs for delivery companies and diminishes customer convenience. There is a need to improve this situation, enhance delivery efficiency, and increase customer satisfaction.

[0461] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0462] In this invention, the server includes means for collecting past delivery information, user schedule information, regional characteristic information, and communication activity history; means for anonymizing the collected information; and means for training an inference AI model based on the anonymized information to predict times when the user is most likely to be at home. This makes it possible to predict the time periods when the user is most likely to be at home and to create an optimal delivery plan based on those times.

[0463] "Past delivery information" refers to records of past deliveries, including the date and time, recipient's address, and delivery status.

[0464] "User schedule information" refers to data that includes schedules for times and days specified by the user, and suggests the possibility of them being at home or away.

[0465] "Regional characteristic information" refers to data that shows the geographical, social, and economic characteristics of a region, including road conditions, traffic patterns, and people's behavioral characteristics.

[0466] "Communication activity history" refers to information about online behavior and communication obtained with the user's permission, including app usage and visit history.

[0467] "Anonymization" is a process that removes elements that can identify an individual from collected information in order to protect individual privacy.

[0468] An "inference AI model" is an artificial intelligence algorithm or computational model built to analyze data and make specific predictions.

[0469] A "delivery plan" is a delivery schedule created based on predicted times when recipients will be at home, in order to improve the efficiency of delivery operations.

[0470] "Data storage means" refers to databases and recording media used to store collected data and utilize it for future predictions and analysis.

[0471] This invention utilizes a server-centered system to improve the efficiency of delivery services. A specific embodiment of this system is described below.

[0472] The server first collects past delivery information from delivery companies. This information includes delivery date and time, recipient's address, and delivery status. The server also collects schedule information provided by users from mobile devices, etc. For example, it obtains information such as "I am home after 6 PM from Monday to Friday." Furthermore, to obtain regional characteristic information, it collects data from public institutions and communication activity history authorized by users.

[0473] After acquiring this information, the server anonymizes it to prevent the identification of individuals. The anonymized data is then used to train a generative AI model. This generative AI model uses commercially available software and proprietary algorithms to make predictions that take into account the day of the week, time of day, and regional characteristics.

[0474] Based on this prediction, the server creates the optimal delivery plan. For example, if the generating AI model predicts that "customer A is likely to be home on Saturday afternoon," the server will schedule the delivery for Saturday afternoon. The created delivery plan is sent to the driver's terminal and can be viewed in real time.

[0475] When a delivery is completed, the terminal feeds the results back to the server. This includes information such as "delivery successful" or "delivery missed." The server uses this feedback information to improve the generated AI model and adds it to a database to make future predictions more accurate.

[0476] As a concrete example, the prompt, "Analyze customer A's weekday and weekend home patterns and predict the optimal delivery time. Consider past delivery data and schedule information," can be used to help create efficient delivery schedules.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server collects past delivery information, user schedule information, regional characteristics information, and communication activity history. The server obtains this information from a database or through direct input from users. Specifically, data collection is done using APIs, and users input their schedules via an app on their mobile devices. This input data includes delivery date and time, address, past delivery results, and scheduled time spent at home, and this is stored as input in the server's data storage.

[0480] Step 2:

[0481] The server anonymizes the collected information. This involves encrypting or ID-ifying personally identifiable data and replacing it with a unique identifier. The input is the unanonymized data collected in step 1, and the output is anonymized data with privacy protection. Specifically, this involves deleting personal information from the database and masking identifying information.

[0482] Step 3:

[0483] The server trains a generative AI model using anonymized data. The anonymized data obtained in step 2 is used as input. The server uses commercially available or custom-developed AI software to analyze user home patterns from data such as day of the week, time, and regional characteristics. The output is a prediction of the time periods when each user is most likely to be at home. Specifically, the AI ​​applies machine learning algorithms to identify patterns based on the user's past behavior history.

[0484] Step 4:

[0485] The server generates an optimal delivery plan based on the output of the AI ​​model. This plan is optimized to schedule deliveries at times when users are most likely to be at home. The input is the predicted time spent at home obtained in step 3. The output is the detailed delivery route and schedule to be given to the driver. The server calculates the shortest path based on the algorithm and determines an efficient delivery order.

[0486] Step 5:

[0487] The terminal receives the delivery plan sent from the server and presents it to the driver in real time. The driver can check the next delivery destination and route information through this terminal. The input is the delivery plan data generated from the server in step 4, and the output is a visual map and schedule displayed on the terminal screen. The driver uses this to carry out deliveries.

[0488] Step 6:

[0489] After delivery, the terminal reports the delivery results to the server. The input is delivery result data entered by the driver, including status such as success or absence. The server receives this feedback data, adds it to the database, and uses it to continuously improve the generated AI model. The output is the next prediction with improved model accuracy. This further improves the accuracy of the next delivery plan.

[0490] (Application Example 1)

[0491] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] In modern delivery services, efficient delivery is essential, but the increase in redeliveries due to attempts to deliver during times when customers are absent is a significant challenge that leads to wasted time and resources. Furthermore, to optimize deliveries to multiple customers, it is essential to analyze various data in real time and calculate the optimal route and time. In addition, a system for continuously improving delivery accuracy is required.

[0493] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0494] In this invention, the server includes means for collecting past delivery information, user activity schedule information, regional characteristics information, and electronic activity history; means for anonymizing the collected information; and means for training a generation AI model based on the anonymized information to predict the time when the user is most likely to arrive. This makes it possible to formulate an efficient delivery plan and reduce the risk of redelivery. Furthermore, the system can receive feedback on delivery results and continuously improve delivery accuracy, thereby enhancing the overall service quality.

[0495] "Delivery information" refers to data related to past deliveries, including information such as the date and time, delivery destination, and delivery result.

[0496] "User activity plan information" refers to the user's plans and schedules for using the service, and is provided through partner apps and online platforms.

[0497] "Regional characteristic information" refers to information about the unique characteristics of a region, collected from public institutions and local services, and includes things like traffic conditions and weather conditions.

[0498] "Electronic activity history" refers to the history of activities performed by users in the digital environment, and is information that is useful for optimizing services.

[0499] "Anonymization" is a processing technique that removes personally identifiable information to protect privacy.

[0500] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes specific predictions or classifications.

[0501] A "delivery plan" is a delivery schedule based on the predicted arrival time of the user, and includes efficient delivery routes.

[0502] "Information equipment" refers to electronic devices that allow drivers and users to receive information in real time.

[0503] A "recording medium" is a storage device used to store data and for system learning and improvement.

[0504] This system requires the application of multiple hardware and software components to enable the efficient planning and execution of delivery schedules.

[0505] First, the server collects past delivery information, user activity schedules, regional characteristics, and electronic activity history. This information is anonymized after collection to protect privacy. For this purpose, the server uses a data anonymization library (e.g., PySyft).

[0506] Based on anonymized information, the server trains a generative AI model to predict the most likely times for users to arrive. This process utilizes machine learning libraries such as TensorFlow and PyTorch. The model performs predictive calculations that take into account time, weekday, and regional characteristics.

[0507] Next, the server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. This information device is a smartphone or other electronic device that receives the optimized route and delivery schedule in real time. This process reduces the risk of redelivery and increases delivery efficiency.

[0508] After delivery is complete, the terminal feeds the delivery results back to the server. Based on this feedback, the server adds data to the storage medium and improves the accuracy of the generated AI model. This cycle promotes continuous improvement of service quality.

[0509] For example, suppose a user enters their schedule into a partner app. Based on this information and past data, the server predicts with high accuracy when the user will be at home and delivers this information to the driver in real time. The system may use prompts such as: "Analyze the user's order history for the past 6 months and predict the optimal delivery time."

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects delivery information, user activity schedule information, regional characteristics information, and electronic activity history. Inputs include a historical delivery database, user schedule input, and regional public data sources. The output is an initial, unanonymized dataset. This dataset is then anonymized through the following process.

[0513] Step 2:

[0514] The server anonymizes the collected information. In this process, the server uses a data anonymization library (e.g., PySyft). The unanonymized dataset obtained in step 1 is used as input, and a privacy-protected anonymized dataset is generated as output. The anonymized data is then provided to the generative AI model as training data.

[0515] Step 3:

[0516] The server trains a generative AI model based on anonymized data. The anonymized dataset obtained in step 2 is used as input. TensorFlow or PyTorch is used for the generative AI model, and a prediction algorithm that takes into account time, day of the week, and regional characteristics predicts the arrival time of users. The output is the optimal predicted arrival time for each user, which is useful for integrated delivery planning.

[0517] Step 4:

[0518] The server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. The input is the predicted arrival time of the user obtained in step 3. This information is transmitted to information devices such as smartphones and tablets via a real-time delivery algorithm for the device. The output is an optimized delivery route and schedule for each driver.

[0519] Step 5:

[0520] Once a delivery is complete, the terminal feeds the delivery results back to the server. The input used is delivery performance information from the terminal (success, failure, time delay, etc.). The server saves this feedback to a storage medium and uses it as data for the next training cycle. The output is an updated dataset for improving model accuracy.

[0521] Through these steps, servers, terminals, and users can work together to improve the accuracy and efficiency of deliveries.

[0522] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0523] This invention is a system that combines AI technology and emotion recognition capabilities with the aim of improving delivery efficiency and customer satisfaction in home delivery services. This system not only uses data collection and generation AI models for prediction, but also utilizes an emotion engine to analyze user emotions and optimize delivery schedules based on those emotions.

[0524] Data collection and anonymization

[0525] First, the server collects past delivery data, customer schedule information, regional characteristics information, and digital activity history. This data is anonymized and cannot be used to identify individuals.

[0526] Utilizing the Emotion Engine

[0527] The server inputs the collected digital activity history into an emotion engine to analyze the user's emotional state. This emotion engine analyzes social media posts, messaging app interactions, and other data to detect changes in emotions.

[0528] Prediction using generative AI models

[0529] Taking sentiment analysis into account, the server uses a generative AI model to predict when users are most likely to be at home. This prediction is integrated with the user's schedule and local characteristics information to create an optimal delivery schedule.

[0530] Generating and adjusting delivery schedules

[0531] The server generates a delivery schedule that reflects the emotional state of the customer and delivers it to the terminal. The driver then carries out deliveries based on this optimized schedule.

[0532] example

[0533] For example, if a user is feeling stressed online, the emotion engine detects this state and, out of consideration, predicts a time when they are more likely to relax. Based on this, the server sets the delivery time to suit the user's comfort level and notifies the driver via the terminal.

[0534] Feedback and continuous improvement

[0535] After delivery is complete, the device sends the results and feedback to the server. This feedback data is used to further improve the accuracy of the generative AI model and emotion engine.

[0536] In this way, by introducing an emotion engine, this system aims to improve delivery efficiency and customer satisfaction by providing a more detailed delivery service that takes into account the user's emotional state.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from multiple data sources. During this collection phase, the data is immediately anonymized to protect privacy and make it impossible to identify individuals.

[0540] Step 2:

[0541] The server inputs anonymized digital activity history into the emotion engine to analyze the user's emotional state. The emotion engine has the ability to identify emotions such as positive, negative, and neutral from the user's text data and online activity patterns.

[0542] Step 3:

[0543] The server integrates the results of the emotion engine with other collected data and includes them in the generative AI model's dataset. The generative AI model then learns from this integrated data to predict the times when each customer is most likely to be at home. This prediction takes into account the user's emotional state, in addition to time of day, day of the week, regional characteristics, and schedule information.

[0544] Step 4:

[0545] The server creates an optimal delivery schedule based on predictions of when customers will be home, calculated by a generative AI model. This schedule is optimized by referencing data from multiple customers and is designed to allow drivers to work at their most efficient pace.

[0546] Step 5:

[0547] The terminal receives the optimal delivery schedule sent from the server and notifies the driver in real time. The driver plans the route for deliveries based on this schedule and travels according to the instructions.

[0548] Step 6:

[0549] The user (driver) performs the scheduled delivery and reports feedback on the delivery completion and results to the server via a terminal. This feedback includes information such as delivery success, details of missed deliveries, and user reactions.

[0550] Step 7:

[0551] The server receives feedback from drivers and uses it for subsequent data analysis. Based on this feedback, the accuracy of the generative AI model and emotion engine is further enhanced, improving the accuracy of future delivery plans.

[0552] (Example 2)

[0553] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0554] In home delivery services, achieving both improved delivery efficiency and customer satisfaction simultaneously is not easy. Accurately predicting customer availability and creating efficient delivery schedules is necessary, but conventional methods have struggled to make highly accurate predictions that take emotional states into account. This invention aims to solve this problem and enable more flexible and customer-centric delivery.

[0555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0556] In this invention, the server includes means for aggregating past delivery history, customer schedule information, regional characteristic information, and electronic activity records; means for modifying the aggregated information so that personal information cannot be identified; means for predicting times when the user is most likely to be at home using a generative AI model based on the modified information; means for adjusting the delivery time and transmitting an optimized delivery plan to the terminal using emotional intelligence that analyzes the user's emotional state; and means for adding the results received after the delivery to the information storage device in order to improve the accuracy of the generative AI model and emotional intelligence. This significantly improves delivery efficiency and enables the provision of flexible delivery services that take customer comfort into consideration.

[0557] "Past delivery history" refers to records of deliveries made in the past, including data such as the date, time, location, and destination.

[0558] "Customer schedule information" refers to information including schedules and activity plans that customers have registered in advance.

[0559] "Regional characteristic information" refers to information that shows geographical, demographic, and traffic conditions specific to the delivery area.

[0560] "Electronic activity records" refer to data that shows a customer's actions and communication history on their digital devices.

[0561] "Modifying data so that personal information cannot be identified" refers to technical measures that anonymize data by removing or encrypting personally identifiable elements.

[0562] A "generative AI model" is a type of machine learning algorithm created to perform specific tasks using artificial intelligence techniques.

[0563] "The time when users are most likely to be at home" refers to the time period predicted by the AI ​​model as having the highest probability of customers being at home.

[0564] "Emotional intelligence" refers to the technology or function of mechanically analyzing a person's emotional state and using that analysis to select appropriate judgments and actions.

[0565] An "optimized delivery plan" is a schedule designed to be executed effectively and efficiently, taking into account delivery efficiency and customer preferences to the fullest extent.

[0566] An "information storage device" refers to a physical or virtual facility or system for recording and storing data.

[0567] This invention is a system aimed at improving efficiency and customer satisfaction in delivery services. At the heart of the system are a generative AI model and emotional intelligence, which operate on a server.

[0568] The server first aggregates past delivery history, customer schedule information, regional characteristics, and electronic activity records. APIs and database connection technologies are used for data collection, and encryption algorithms are applied to securely anonymize this data. Next, a generative AI model is used based on the collected data to predict the times when customers are most likely to be at home. Here, a representative machine learning algorithm is used, and the AI ​​model is instructed with prompts such as, "Predict the optimal delivery time while considering the user's emotional state."

[0569] Furthermore, the emotional intelligence analyzes the user's electronic activity log and determines their emotional state based on social media posts and messaging app content. This analysis utilizes an API equipped with natural language processing technology. The server comprehensively considers the predicted time spent at home and the emotional state to generate an optimal delivery schedule and send it to the device.

[0570] The terminal notifies the driver of the delivery schedule received from the server. Specifically, an application running on the mobile device is used to show the driver the optimal delivery route and time.

[0571] For example, if a user's online activity reveals signs of stress, the server analyzes this information and schedules delivery for a time when the user can relax. In this way, the implementation of this invention makes it possible to provide a detailed service that takes into account the individual user's state.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The server collects past delivery history, customer schedule information, regional characteristics information, and electronic activity records. It retrieves information from various APIs and databases as input and integrates it as digital data. As output, the collected data is stored after anonymization algorithms have been applied.

[0575] Step 2:

[0576] The server trains a generative AI model using anonymized data. It receives a prompt message, "Predict the optimal delivery time while considering the user's emotional state," and the AI ​​model predicts the time slots when the user is most likely to be at home. As a result, predicted time slots are extracted.

[0577] Step 3:

[0578] The server provides electronic activity logs to emotional intelligence to analyze the user's emotional state. As input, it analyzes social media posts and messaging app history, and uses natural language processing techniques to detect changes in emotion. As output, it estimates the user's current emotional state.

[0579] Step 4:

[0580] The server integrates predicted time spent at home and emotional state to generate an optimal delivery schedule. The input uses the data obtained in steps 2 and 3. Specifically, the generated schedule is optimized by a time management algorithm. The output is a specific delivery schedule for the driver.

[0581] Step 5:

[0582] The terminal receives an optimized delivery schedule sent from the server and notifies the driver. It receives the generated schedule data as input and provides visual instructions on the mobile device. As output, the driver receives real-time route and time information.

[0583] Step 6:

[0584] The terminal sends feedback to the server after delivery is complete. The input includes delivery results and driver comments, which are added to the server's database. As output, the feedback is used to further improve the accuracy of generative AI models and emotional intelligence.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] Current delivery services create delivery schedules that only consider the user's location, without taking into account the user's emotional state. This leads to problems such as deliveries occurring under stressful circumstances and service that doesn't suit the user's feelings. Furthermore, achieving both efficient delivery routes and emotionally responsive service simultaneously is difficult, posing a challenge to improving customer satisfaction.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0589] In this invention, the server includes means for acquiring past delivery-related information, user schedule information, regional characteristics information, and digital behavior history; means for training a generative artificial intelligence model based on anonymized information to estimate the times when the user is most likely to be present; and means for integrating an emotion recognition function for analyzing the user's emotional state. This makes it possible to provide an optimal delivery schedule and service that takes into account the user's location and emotional state.

[0590] "Past delivery-related information" refers to all data related to past deliveries, including information such as delivery date and time, delivery destination, and positive feedback.

[0591] "User schedule information" refers to information about activities and schedules that the user has set or anticipates, including, for example, appointments and public holiday information in calendar applications.

[0592] "Regional characteristics information" refers to data about the characteristics of a specific region, including elements unique to that region, such as climate conditions, traffic conditions, and local events.

[0593] "Digital behavioral history" refers to data based on a user's online behavior, including, for example, statements made on social media and internet usage history.

[0594] A "generative artificial intelligence model" is a statistical model that uses AI technology to learn from collected data and make specific predictions or classifications.

[0595] "User location probability" is a concept that predicts the probability that a user is in a certain location during a specific time period.

[0596] "Emotion recognition functionality" refers to technology that analyzes a user's digital behavior history to identify their emotions at any given time.

[0597] An "optimal delivery schedule" is a delivery plan designed to maximize delivery efficiency and customer satisfaction, taking into account the user's location, emotions, and regional characteristics.

[0598] An "information terminal" refers to a device used to receive delivery schedules and other information, such as a smartphone or tablet.

[0599] An "information recording device" is a system or device for storing data over a long period of time. Examples include cloud-based data storage services.

[0600] The server acquires past delivery-related information, user schedule information, regional characteristics information, and digital behavior history. This information is collected through applications on the user's smartphone or tablet and anonymized to protect privacy. In this process, the aforementioned information is analyzed on a keyword basis and converted into a format that does not identify individual users. The anonymized data is securely stored in an information recording device, for example, on a cloud service. This stored information is used as foundational data to train a generative artificial intelligence model. This AI model is used to predict the user's location and emotional state, with its emotion recognition function analyzing statements from social media and messaging apps.

[0601] The generative artificial intelligence model utilizes technologies like OpenAI to determine when users are most relaxed, taking into account time, regional characteristics, and effective emotional indicators. Based on these predictions, the server generates an optimal delivery schedule, adjusting it to reflect the user's emotional state. This information is delivered to drivers in real time, enabling efficient and satisfying deliveries.

[0602] For example, if the server detects data indicating a user is experiencing stress during an online meeting using its emotion recognition function, it will identify a relaxing time in the evening and adjust the food delivery accordingly. The user receives this information via their smartphone and is offered a suitable menu (e.g., a herbal tea set).

[0603] An example of a prompt to input into the generating AI model is, "User A has recently been posting stressful comments on social media. At what time of day should we schedule a food delivery so that he can relax the most?" In this way, the entire service can comprehensively consider the user's location and emotions, enabling it to provide a highly satisfying delivery experience.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The server collects past delivery-related information, user schedule information, regional characteristics information, and digital behavior history from users' smartphones and tablets. The input comes from the user's device, and this input data is stored in the database after an anonymization process. As part of the data processing, identifiers are removed and information is aggregated so that individual users cannot be identified.

[0607] Step 2:

[0608] The server uses anonymized data to train a pre-developed generative AI model. The input consists of anonymized delivery-related information and user behavior history. By inputting this into the model, a predictive algorithm is built to infer the user's likely location and emotional state. Statistical analysis and machine learning techniques are used for data computation to obtain the output.

[0609] Step 3:

[0610] The server integrates emotion recognition capabilities to analyze users' emotional states from their social media and messaging app posts. The input is text data from online platforms, which is then converted into numerical or categorical data corresponding to emotions using emotion analysis algorithms. This makes it possible to identify states where users are feeling stressed or relaxed.

[0611] Step 4:

[0612] The server creates the optimal delivery schedule for the user based on the results of the generative AI model and emotion recognition. The input is the output data from steps 2 and 3, which are integrated to determine the time when the user is at home and relaxed, thereby setting the delivery time.

[0613] Step 5:

[0614] The server delivers optimized delivery schedules to the delivery drivers' terminals. The input is the generated delivery schedule data, and the output is a real-time updated delivery plan sent to the drivers. This enables efficient deliveries.

[0615] Step 6:

[0616] Users provide feedback after delivery is complete, which the server receives to improve the accuracy of the generative artificial intelligence model and emotion recognition function. The input is user evaluation information, and this data is used to update the parameters of the AI ​​model. As part of the data calculation, model evaluation metrics and performance metrics are recalculated and used to plan future deliveries.

[0617] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0623] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0625] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0627] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0628] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0629] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0630] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0631] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0632] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0633] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] This invention is a system that utilizes AI technology to improve the efficiency of delivery services. The system is designed to reduce the burden of redeliveries for delivery companies and improve customer convenience.

[0635] Data collection and anonymization

[0636] First, the server retrieves past delivery data, including date, time, delivery destination, and delivery result. Next, the server collects schedule information provided by the customer, which is entered by the user through partner apps and online platforms. In addition, the server collects local characteristic information from public institutions and local services, and digital activity history is collected with permission. All data is anonymized by the server to protect privacy.

[0637] Performing predictions using generative AI

[0638] The collected data is trained on commercially available or custom-built generative AI models within the server. The server uses these models to accurately predict when customers are likely to be at home. The models analyze the day of the week, time of day, and past customer behavior patterns to calculate the optimal delivery time for each customer.

[0639] Generating a delivery schedule

[0640] Next, the server generates an optimized delivery schedule for the driver based on the predicted time spent at home, efficiently combining multiple delivery destinations. The generated schedule is sent to the terminal, which the driver can view in real time.

[0641] Optimization through feedback

[0642] Once a delivery is complete, the terminal feeds the delivery results back to the server. This information includes the success rate of the delivery and the difference between the predicted time the recipient was home and the actual time of delivery. This allows the server to continuously improve the accuracy of its model and optimize future predictions.

[0643] Specific example

[0644] For example, if past data reveals that customer A, who is busy on weekdays, tends to be home on Saturday afternoons, the server will use this information to select Saturday afternoons as the recommended delivery time. Drivers can receive this information via their terminals and plan their deliveries accordingly, reducing the risk of redeliveries and increasing efficiency.

[0645] The following describes the processing flow.

[0646] Step 1:

[0647] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from various data sources. Since each piece of data may contain personal information, it is immediately anonymized after acquisition and converted into a form that does not identify individuals.

[0648] Step 2:

[0649] The server trains a generative AI model using anonymized data. This model extracts patterns from the input data and is used to learn the times of day when customers are most likely to be at home. This learning process incorporates algorithms that take into account schedule characteristics and regional trends.

[0650] Step 3:

[0651] The server uses a trained model to predict the optimal delivery time for each customer. This prediction reflects information tailored to each customer's location and individual needs. It also generates an overall schedule to create efficient delivery routes for drivers.

[0652] Step 4:

[0653] The terminal receives the optimal delivery schedule sent from the server and notifies the driver. Based on this information, the driver prepares to execute the daily delivery plan and adjusts their actions to complete deliveries by the specified time.

[0654] Step 5:

[0655] The user (driver) performs the delivery and sends the results to the server via their terminal upon completion. This result includes details such as whether the delivery was successful or if the recipient was absent.

[0656] Step 6:

[0657] The server receives and stores feedback data after delivery. This feedback is used to update and improve the model in the next update, contributing to increased prediction accuracy. This ensures continuously efficient delivery operations.

[0658] (Example 1)

[0659] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] In modern delivery services, the increase in redeliveries and the decline in delivery efficiency due to customer absence are significant problems. This increases costs for delivery companies and diminishes customer convenience. There is a need to improve this situation, enhance delivery efficiency, and increase customer satisfaction.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes means for collecting past delivery information, user schedule information, regional characteristic information, and communication activity history; means for anonymizing the collected information; and means for training an inference AI model based on the anonymized information to predict times when the user is most likely to be at home. This makes it possible to predict the time periods when the user is most likely to be at home and to create an optimal delivery plan based on those times.

[0663] "Past delivery information" refers to records of past deliveries, including the date and time, recipient's address, and delivery status.

[0664] "User schedule information" refers to data that includes schedules for times and days specified by the user, and suggests the possibility of them being at home or away.

[0665] "Regional characteristic information" refers to data that shows the geographical, social, and economic characteristics of a region, including road conditions, traffic patterns, and people's behavioral characteristics.

[0666] "Communication activity history" refers to information about online behavior and communication obtained with the user's permission, including app usage and visit history.

[0667] "Anonymization" is a process that removes elements that can identify an individual from collected information in order to protect individual privacy.

[0668] An "inference AI model" is an artificial intelligence algorithm or computational model built to analyze data and make specific predictions.

[0669] A "delivery plan" is a delivery schedule created based on predicted times when recipients will be at home, in order to improve the efficiency of delivery operations.

[0670] "Data storage means" refers to databases and recording media used to store collected data and utilize it for future predictions and analysis.

[0671] This invention utilizes a server-centered system to improve the efficiency of delivery services. A specific embodiment of this system is described below.

[0672] The server first collects past delivery information from delivery companies. This information includes delivery date and time, recipient's address, and delivery status. The server also collects schedule information provided by users from mobile devices, etc. For example, it obtains information such as "I am home after 6 PM from Monday to Friday." Furthermore, to obtain regional characteristic information, it collects data from public institutions and communication activity history authorized by users.

[0673] After acquiring this information, the server anonymizes it to prevent the identification of individuals. The anonymized data is then used to train a generative AI model. This generative AI model uses commercially available software and proprietary algorithms to make predictions that take into account the day of the week, time of day, and regional characteristics.

[0674] Based on this prediction, the server creates the optimal delivery plan. For example, if the generating AI model predicts that "customer A is likely to be home on Saturday afternoon," the server will schedule the delivery for Saturday afternoon. The created delivery plan is sent to the driver's terminal and can be viewed in real time.

[0675] When a delivery is completed, the terminal feeds the results back to the server. This includes information such as "delivery successful" or "delivery missed." The server uses this feedback information to improve the generated AI model and adds it to a database to make future predictions more accurate.

[0676] As a concrete example, the prompt, "Analyze customer A's weekday and weekend home patterns and predict the optimal delivery time. Consider past delivery data and schedule information," can be used to help create efficient delivery schedules.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] The server collects past delivery information, user schedule information, regional characteristics information, and communication activity history. The server obtains this information from a database or through direct input from users. Specifically, data collection is done using APIs, and users input their schedules via an app on their mobile devices. This input data includes delivery date and time, address, past delivery results, and scheduled time spent at home, and this is stored as input in the server's data storage.

[0680] Step 2:

[0681] The server anonymizes the collected information. This involves encrypting or ID-ifying personally identifiable data and replacing it with a unique identifier. The input is the unanonymized data collected in step 1, and the output is anonymized data with privacy protection. Specifically, this involves deleting personal information from the database and masking identifying information.

[0682] Step 3:

[0683] The server trains a generative AI model using anonymized data. The anonymized data obtained in step 2 is used as input. The server uses commercially available or custom-developed AI software to analyze user home patterns from data such as day of the week, time, and regional characteristics. The output is a prediction of the time periods when each user is most likely to be at home. Specifically, the AI ​​applies machine learning algorithms to identify patterns based on the user's past behavior history.

[0684] Step 4:

[0685] The server generates an optimal delivery plan based on the output of the AI ​​model. This plan is optimized to schedule deliveries at times when users are most likely to be at home. The input is the predicted time spent at home obtained in step 3. The output is the detailed delivery route and schedule to be given to the driver. The server calculates the shortest path based on the algorithm and determines an efficient delivery order.

[0686] Step 5:

[0687] The terminal receives the delivery plan sent from the server and presents it to the driver in real time. The driver can check the next delivery destination and route information through this terminal. The input is the delivery plan data generated from the server in step 4, and the output is a visual map and schedule displayed on the terminal screen. The driver uses this to carry out deliveries.

[0688] Step 6:

[0689] After delivery, the terminal reports the delivery results to the server. The input is delivery result data entered by the driver, including status such as success or absence. The server receives this feedback data, adds it to the database, and uses it to continuously improve the generated AI model. The output is the next prediction with improved model accuracy. This further improves the accuracy of the next delivery plan.

[0690] (Application Example 1)

[0691] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0692] In modern delivery services, efficient delivery is essential, but the increase in redeliveries due to attempts to deliver during times when customers are absent is a significant challenge that leads to wasted time and resources. Furthermore, to optimize deliveries to multiple customers, it is essential to analyze various data in real time and calculate the optimal route and time. In addition, a system for continuously improving delivery accuracy is required.

[0693] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0694] In this invention, the server includes means for collecting past delivery information, user activity schedule information, regional characteristics information, and electronic activity history; means for anonymizing the collected information; and means for training a generation AI model based on the anonymized information to predict the time when the user is most likely to arrive. This makes it possible to formulate an efficient delivery plan and reduce the risk of redelivery. Furthermore, the system can receive feedback on delivery results and continuously improve delivery accuracy, thereby enhancing the overall service quality.

[0695] "Delivery information" refers to data related to past deliveries, including information such as the date and time, delivery destination, and delivery result.

[0696] "User activity plan information" refers to the user's plans and schedules for using the service, and is provided through partner apps and online platforms.

[0697] "Regional characteristic information" refers to information about the unique characteristics of a region, collected from public institutions and local services, and includes things like traffic conditions and weather conditions.

[0698] "Electronic activity history" refers to the history of activities performed by users in the digital environment, and is information that is useful for optimizing services.

[0699] "Anonymization" is a processing technique that removes personally identifiable information to protect privacy.

[0700] A "generative AI model" is an artificial intelligence algorithm that learns from collected data and makes specific predictions or classifications.

[0701] A "delivery plan" is a delivery schedule based on the predicted arrival time of the user, and includes efficient delivery routes.

[0702] "Information equipment" refers to electronic devices that allow drivers and users to receive information in real time.

[0703] A "recording medium" is a storage device used to store data and for system learning and improvement.

[0704] This system requires the application of multiple hardware and software components to enable the efficient planning and execution of delivery schedules.

[0705] First, the server collects past delivery information, user activity schedules, regional characteristics, and electronic activity history. This information is anonymized after collection to protect privacy. For this purpose, the server uses a data anonymization library (e.g., PySyft).

[0706] Based on anonymized information, the server trains a generative AI model to predict the most likely times for users to arrive. This process utilizes machine learning libraries such as TensorFlow and PyTorch. The model performs predictive calculations that take into account time, weekday, and regional characteristics.

[0707] Next, the server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. This information device is a smartphone or other electronic device that receives the optimized route and delivery schedule in real time. This process reduces the risk of redelivery and increases delivery efficiency.

[0708] After delivery is complete, the terminal feeds the delivery results back to the server. Based on this feedback, the server adds data to the storage medium and improves the accuracy of the generated AI model. This cycle promotes continuous improvement of service quality.

[0709] For example, suppose a user enters their schedule into a partner app. Based on this information and past data, the server predicts with high accuracy when the user will be at home and delivers this information to the driver in real time. The system may use prompts such as: "Analyze the user's order history for the past 6 months and predict the optimal delivery time."

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The server collects delivery information, user activity schedule information, regional characteristics information, and electronic activity history. Inputs include a historical delivery database, user schedule input, and regional public data sources. The output is an initial, unanonymized dataset. This dataset is then anonymized through the following process.

[0713] Step 2:

[0714] The server anonymizes the collected information. In this process, the server uses a data anonymization library (e.g., PySyft). The unanonymized dataset obtained in step 1 is used as input, and a privacy-protected anonymized dataset is generated as output. The anonymized data is then provided to the generative AI model as training data.

[0715] Step 3:

[0716] The server trains a generative AI model based on anonymized data. The anonymized dataset obtained in step 2 is used as input. TensorFlow or PyTorch is used for the generative AI model, and a prediction algorithm that takes into account time, day of the week, and regional characteristics predicts the arrival time of users. The output is the optimal predicted arrival time for each user, which is useful for integrated delivery planning.

[0717] Step 4:

[0718] The server generates an integrated delivery plan based on the predicted arrival time of the user and distributes it to the information device. The input is the predicted arrival time of the user obtained in step 3. This information is transmitted to information devices such as smartphones and tablets via a real-time delivery algorithm for the device. The output is an optimized delivery route and schedule for each driver.

[0719] Step 5:

[0720] Once a delivery is complete, the terminal feeds the delivery results back to the server. The input used is delivery performance information from the terminal (success, failure, time delay, etc.). The server saves this feedback to a storage medium and uses it as data for the next training cycle. The output is an updated dataset for improving model accuracy.

[0721] Through these steps, servers, terminals, and users can work together to improve the accuracy and efficiency of deliveries.

[0722] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0723] This invention is a system that combines AI technology and emotion recognition capabilities with the aim of improving delivery efficiency and customer satisfaction in home delivery services. This system not only uses data collection and generation AI models for prediction, but also utilizes an emotion engine to analyze user emotions and optimize delivery schedules based on those emotions.

[0724] Data collection and anonymization

[0725] First, the server collects past delivery data, customer schedule information, regional characteristics information, and digital activity history. This data is anonymized and cannot be used to identify individuals.

[0726] Utilizing the Emotion Engine

[0727] The server inputs the collected digital activity history into an emotion engine to analyze the user's emotional state. This emotion engine analyzes social media posts, messaging app interactions, and other data to detect changes in emotions.

[0728] Prediction using generative AI models

[0729] Taking sentiment analysis into account, the server uses a generative AI model to predict when users are most likely to be at home. This prediction is integrated with the user's schedule and local characteristics information to create an optimal delivery schedule.

[0730] Generating and adjusting delivery schedules

[0731] The server generates a delivery schedule that reflects the emotional state of the customer and delivers it to the terminal. The driver then carries out deliveries based on this optimized schedule.

[0732] example

[0733] For example, if a user is feeling stressed online, the emotion engine detects this state and, out of consideration, predicts a time when they are more likely to relax. Based on this, the server sets the delivery time to suit the user's comfort level and notifies the driver via the terminal.

[0734] Feedback and continuous improvement

[0735] After delivery is complete, the device sends the results and feedback to the server. This feedback data is used to further improve the accuracy of the generative AI model and emotion engine.

[0736] In this way, by introducing an emotion engine, this system aims to improve delivery efficiency and customer satisfaction by providing a more detailed delivery service that takes into account the user's emotional state.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] The server collects historical delivery data, customer schedule information, regional characteristics information, and digital activity history from multiple data sources. During this collection phase, the data is immediately anonymized to protect privacy and make it impossible to identify individuals.

[0740] Step 2:

[0741] The server inputs anonymized digital activity history into the emotion engine to analyze the user's emotional state. The emotion engine has the ability to identify emotions such as positive, negative, and neutral from the user's text data and online activity patterns.

[0742] Step 3:

[0743] The server integrates the results of the emotion engine with other collected data and includes them in the generative AI model's dataset. The generative AI model then learns from this integrated data to predict the times when each customer is most likely to be at home. This prediction takes into account the user's emotional state, in addition to time of day, day of the week, regional characteristics, and schedule information.

[0744] Step 4:

[0745] The server creates an optimal delivery schedule based on predictions of when customers will be home, calculated by a generative AI model. This schedule is optimized by referencing data from multiple customers and is designed to allow drivers to work at their most efficient pace.

[0746] Step 5:

[0747] The terminal receives the optimal delivery schedule sent from the server and notifies the driver in real time. The driver plans the route for deliveries based on this schedule and travels according to the instructions.

[0748] Step 6:

[0749] The user (driver) performs the scheduled delivery and reports feedback on the delivery completion and results to the server via a terminal. This feedback includes information such as delivery success, details of missed deliveries, and user reactions.

[0750] Step 7:

[0751] The server receives feedback from drivers and uses it for subsequent data analysis. Based on this feedback, the accuracy of the generative AI model and emotion engine is further enhanced, improving the accuracy of future delivery plans.

[0752] (Example 2)

[0753] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] In home delivery services, achieving both improved delivery efficiency and customer satisfaction simultaneously is not easy. Accurately predicting customer availability and creating efficient delivery schedules is necessary, but conventional methods have struggled to make highly accurate predictions that take emotional states into account. This invention aims to solve this problem and enable more flexible and customer-centric delivery.

[0755] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0756] In this invention, the server includes means for aggregating past delivery history, customer schedule information, regional characteristic information, and electronic activity records; means for modifying the aggregated information so that personal information cannot be identified; means for predicting times when the user is most likely to be at home using a generative AI model based on the modified information; means for adjusting the delivery time and transmitting an optimized delivery plan to the terminal using emotional intelligence that analyzes the user's emotional state; and means for adding the results received after the delivery to the information storage device in order to improve the accuracy of the generative AI model and emotional intelligence. This significantly improves delivery efficiency and enables the provision of flexible delivery services that take customer comfort into consideration.

[0757] "Past delivery history" refers to records of deliveries made in the past, including data such as the date, time, location, and destination.

[0758] "Customer schedule information" refers to information including schedules and activity plans that customers have registered in advance.

[0759] "Regional characteristic information" refers to information that shows geographical, demographic, and traffic conditions specific to the delivery area.

[0760] "Electronic activity records" refer to data that shows a customer's actions and communication history on their digital devices.

[0761] "Modifying data so that personal information cannot be identified" refers to technical measures that anonymize data by removing or encrypting personally identifiable elements.

[0762] A "generative AI model" is a type of machine learning algorithm created to perform specific tasks using artificial intelligence techniques.

[0763] "The time when users are most likely to be at home" refers to the time period predicted by the AI ​​model as having the highest probability of customers being at home.

[0764] "Emotional intelligence" refers to the technology or function of mechanically analyzing a person's emotional state and using that analysis to select appropriate judgments and actions.

[0765] An "optimized delivery plan" is a schedule designed to be executed effectively and efficiently, taking into account delivery efficiency and customer preferences to the fullest extent.

[0766] An "information storage device" refers to a physical or virtual facility or system for recording and storing data.

[0767] This invention is a system aimed at improving efficiency and customer satisfaction in delivery services. At the heart of the system are a generative AI model and emotional intelligence, which operate on a server.

[0768] The server first aggregates past delivery history, customer schedule information, regional characteristics, and electronic activity records. APIs and database connection technologies are used for data collection, and encryption algorithms are applied to securely anonymize this data. Next, a generative AI model is used based on the collected data to predict the times when customers are most likely to be at home. Here, a representative machine learning algorithm is used, and the AI ​​model is instructed with prompts such as, "Predict the optimal delivery time while considering the user's emotional state."

[0769] Furthermore, the emotional intelligence analyzes the user's electronic activity log and determines their emotional state based on social media posts and messaging app content. This analysis utilizes an API equipped with natural language processing technology. The server comprehensively considers the predicted time spent at home and the emotional state to generate an optimal delivery schedule and send it to the device.

[0770] The terminal notifies the driver of the delivery schedule received from the server. Specifically, an application running on the mobile device is used to show the driver the optimal delivery route and time.

[0771] For example, if a user's online activity reveals signs of stress, the server analyzes this information and schedules delivery for a time when the user can relax. In this way, the implementation of this invention makes it possible to provide a detailed service that takes into account the individual user's state.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The server collects past delivery history, customer schedule information, regional characteristics information, and electronic activity records. It retrieves information from various APIs and databases as input and integrates it as digital data. As output, the collected data is stored after anonymization algorithms have been applied.

[0775] Step 2:

[0776] The server trains a generative AI model using anonymized data. It receives a prompt message, "Predict the optimal delivery time while considering the user's emotional state," and the AI ​​model predicts the time slots when the user is most likely to be at home. As a result, predicted time slots are extracted.

[0777] Step 3:

[0778] The server provides electronic activity logs to emotional intelligence to analyze the user's emotional state. As input, it analyzes social media posts and messaging app history, and uses natural language processing techniques to detect changes in emotion. As output, it estimates the user's current emotional state.

[0779] Step 4:

[0780] The server integrates predicted time spent at home and emotional state to generate an optimal delivery schedule. The input uses the data obtained in steps 2 and 3. Specifically, the generated schedule is optimized by a time management algorithm. The output is a specific delivery schedule for the driver.

[0781] Step 5:

[0782] The terminal receives an optimized delivery schedule sent from the server and notifies the driver. It receives the generated schedule data as input and provides visual instructions on the mobile device. As output, the driver receives real-time route and time information.

[0783] Step 6:

[0784] The terminal sends feedback to the server after delivery is complete. The input includes delivery results and driver comments, which are added to the server's database. As output, the feedback is used to further improve the accuracy of generative AI models and emotional intelligence.

[0785] (Application Example 2)

[0786] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] Current delivery services create delivery schedules that only consider the user's location, without taking into account the user's emotional state. This leads to problems such as deliveries occurring under stressful circumstances and service that doesn't suit the user's feelings. Furthermore, achieving both efficient delivery routes and emotionally responsive service simultaneously is difficult, posing a challenge to improving customer satisfaction.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0789] In this invention, the server includes means for acquiring past delivery-related information, user schedule information, regional characteristics information, and digital behavior history; means for training a generative artificial intelligence model based on anonymized information to estimate the times when the user is most likely to be present; and means for integrating an emotion recognition function for analyzing the user's emotional state. This makes it possible to provide an optimal delivery schedule and service that takes into account the user's location and emotional state.

[0790] "Past delivery-related information" refers to all data related to past deliveries, including information such as delivery date and time, delivery destination, and positive feedback.

[0791] "User schedule information" refers to information about activities and schedules that the user has set or anticipates, including, for example, appointments and public holiday information in calendar applications.

[0792] "Regional characteristics information" refers to data about the characteristics of a specific region, including elements unique to that region, such as climate conditions, traffic conditions, and local events.

[0793] "Digital behavioral history" refers to data based on a user's online behavior, including, for example, statements made on social media and internet usage history.

[0794] A "generative artificial intelligence model" is a statistical model that uses AI technology to learn from collected data and make specific predictions or classifications.

[0795] "User location probability" is a concept that predicts the probability that a user is in a certain location during a specific time period.

[0796] "Emotion recognition functionality" refers to technology that analyzes a user's digital behavior history to identify their emotions at any given time.

[0797] An "optimal delivery schedule" is a delivery plan designed to maximize delivery efficiency and customer satisfaction, taking into account the user's location, emotions, and regional characteristics.

[0798] An "information terminal" refers to a device used to receive delivery schedules and other information, such as a smartphone or tablet.

[0799] An "information recording device" is a system or device for storing data over a long period of time. Examples include cloud-based data storage services.

[0800] The server acquires past delivery-related information, user schedule information, regional characteristics information, and digital behavior history. This information is collected through applications on the user's smartphone or tablet and anonymized to protect privacy. In this process, the aforementioned information is analyzed on a keyword basis and converted into a format that does not identify individual users. The anonymized data is securely stored in an information recording device, for example, on a cloud service. This stored information is used as foundational data to train a generative artificial intelligence model. This AI model is used to predict the user's location and emotional state, with its emotion recognition function analyzing statements from social media and messaging apps.

[0801] The generative artificial intelligence model utilizes technologies like OpenAI to determine when users are most relaxed, taking into account time, regional characteristics, and effective emotional indicators. Based on these predictions, the server generates an optimal delivery schedule, adjusting it to reflect the user's emotional state. This information is delivered to drivers in real time, enabling efficient and satisfying deliveries.

[0802] For example, if the server detects data indicating a user is experiencing stress during an online meeting using its emotion recognition function, it will identify a relaxing time in the evening and adjust the food delivery accordingly. The user receives this information via their smartphone and is offered a suitable menu (e.g., a herbal tea set).

[0803] An example of a prompt to input into the generating AI model is, "User A has recently been posting stressful comments on social media. At what time of day should we schedule a food delivery so that he can relax the most?" In this way, the entire service can comprehensively consider the user's location and emotions, enabling it to provide a highly satisfying delivery experience.

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0805] Step 1:

[0806] The server collects past delivery-related information, user schedule information, regional characteristics information, and digital behavior history from users' smartphones and tablets. The input comes from the user's device, and this input data is stored in the database after an anonymization process. As part of the data processing, identifiers are removed and information is aggregated so that individual users cannot be identified.

[0807] Step 2:

[0808] The server uses anonymized data to train a pre-developed generative AI model. The input consists of anonymized delivery-related information and user behavior history. By inputting this into the model, a predictive algorithm is built to infer the user's likely location and emotional state. Statistical analysis and machine learning techniques are used for data computation to obtain the output.

[0809] Step 3:

[0810] The server integrates emotion recognition capabilities to analyze users' emotional states from their social media and messaging app posts. The input is text data from online platforms, which is then converted into numerical or categorical data corresponding to emotions using emotion analysis algorithms. This makes it possible to identify states where users are feeling stressed or relaxed.

[0811] Step 4:

[0812] The server creates the optimal delivery schedule for the user based on the results of the generative AI model and emotion recognition. The input is the output data from steps 2 and 3, which are integrated to determine the time when the user is at home and relaxed, thereby setting the delivery time.

[0813] Step 5:

[0814] The server delivers optimized delivery schedules to the delivery drivers' terminals. The input is the generated delivery schedule data, and the output is a real-time updated delivery plan sent to the drivers. This enables efficient deliveries.

[0815] Step 6:

[0816] Users provide feedback after delivery is complete, which the server receives to improve the accuracy of the generative artificial intelligence model and emotion recognition function. The input is user evaluation information, and this data is used to update the parameters of the AI ​​model. As part of the data calculation, model evaluation metrics and performance metrics are recalculated and used to plan future deliveries.

[0817] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0818] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0819] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0820] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0821] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0822] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0823] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0824] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0825] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0826] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0827] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0828] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0829] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0830] 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.

[0831] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0832] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0833] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0834] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0835] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0836] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0837] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] Means for collecting past delivery data, customer schedule information, regional characteristics information, and digital activity history,

[0841] A means for anonymizing the aforementioned collected data,

[0842] A method for training a generative AI model based on anonymized data to predict the times when customers are most likely to be at home,

[0843] A means of generating and delivering an optimal delivery schedule to a terminal based on the predicted time when the customer will be at home,

[0844] A means for receiving feedback on delivery results and adding it to a database to improve the accuracy of the generated AI model,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, characterized in that the delivery schedule is optimized based on data from multiple customers and also includes an efficient delivery route.

[0848] (Claim 3)

[0849] The system according to claim 1, characterized in that the generating AI model uses a prediction algorithm that takes into account the characteristics of time, day of the week, and region.

[0850] "Example 1"

[0851] (Claim 1)

[0852] Means for collecting past delivery information, user schedule information, regional characteristic information, and communication activity history,

[0853] A means for anonymizing the collected information,

[0854] A method for training an inference AI model based on anonymized information to predict the times when users are most likely to be at home,

[0855] A means for generating an optimal delivery plan based on the predicted time when users will be at home and distributing it to their information terminals,

[0856] A means for receiving feedback on delivery results and adding it to the data storage means in order to improve the accuracy of the inference AI model,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, characterized in that the delivery plan is optimized based on information from multiple users and also includes an efficient delivery route.

[0860] (Claim 3)

[0861] The system according to claim 1, characterized in that the inference AI model uses a prediction algorithm that takes into account the characteristics of time, day of the week, and region.

[0862] "Application Example 1"

[0863] (Claim 1)

[0864] A means of collecting past delivery information, user activity schedule information, regional characteristics information, and electronic activity history,

[0865] A means for anonymizing the collected information,

[0866] A method for training a generative AI model based on anonymized information to predict the time when a user is most likely to arrive,

[0867] A means for generating an integrated delivery plan based on the predicted arrival time of users and distributing it to information devices,

[0868] A means for receiving feedback on the delivery results and adding it to a recording medium to improve the accuracy of the generated AI model,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, characterized in that the delivery plan is improved based on information from multiple users and also includes a reasonable delivery route.

[0872] (Claim 3)

[0873] The system according to claim 1, characterized in that the generating AI model uses predictive calculations that take into account the characteristics of time, weekday, and region.

[0874] "Example 2 of combining an emotion engine"

[0875] (Claim 1)

[0876] A means of aggregating past delivery history, customer schedule information, regional characteristic information, and electronic activity records,

[0877] A means of modifying the aggregated information so that personal information cannot be identified,

[0878] A method for predicting the times when users are most likely to be at home, using a generated AI model based on changed information.

[0879] A means of using emotional intelligence to analyze the user's emotional state, adjusting delivery times, and transmitting an optimized delivery plan to the terminal,

[0880] Means to be added to the information storage device in order to improve the accuracy of the generative AI model and emotional intelligence using evaluation of the results received after the delivery is carried out,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, characterized in that the delivery plan is improved based on information from multiple users and also includes an efficient delivery route.

[0884] (Claim 3)

[0885] The system according to claim 1, characterized in that the generating AI model uses a predictive algorithm that takes into account the characteristics of time, day of the week, and region, and includes the results of sentiment analysis.

[0886] "Application example 2 when combining with an emotional engine"

[0887] (Claim 1)

[0888] Means for obtaining past delivery-related information, user schedule information, regional characteristics information, and digital behavior history,

[0889] A means for anonymizing the acquired information,

[0890] A means of training a generative artificial intelligence model based on anonymized information to estimate the time when a user is most likely to be located,

[0891] A means of integrating an emotion recognition function to analyze the emotional state of the user,

[0892] A means for generating an optimal delivery schedule based on the estimated time of location and emotional state, and transmitting it to an information terminal,

[0893] Means for receiving an evaluation of the delivery results and adding them to the information recording device in order to improve the accuracy of the generative artificial intelligence model and emotion recognition function,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, characterized in that the delivery schedule is optimized based on information from multiple users and includes efficient delivery routes and menu suggestions tailored to the user's mood.

[0897] (Claim 3)

[0898] The system according to claim 1, characterized in that the generating artificial intelligence model uses a prediction algorithm that takes into account the characteristics of time, calendar day, and region, as well as changes in the user's emotions. [Explanation of Symbols]

[0899] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting past delivery data, customer schedule information, regional characteristics information, and digital activity history, A means for anonymizing the aforementioned collected data, A method for training a generative AI model based on anonymized data to predict the times when customers are most likely to be at home, A means of generating and delivering an optimal delivery schedule to a terminal based on the predicted time when the customer will be at home, A means for receiving feedback on delivery results and adding it to a database to improve the accuracy of the generated AI model, A system that includes this.

2. The system according to claim 1, characterized in that the delivery schedule is optimized based on data from multiple customers and also includes an efficient delivery route.

3. The system according to claim 1, characterized in that the generating AI model uses a prediction algorithm that takes into account the characteristics of time, day of the week, and region.

Images