System

Abstract

A system is provided.SOLUTION: A system includes a means for collecting and analyzing disaster information acquired when a natural disaster occurs, a means for associating a deliverable area code with a postal code, a means for determining whether delivery is possible on the basis of the collected disaster information, and a means for notifying a customer of information on whether the delivery is possible.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The present invention aims to improve customer satisfaction by providing a system that enables mail-order businesses to quickly and accurately provide customers with information on whether or not delivery is possible when a natural disaster occurs. Conventional systems have had problems with delays in obtaining delivery information and notifying customers when a natural disaster occurs, causing inconvenience to customers. Furthermore, there have been issues with the efficiency of collecting and analyzing disaster information, which often leads to delays in determining whether or not delivery is possible. The present invention aims to solve these problems. [Means for solving the problem]

[0005] This invention provides a system that includes a means for collecting and analyzing disaster information obtained when a natural disaster occurs, a means for linking delivery area codes with postal codes, a means for determining whether delivery is possible based on the collected disaster information, and a means for notifying customers of the delivery possibility information. Specifically, the system is configured to include a means for collecting and analyzing disaster information from public and private data sources, and to generate and notify affected customers based on delivery area information linked to customer order history. This enables prompt and accurate provision of information to customers and delivery management even when a disaster occurs.

[0006] "Natural disasters" are unpredictable natural phenomena caused by natural disasters such as earthquakes, typhoons, heavy rains, floods, and tsunamis.

[0007] "Disaster information" refers to data and reports on the occurrence of natural disasters, the extent of their impact, and the extent of the damage.

[0008] A "delivery area code" is an identification code assigned to a specific region or area and is used to manage product delivery.

[0009] "Postal Code" means a set of numbers used to identify a mail delivery area.

[0010] "Generative AI" is a system that uses artificial intelligence technology to collect and analyze data and generate new information and judgments.

[0011] "Means of collection and analysis" refers to the technology and equipment used to obtain the necessary data, analyze its contents, and extract useful information.

[0012] "Delivery possibility" is a judgment indicating whether or not the product can be delivered to the specified area or address.

[0013] "Means of notification" refers to means for transmitting specific information to a designated person, and includes email, chat, fax, etc.

[0014] "Customer" refers to a consumer or corporation that purchases a product from a mail-order business and requests its delivery. [Brief explanation of the drawings]

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

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

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

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

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

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

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

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

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

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0036] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0037] System Configuration

[0038] The present invention comprises the following main components:

[0039] 1. Disaster information collection and analysis methods

[0040] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0041] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[0042] 2. Delivery area code linking method

[0043] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0044] This allows for clear management of which delivery area code a particular postal code falls under.

[0045] 3. Means of determining delivery availability

[0046] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[0047] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0048] 4. Customer Notification Means

[0049] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0050] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0051] Program processing

[0052] 1. Disaster information collection and analysis

[0053] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[0054] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[0055] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered damage from heavy rain."

[0056] 2. Linking delivery area codes

[0057] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[0058] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[0059] 3. Determining whether delivery is possible

[0060] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[0061] For example, "Postal code 123-4567 will be marked as undeliverable."

[0062] 4. Notice to Customer

[0063] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[0064] Notify each customer by email, etc. For example, "Send a delivery delay notification to customer A by email."

[0065] Specific examples

[0066] Disaster information collection and analysis

[0067] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0068] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0069] Linking delivery area codes

[0070] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0071] Judgment on delivery availability

[0072] The server flags "123-4567" as undeliverable.

[0073] customer notification

[0074] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0075] This system will enable mail-order businesses to respond to customers quickly and accurately even during natural disasters, improving customer satisfaction and streamlining logistics.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[0079] Step 2:

[0080] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[0081] Step 3:

[0082] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[0083] Step 4:

[0084] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[0085] Step 5:

[0086] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[0087] Step 6:

[0088] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[0089] Step 7:

[0090] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[0091] Step 8:

[0092] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[0093] Step 9:

[0094] The server checks whether the notification was sent successfully and determines whether it needs to be sent again. If the notification is not received, it will try to notify the customer by other means (e.g., SMS, phone call) to improve the accuracy of customer support.

[0095] In this way, the system of the present invention, through a series of processing steps, enables quick and accurate response to customers even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[0096] Example 1

[0097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0098] When a natural disaster occurs, it is difficult for mail order businesses to quickly and accurately provide customers with information about whether or not their deliveries will be successful. In particular, when the disaster has a wide impact, it is difficult to immediately assess the situation in each region and provide appropriate notifications. As a result, customers often become dissatisfied because they are unable to properly grasp information about delivery delays or cancellations.

[0099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0100] In this invention, the server includes means for collecting disaster information from public and private data sources, means for analyzing the collected disaster information using a generative AI model, means for linking delivery area codes with multiple postal codes, means for generating a list of affected postal codes based on the analyzed disaster information and determining whether delivery is possible for each delivery area code, and means for generating a list of affected customers based on delivery area information linked to customer order history and notifying them by means of email, chat, etc. This enables mail-order businesses to quickly and accurately provide customers with delivery possibility information even during natural disasters.

[0101] "Official data sources" are official sources of information provided by government agencies or local governments.

[0102] "Private data sources" are information sources provided by private organizations and individuals, such as news media and social media.

[0103] "Disaster information" refers to specific data and reports on natural disasters, such as the extent of damage, the extent of impact, and the location of the disaster.

[0104] A "generative AI model" is an artificial intelligence model that is trained using machine learning to perform a specific task.

[0105] "Analysis" is the process of identifying the scale and scope of a disaster based on collected data.

[0106] A "delivery area code" is a code that indicates a certain area and is used to determine whether delivery is possible within that area.

[0107] "Postal Codes" are a series of numbers used to designate a particular area and are utilized to uniquely identify multiple areas.

[0108] A "delivery area code" is a code that identifies a delivery area and includes multiple postal codes.

[0109] "Delivery availability" is a status indicating whether delivery is possible to a specific area.

[0110] "Customer" means a person who purchases goods or services.

[0111] "Order History" refers to a record of past orders placed by a customer.

[0112] "Delivery area information" is information relating to the area to be delivered.

[0113] The "list of affected customers" is a list of customers whose deliveries may be affected, identified based on disaster information.

[0114] "Notification" is the act of informing someone of information, and is done via email, chat, etc.

[0115] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that uses AI technology to provide customers with fast and accurate information on whether delivery is possible. This system has a multi-functional configuration that collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0116] 1. Collecting disaster information

[0117] The server collects disaster information from public and private data sources. To do this, it uses the Japan Meteorological Agency's API, SNS API, and news API. Specifically, the server accesses these APIs every hour and runs a regular job to obtain the latest disaster data. This information is used as basic data for quickly understanding the disaster situation.

[0118] 2. Disaster Information Analysis

[0119] The server uses the generative AI model to analyze the acquired disaster data. This analysis makes it possible to identify the scale of the disaster, the extent of the impact, and the affected areas. Specifically, the server creates a prompt for the generative AI model, inputs it into the AI ​​model, and obtains the analysis results. For example, "The server analyzes the information acquired by the generative AI and identifies that Shinagawa Ward and surrounding areas in Tokyo are affected by heavy rain."

[0120] 3. Linking delivery area codes

[0121] The server checks the databases provided by the mail-order business and the delivery company. It links each postal code with a corresponding delivery area code, and this is how delivery areas are managed. Specifically, the server periodically performs a database join operation to obtain the latest delivery area information. For example, "The server links Shinagawa Ward (postal code 123-4567) to the area code for Tokyo's 23 wards."

[0122] 4. Delivery Determination

[0123] The server generates a list of affected postal codes based on the disaster information analyzed by the AI. Based on this list, it sets a flag for delivery suspension or delay for each delivery area code. For example, "The server sets a flag for delivery ineligible for the area with postal codes 123-4567." Specifically, the server loops through the postal code list and sets a delivery flag for each postal code.

[0124] 5. Notice to Customer

[0125] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer of delivery delays or cancellations using methods such as email, personal pages, and chat. For example, the server might "send an email to customer A notifying them of a delivery delay." Specifically, the server uses an email sending API to automatically send an email with the specified content.

[0126] Examples:

[0127] Disaster information collection:

[0128] The server accesses the Japan Meteorological Agency API at 9:00 a.m. and obtains information about the heavy rain disaster in Shinagawa Ward, Tokyo.

[0129] Disaster information analysis:

[0130] The server inputs the acquired heavy rain information into the generation AI, which analyzes and determines that all postal codes in Shinagawa Ward are affected.

[0131] Delivery Area Code Linking:

[0132] The server recognizes Shinagawa Ward (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0133] Delivery availability:

[0134] The server flags "123-4567" as undeliverable.

[0135] Customer Notice:

[0136] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0137] Example prompt sentence:

[0138] "Please collect the latest disaster information. Use the Japan Meteorological Agency API, news API, and SNS API to obtain disaster information affecting the 23 wards of Tokyo, and analyze it to identify which areas are affected."

[0139] This will enable the system to respond quickly and accurately even in the event of a natural disaster, contributing to improved customer satisfaction and more efficient logistics.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] Disaster information collection:

[0143] The server collects the latest disaster information from public data sources (such as the Japan Meteorological Agency API) and private data sources (such as news APIs and SNS APIs). It uses the API endpoints and necessary authentication information as input, and obtains the latest disaster information data as output. Specifically, the server runs a periodic job that accesses these APIs every hour and retrieves the latest disaster data in JSON format.

[0144] Step 2:

[0145] Disaster information analysis:

[0146] The disaster information acquired by the server is input into a generative AI model, which then obtains the analysis results. This generative AI model uses natural language processing technology to identify the scale, extent of impact, and affected areas of the disaster. As input, the acquired disaster information data is converted into prompt statements, which are then input into the generative AI model. As output, the affected areas of the disaster and detailed information about them are obtained. For example, it generates information such as "Shinagawa Ward, Tokyo, has suffered damage from heavy rain."

[0147] Step 3:

[0148] Delivery Area Code Linking:

[0149] The server retrieves the postal code database provided by the mail-order business and the delivery area information provided by the delivery company, and associates each postal code with a corresponding delivery area code. Both databases are used as input, and a list of correspondences between postal codes and delivery area codes is generated as output. Specifically, the server compares these databases using a join operation and periodically updates the latest delivery area information.

[0150] Step 4:

[0151] Delivery availability:

[0152] The server generates a list of affected postal codes based on the disaster information analyzed by the AI ​​model. It uses the delivery area code associated with the disaster information from the analysis as input, and generates a list of postal codes flagged as undeliverable or delayed as output. Specifically, the server loops through the list of affected postal codes and flags each one as undeliverable or deferred.

[0153] Step 5:

[0154] Customer Notice:

[0155] The server checks customer order history and generates a list of customers requesting delivery in the affected areas. It uses customer order history data and a list of affected postal codes as input. It generates a list of customers with information to notify of delivery delays or cancellations as output. Specifically, the server automatically sends delivery delay notifications to each customer using an email sending API or chat notification function.

[0156] This will enable the system to respond quickly and accurately even in the event of a natural disaster, improving customer satisfaction and streamlining logistics.

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] In recent years, the frequent occurrence of natural disasters has increasingly had a major impact on mail-order logistics. This has created a need for fast and accurate notification of delivery status to customers. However, conventional systems are unable to quickly collect and analyze disaster information or determine whether or not delivery can be made, which can lead to a decline in customer satisfaction. Furthermore, the resulting delays and cancellations of logistics are a major issue for businesses. To solve these issues, a system is needed that can efficiently collect and analyze disaster information and quickly notify customers.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes means for collecting and analyzing disaster information acquired when a natural disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, and means for sending push notifications to customers via a smartphone application. This makes it possible to notify customers of delivery status quickly and accurately even when a disaster occurs, thereby improving customer satisfaction and streamlining logistics.

[0162] "Natural disaster information" refers to information about disasters collected from disaster reports by the Japan Meteorological Agency and local governments, social media, breaking news, etc.

[0163] "Means of collection and analysis" refers to the system by which data is acquired using a server or related technology, and then analyzed to create usable information.

[0164] A "delivery area code" is a code that indicates whether an item can be delivered to a specific area or postal code.

[0165] A "postal code" is a code consisting of a series of numbers that identifies an area or address.

[0166] The "means for determining whether delivery is possible" is a mechanism that determines whether delivery of goods to a specific area is possible based on collected disaster information.

[0167] "Means of notification" refers to a system for communicating information such as delivery delays or cancellations to customers.

[0168] A "smartphone application" is software that is installed on a smartphone and enables the user to use certain functions.

[0169] "Push notifications" are real-time messages or notifications sent from an application directly to a user's smartphone.

[0170] A "server" is a computer that provides services to other computers and devices on a network.

[0171] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0172] System Configuration

[0173] The system consists of the following main components:

[0174] 1. Disaster information collection and analysis methods

[0175] When a disaster occurs, the server collects information from public data sources (e.g., disaster reports from the Japan Meteorological Agency and local governments) and private data sources (e.g., social media and breaking news). The server uses generative AI to analyze the collected data and obtain detailed information about the affected area.

[0176] 2. Delivery area code linking method

[0177] The server connects the mail-order company's database with the delivery company's database, and associates each postal code with a corresponding delivery area code, thereby clearly managing which delivery area code a specific postal code corresponds to.

[0178] 3. Means of determining delivery availability

[0179] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the AI. For each postal code, it references the delivery area code and determines whether delivery is possible there.

[0180] 4. Customer Notification Means

[0181] The server generates a list of affected customers based on delivery area information linked to the customer's order history, and notifies each customer of delivery delays or cancellations via email, their personal page, chat, or smartphone application.

[0182] Program processing

[0183] 1. Disaster information collection and analysis

[0184] The server collects the latest disaster information using news APIs, social media APIs, and data from the Japan Meteorological Agency. The generation AI analyzes this information and identifies areas that may be affected by the disaster. For example, "The information obtained by the server reveals that local city A has been hit by heavy rain."

[0185] 2. Linking delivery area codes

[0186] The server obtains the delivery area information provided by the delivery company and compares it with its own postal code database. For example, "Regional city A (postal code 123-4567) is linked to the regional area code."

[0187] 3. Determining whether delivery is possible

[0188] The server generates a list of affected zip codes and flags each shipping area code from that list as undeliverable or delayed, for example, "zip codes 123-4567 will be marked as undeliverable."

[0189] 4. Notice to Customer

[0190] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer via email or smartphone application. For example, "Send a delivery delay notification to customer A via a smartphone application."

[0191] Specific examples

[0192] The server obtains information about the heavy rain disaster in Regional City A from the API, and the generation AI analyzes that information and adds all postal codes in Regional City A to the affected list. Furthermore, the server recognizes Regional City A (postal code 123-4567) as a "regional area" from the delivery company's database and flags the corresponding postal code as undeliverable. Finally, the server extracts the customer list for the corresponding postal code and sends a notification to the smartphone app stating, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[0193] Example prompts for generative AI models

[0194] Heavy rain has hit local city A, affecting the area with zip code 123-4567. Delivery may be delayed or canceled. Please promptly notify customers in the affected area via email and push notifications.

[0195] With these configurations, this system is able to quickly and accurately notify customers of delivery status even in the event of a disaster, thereby improving customer satisfaction and streamlining logistics.

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] The server collects disaster information. The server obtains disaster information from public data sources (e.g., the Japan Meteorological Agency, local government disaster reports) and private data sources (e.g., SNS APIs, news APIs). This information includes details such as the type of disaster, the location of the disaster, and the extent of the impact. The input is disaster information from each API, and the output is disaster data that is centrally managed within the server.

[0199] Step 2:

[0200] The disaster information collected by the server is analyzed using a generative AI model. The generative AI model analyzes the collected information and identifies areas that may be affected. Specifically, it uses natural language processing and machine learning algorithms to process text data and generate a list of affected postal codes. The input is the disaster information from Step 1, and the output is the list of affected postal codes.

[0201] Step 3:

[0202] The server links the generated list of postal codes to existing delivery area codes. The server references a database linked to delivery companies to determine which delivery area code corresponds to each postal code. This process determines which delivery area a specific region falls into. The input is the list of postal codes from step 2, and the output is a list of delivery area codes linked to each postal code.

[0203] Step 4:

[0204] The server determines whether delivery is possible. Based on the delivery area code obtained in step 3, the server references the collected and analyzed disaster information to determine whether delivery to that area is possible. A flag is set for each area code to indicate whether delivery will be delayed or canceled. The input is the delivery area code from step 3 and the disaster information from step 2, and the output is a list of area codes with delivery possibility flags.

[0205] Step 5:

[0206] The server checks the customer's order history. The server extracts delivery area information for each customer from the customer database and generates a list of customers who belong to the affected area. Specifically, it extracts and lists the order histories of customers who belong to the affected postal codes. The input is the customer database and the delivery availability flag from step 4, and the output is a list of customers to be notified.

[0207] Step 6:

[0208] The server notifies affected customers. Based on the generated customer list, the server sends notifications to each customer via email or smartphone application. The message contains detailed information about the delivery delay or cancellation and recommended action to take. The input is the list of customers to be notified in step 5, and the output is the notification sent to the customer. For example, the server sends a notification via a smartphone app saying, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[0209] Through the above processing steps, customers can be notified of delivery status quickly and accurately even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[0210] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0211] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[0212] System Configuration

[0213] The present invention comprises the following main components:

[0214] 1. Disaster information collection and analysis methods

[0215] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0216] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[0217] 2. Delivery area code linking method

[0218] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0219] This allows for clear management of which delivery area code a particular postal code falls under.

[0220] 3. Means of determining delivery availability

[0221] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[0222] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0223] 4. Customer Notification Means

[0224] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0225] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0226] 5. Emotion Engine

[0227] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[0228] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[0229] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[0230] Program processing

[0231] 1. Disaster information collection and analysis

[0232] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[0233] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[0234] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered flooding damage due to heavy rain."

[0235] 2. Linking delivery area codes

[0236] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[0237] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[0238] 3. Determining whether delivery is possible

[0239] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[0240] For example, "Postal code 123-4567 will be marked as undeliverable."

[0241] 4. Notice to Customer

[0242] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[0243] Notify each customer by email, etc. For example, "Notify customer A by email that delivery of order number ABC123 will be delayed."

[0244] 5. Collecting Emotional Data

[0245] The server collects the user's response to the notification, such as the content of the email reply or the comments on the user's personal page.

[0246] For example, "The server collects reply emails from user B and analyzes their contents."

[0247] 6. Emotional Data Analysis and Response

[0248] The server analyzes the data collected by the emotion engine and evaluates the user's emotional state.

[0249] For example, "The server recognizes from the analysis results that user B is highly dissatisfied."

[0250] Based on the analysis results, the server automatically generates a notification to instruct customer support to take appropriate action, such as "Configure sending of additional follow-up emails to User B, who is very dissatisfied."

[0251] Specific examples

[0252] Disaster information collection and analysis

[0253] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0254] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0255] Linking delivery area codes

[0256] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0257] Judgment on delivery availability

[0258] The server flags "123-4567" as undeliverable.

[0259] customer notification

[0260] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0261] Collecting Emotional Data

[0262] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0263] For example, a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[0264] Customer support coordination

[0265] The server determines that the user is extremely dissatisfied and automatically generates and sends a follow-up email.

[0266] For example, "The server will send an additional follow-up email to the user with an apology."

[0267] In this way, the system of the present invention can respond to customers quickly and accurately even in the event of a disaster, and can also respond while taking into consideration the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[0271] Step 2:

[0272] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[0273] Step 3:

[0274] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[0275] Step 4:

[0276] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[0277] Step 5:

[0278] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[0279] Step 6:

[0280] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[0281] Step 7:

[0282] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[0283] Step 8:

[0284] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[0285] Step 9:

[0286] The server collects emotional data from users who receive notifications. The collected data includes how users reacted to notifications (e.g., the content of reply emails, comments on their personal page, responses in chat, etc.). For example, "User A left a comment on their personal page saying, 'Delays in delivery are a problem.'"

[0287] Step 10:

[0288] The server uses an emotion engine to analyze the collected emotional data and measure the user's level of satisfaction or dissatisfaction. For example, "The server recognizes from User A's comments that User A is very dissatisfied."

[0289] Step 11:

[0290] The server automatically adjusts the content and methods of customer support based on the analysis results, for example, "for highly dissatisfied users, it will automatically generate and send additional follow-up emails or phone calls."

[0291] Step 12:

[0292] The server sends follow-up notifications to the user to improve customer satisfaction. For example, "Send an apology email to User A, and notify customer support if further action is required."

[0293] In this way, the system of the present invention, through a series of processing steps, can respond to customers quickly and accurately even in the event of a natural disaster, and can respond while taking into account the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[0294] Example 2

[0295] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] In conventional mail order systems, it was difficult to provide fast and accurate information on delivery availability in the event of a natural disaster, resulting in problems such as a decline in customer satisfaction and logistics disruptions. Furthermore, there was a lack of consideration for customer feelings, making it difficult to provide appropriate follow-up for dissatisfied customers.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0298] In this invention, the server includes means for collecting and analyzing disaster information acquired when a disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotion data and optimizing customer service, means for analyzing disaster information using a generative AI model, and means for collecting natural disaster information from public and private data sources. This makes it possible to quickly and accurately provide delivery possibility information even when a natural disaster occurs, and to respond in consideration of the emotional state of the customer.

[0299] The "disaster information collection and analysis means" is a device that collects disaster information from public and private data sources when a disaster occurs and analyzes it using a generative AI model.

[0300] A "delivery area code" is a unique code for identifying each delivery area, and is an identifier used to associate with a postal code.

[0301] A "postal code" is a unique number that represents a specific region or area, and is an identifier linked to a delivery area code.

[0302] The "delivery possibility determination means" is a device that determines whether delivery is possible to a specific delivery area or postal code based on the collected and analyzed disaster information.

[0303] The "customer notification means" is a device that notifies the customer of the information on whether delivery is possible or not using an appropriate means (e.g., email, personal page, chat).

[0304] The "emotion data collection and analysis means" is a device that collects the reactions shown by customers to notifications and analyzes their emotional state using an emotion engine.

[0305] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze disaster information and emotional data.

[0306] "Public data sources" are data provided by public institutions such as the Japan Meteorological Agency and local government disaster reports.

[0307] "Private data sources" are data provided by private companies such as social media and breaking news.

[0308] An "emotion engine" is an artificial intelligence system that analyzes the emotional state of customers and is used to optimize customer service.

[0309] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[0310] The present invention comprises the following main components:

[0311] 1. Disaster information collection and analysis methods

[0312] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0313] The server uses a generative AI model to analyze the collected data and obtain detailed information about the affected area.

[0314] 2. Delivery area code linking method

[0315] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0316] This allows for clear management of which delivery area code a particular postal code falls under.

[0317] 3. Means of determining delivery availability

[0318] The server generates a list of postal codes for affected areas based on disaster information analyzed by the generative AI model.

[0319] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0320] 4. Customer Notification Means

[0321] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0322] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0323] 5. Emotion Engine

[0324] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[0325] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[0326] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[0327] Specific examples

[0328] Disaster information collection and analysis

[0329] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0330] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0331] Linking delivery area codes

[0332] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[0333] Judgment on delivery availability

[0334] The server flags Shinagawa-ku (zip code 123-4567) as undeliverable.

[0335] customer notification

[0336] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0337] Collecting Emotional Data

[0338] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0339] For example, suppose that a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[0340] Customer support coordination

[0341] The server determines that the user is very dissatisfied and automatically generates and sends a follow-up email.

[0342] For example, "The server will send an additional follow-up email to the user with an apology."

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] Step 1:

[0345] The server calls data from news APIs, SNS APIs, and the Japan Meteorological Agency to collect the latest disaster information. Specifically, it uses an API key to access each data source and obtain new disaster information. The obtained data is stored on the server in formats such as JSON and XML. The input is the API endpoint and key, and the output is a dataset of disaster information.

[0346] Step 2:

[0347] The server inputs the collected disaster information into a generative AI model to identify affected areas. Specifically, the data is preprocessed and converted into a format suitable for the model, and then input into the model. A list of affected areas is generated and output. The input is the preprocessed disaster information data, and the output is a list of affected postal codes.

[0348] Step 3:

[0349] The server accesses the delivery company's database to obtain delivery area information. Specifically, it uses an SQL query to extract delivery area data. It then compares the obtained delivery area information with its own postal code database and sets the delivery area code corresponding to each postal code. The input is the delivery company's area database, and the output is a mapping between postal codes and area codes.

[0350] Step 4:

[0351] The server uses the generated list of postal codes in disaster-affected areas to refer to the delivery area code for each postal code and determine whether delivery is possible. Specifically, it uses mapping data between postal codes and area codes to identify affected areas. The input is the list of disaster-affected areas and the mapping data between postal codes and area codes, and the output is a list with a flag indicating whether delivery is possible or not.

[0352] Step 5:

[0353] The server generates a list of customers in the affected areas based on their order history. Specifically, it extracts order data linked to affected postal codes and creates a list of affected customers. The input is a list of postal codes in the affected areas and an order history database, and the output is a list of affected customers.

[0354] Step 6:

[0355] The server notifies each customer whether delivery is possible or not using email, My Page, chat, etc. Specifically, it sends email using an SMTP server or calls a chatbot API to notify. The input is a list of customers to be notified and the notification content, and the output is a notification message to each customer.

[0356] Step 7:

[0357] The server collects the reactions of users who received the notifications. Specifically, it analyzes the logs of the mail server and web server to extract user feedback. The input is each user's notification message and their reaction data (email replies, personal page comments, etc.), and the output is the collected feedback data.

[0358] Step 8:

[0359] The server analyzes the collected feedback data using an emotion engine and evaluates the user's emotional state. Specifically, it performs text sentiment analysis using natural language processing technology to measure dissatisfaction and satisfaction. The input is the collected feedback data, and the output is the evaluation result of the user's emotional state.

[0360] Step 9:

[0361] The server determines the customer support response based on the sentiment analysis results and automatically sets the appropriate action. Specifically, it executes a script that generates and sends a follow-up email. The input is the sentiment analysis results and the follow-up content, and the output is a follow-up message to the user.

[0362] (Application example 2)

[0363] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0364] When a natural disaster occurs, mail-order sales systems must quickly and accurately provide customers with information on whether or not delivery is possible. However, in many cases, collecting disaster information and determining whether or not delivery is possible is done manually, which takes time and effort and can result in delays in customer response. Furthermore, a uniform response that ignores the customer's emotional state can lead to a decrease in customer satisfaction. In response to this, the objective of this invention is to provide customer support that automatically collects and analyzes disaster information and takes into account the customer's emotional state.

[0365] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing disaster information obtained when a natural disaster occurs, means for linking deliverable area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotional data, and means for adjusting responses according to the customer's emotional state. This makes it possible to quickly and accurately provide customers with information on whether delivery is possible even when a disaster occurs, and to respond flexibly in accordance with the customer's emotional state.

[0366] "Natural disaster information" refers to information on natural disasters such as earthquakes, floods, typhoons, and heavy rains obtained from public and private data sources.

[0367] "Disaster information collection and analysis means" is a function for collecting and analyzing disaster information from various data sources when a natural disaster occurs.

[0368] A "delivery area code" is a code that indicates whether delivery is possible in a specific area, and is linked to a postal code.

[0369] The "means for determining whether delivery is possible" is a function that determines whether delivery is possible to a specific area based on collected and analyzed disaster information.

[0370] "Customer notification means" refers to a means for informing customers of the availability of delivery, and includes communication means such as email and messages.

[0371] "Emotional data" is data that indicates the emotional state of a customer, collected from their reactions and opinions.

[0372] "Emotional data collection and analysis means" is a function for collecting customer reaction data and analyzing it to evaluate the emotional state of the customer.

[0373] The "response adjustment means" is a function for adjusting the customer support response in accordance with the analyzed emotional state of the customer.

[0374] The present invention is a system that utilizes AI technology to provide customers with prompt and accurate delivery availability information regarding the operation of a mail-order sales system in the event of a natural disaster. Furthermore, by combining it with an emotion engine, it also includes a function to recognize the user's emotional state and improve the quality of customer service. Specific embodiments of the system are described below.

[0375] First, as a means of collecting and analyzing disaster information, the server collects the latest disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The collected information is analyzed by a generative AI model using TensorFlow to identify areas that may be affected by the disaster.

[0376] Next, to link delivery area codes with postal codes, the server retrieves delivery area information provided by the delivery company's database and compares it with its own postal code database. This process is performed using a backend system using Django.

[0377] As a means of determining whether delivery is possible based on the collected and analyzed disaster information, the server generates a list of postal codes in the affected areas and, based on that list, sets a flag for each postal code indicating that delivery should be canceled or delayed.

[0378] The customer notification system reviews customer order history and generates a list of customers requesting delivery in the affected area. This list of customers will be notified of delivery delays or cancellations via email or message using communication methods such as Twilio.

[0379] Furthermore, as a means of collecting and analyzing emotional data, the server collects the reactions of customers who receive notifications. This reaction data includes email replies, comments on their personal pages, and responses in chat. The collected emotional data is then analyzed again using TensorFlow to evaluate the customer's emotional state.

[0380] Finally, as a means of adjusting responses according to the customer's emotional state, the server automatically adjusts the content and methods of customer support responses based on the analysis results. For example, if a customer is highly dissatisfied, additional follow-up emails or special coupon offers will be automatically generated and sent. This series of processes enables quick and accurate responses even in the event of a disaster, improving customer satisfaction.

[0381] Specific examples

[0382] 1. Disaster information collection and analysis

[0383] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0384] The generating AI will analyze that information and add all postal codes in Shinagawa Ward to the affected list.

[0385] 2. Linking delivery area codes

[0386] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[0387] 3. Determining whether delivery is possible

[0388] The server flags "zip code 123-4567" as undeliverable.

[0389] 4. Customer Notification

[0390] The server extracts the list of customers with the relevant postal code and sends a notification email stating that "Delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0391] 5. Collecting Emotional Data

[0392] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0393] 6. Customer Support Coordination

[0394] If the user is determined to be highly dissatisfied, a follow-up email containing a special coupon will be sent.

[0395] Prompt Sentence Examples

[0396] 1. Prompts for disaster information collection and analysis

[0397] "Based on the latest heavy rain information obtained from the Japan Meteorological Agency API, identify the affected area in Shinagawa Ward, Tokyo."

[0398] 2. Input prompt sentence to emotion engine

[0399] "Analyze this email response to assess the customer's level of dissatisfaction and emotional state."

[0400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0401] Step 1:

[0402] The server collects natural disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The input data is disaster information from each API and is stored on the server. This collected data is stored on the server in its raw form.

[0403] Step 2:

[0404] The server analyzes the collected disaster information using a generative AI model powered by TensorFlow. The input data is the disaster information collected in step 1, and through analysis, potentially affected areas are identified. The output data is a list of affected areas, including detailed information about the identified areas.

[0405] Step 3:

[0406] The server retrieves delivery area information from the delivery company's database and compares it with its own postal code database. The input data is the delivery company's delivery area information and the company's postal code information, and by comparing these, a delivery area code corresponding to each postal code is generated. The output data is a pair of the matched delivery area code and postal code.

[0407] Step 4:

[0408] The server determines whether delivery is possible or not based on the generated affected area list and delivery area code. The input data is a pair of the affected area list and delivery area code, and based on that, it determines whether delivery is possible (or not) for each specific postal code. The output data is a flag set for each postal code indicating whether delivery has been canceled or delayed.

[0409] Step 5:

[0410] The server checks customer order history and generates a list of customers requesting delivery to the affected area. The input data is customer order history and delivery area information, and the affected customer list is created based on these. The output data is the affected customer list.

[0411] Step 6:

[0412] The server uses a communication method such as Twilio to notify affected customers by email or message. The input data is a list of affected customers and delivery availability information, and individual notifications are sent to each customer based on that. The output data is a record of the notifications sent to customers.

[0413] Step 7:

[0414] The user receives a delivery success or failure notification from the server. The input data is the notification sent from the server, which the user confirms. The output data is the user's confirmation and their reaction (for example, a reply to an email or a comment on their personal page).

[0415] Step 8:

[0416] The server collects the user's reactions upon receiving the notification and analyzes them using an emotion engine. The input data is the user's reactions (email replies, comments on their personal page, etc.), which are analyzed by the emotion engine using TensorFlow. The output data is the evaluation results regarding the customer's emotional state.

[0417] Step 9:

[0418] The server adjusts customer support responses based on the results of sentiment analysis. The input data are the sentiment analysis results and customer support response patterns, and based on these, responses tailored to specific customers (for example, generating follow-up emails or special coupons) are automatically generated. The output data is the automatically generated customer response actions.

[0419] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0420] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0421] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0422] [Second embodiment]

[0423] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0424] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0425] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0426] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0427] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0428] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0429] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0430] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0431] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0432] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0433] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0434] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0435] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0436] System Configuration

[0437] The present invention comprises the following main components:

[0438] 1. Disaster information collection and analysis methods

[0439] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0440] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[0441] 2. Delivery area code linking method

[0442] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0443] This allows for clear management of which delivery area code a particular postal code falls under.

[0444] 3. Means of determining delivery availability

[0445] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[0446] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0447] 4. Customer Notification Means

[0448] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0449] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0450] Program processing

[0451] 1. Disaster information collection and analysis

[0452] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[0453] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[0454] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered damage from heavy rain."

[0455] 2. Linking delivery area codes

[0456] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[0457] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[0458] 3. Determining whether delivery is possible

[0459] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[0460] For example, "Postal code 123-4567 will be marked as undeliverable."

[0461] 4. Notice to Customer

[0462] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[0463] Notify each customer by email, etc. For example, "Send a delivery delay notification to customer A by email."

[0464] Specific examples

[0465] Disaster information collection and analysis

[0466] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0467] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0468] Linking delivery area codes

[0469] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0470] Judgment on delivery availability

[0471] The server flags "123-4567" as undeliverable.

[0472] customer notification

[0473] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0474] This system will enable mail-order businesses to respond to customers quickly and accurately even during natural disasters, improving customer satisfaction and streamlining logistics.

[0475] The processing flow will be explained below.

[0476] Step 1:

[0477] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[0478] Step 2:

[0479] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[0480] Step 3:

[0481] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[0482] Step 4:

[0483] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[0484] Step 5:

[0485] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[0486] Step 6:

[0487] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[0488] Step 7:

[0489] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[0490] Step 8:

[0491] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[0492] Step 9:

[0493] The server checks whether the notification was sent successfully and determines whether it needs to be sent again. If the notification is not received, it will try to notify the customer by other means (e.g., SMS, phone call) to improve the accuracy of customer support.

[0494] In this way, the system of the present invention, through a series of processing steps, enables quick and accurate response to customers even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[0495] Example 1

[0496] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0497] When a natural disaster occurs, it is difficult for mail order businesses to quickly and accurately provide customers with information about whether or not their deliveries will be successful. In particular, when the disaster has a wide impact, it is difficult to immediately assess the situation in each region and provide appropriate notifications. As a result, customers often become dissatisfied because they are unable to properly grasp information about delivery delays or cancellations.

[0498] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0499] In this invention, the server includes means for collecting disaster information from public and private data sources, means for analyzing the collected disaster information using a generative AI model, means for linking delivery area codes with multiple postal codes, means for generating a list of affected postal codes based on the analyzed disaster information and determining whether delivery is possible for each delivery area code, and means for generating a list of affected customers based on delivery area information linked to customer order history and notifying them by means of email, chat, etc. This enables mail-order businesses to quickly and accurately provide customers with delivery possibility information even during natural disasters.

[0500] "Official data sources" are official sources of information provided by government agencies or local governments.

[0501] "Private data sources" are information sources provided by private organizations and individuals, such as news media and social media.

[0502] "Disaster information" refers to specific data and reports on natural disasters, such as the extent of damage, the extent of impact, and the location of the disaster.

[0503] A "generative AI model" is an artificial intelligence model that is trained using machine learning to perform a specific task.

[0504] "Analysis" is the process of identifying the scale and scope of a disaster based on collected data.

[0505] A "delivery area code" is a code that indicates a certain area and is used to determine whether delivery is possible within that area.

[0506] "Postal Codes" are a series of numbers used to designate a particular area and are utilized to uniquely identify multiple areas.

[0507] A "delivery area code" is a code that identifies a delivery area and includes multiple postal codes.

[0508] "Delivery availability" is a status indicating whether delivery is possible to a specific area.

[0509] "Customer" means a person who purchases goods or services.

[0510] "Order History" refers to a record of past orders placed by a customer.

[0511] "Delivery area information" is information relating to the area to be delivered.

[0512] The "list of affected customers" is a list of customers whose deliveries may be affected, identified based on disaster information.

[0513] "Notification" is the act of informing someone of information, and is done via email, chat, etc.

[0514] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that uses AI technology to provide customers with fast and accurate information on whether delivery is possible. This system has a multi-functional configuration that collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0515] 1. Collecting disaster information

[0516] The server collects disaster information from public and private data sources. To do this, it uses the Japan Meteorological Agency's API, SNS API, and news API. Specifically, the server accesses these APIs every hour and runs a regular job to obtain the latest disaster data. This information is used as basic data for quickly understanding the disaster situation.

[0517] 2. Disaster Information Analysis

[0518] The server uses the generative AI model to analyze the acquired disaster data. This analysis makes it possible to identify the scale of the disaster, the extent of the impact, and the affected areas. Specifically, the server creates a prompt for the generative AI model, inputs it into the AI ​​model, and obtains the analysis results. For example, "The server analyzes the information acquired by the generative AI and identifies that Shinagawa Ward and surrounding areas in Tokyo are affected by heavy rain."

[0519] 3. Linking delivery area codes

[0520] The server checks the databases provided by the mail-order business and the delivery company. It links each postal code with a corresponding delivery area code, and this is how delivery areas are managed. Specifically, the server periodically performs a database join operation to obtain the latest delivery area information. For example, "The server links Shinagawa Ward (postal code 123-4567) to the area code for Tokyo's 23 wards."

[0521] 4. Delivery Determination

[0522] The server generates a list of affected postal codes based on the disaster information analyzed by the AI. Based on this list, it sets a flag for delivery suspension or delay for each delivery area code. For example, "The server sets a flag for delivery ineligible for the area with postal codes 123-4567." Specifically, the server loops through the postal code list and sets a delivery flag for each postal code.

[0523] 5. Notice to Customer

[0524] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer of delivery delays or cancellations using methods such as email, personal pages, and chat. For example, the server might "send an email to customer A notifying them of a delivery delay." Specifically, the server uses an email sending API to automatically send an email with the specified content.

[0525] Examples:

[0526] Disaster information collection:

[0527] The server accesses the Japan Meteorological Agency API at 9:00 a.m. and obtains information about the heavy rain disaster in Shinagawa Ward, Tokyo.

[0528] Disaster information analysis:

[0529] The server inputs the acquired heavy rain information into the generation AI, which analyzes and determines that all postal codes in Shinagawa Ward are affected.

[0530] Delivery Area Code Linking:

[0531] The server recognizes Shinagawa Ward (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0532] Delivery availability:

[0533] The server flags "123-4567" as undeliverable.

[0534] Customer Notice:

[0535] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0536] Example prompt sentence:

[0537] "Please collect the latest disaster information. Use the Japan Meteorological Agency API, news API, and SNS API to obtain disaster information affecting the 23 wards of Tokyo, and analyze it to identify which areas are affected."

[0538] This will enable the system to respond quickly and accurately even in the event of a natural disaster, contributing to improved customer satisfaction and more efficient logistics.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] Disaster information collection:

[0542] The server collects the latest disaster information from public data sources (such as the Japan Meteorological Agency API) and private data sources (such as news APIs and SNS APIs). It uses the API endpoints and necessary authentication information as input, and obtains the latest disaster information data as output. Specifically, the server runs a periodic job that accesses these APIs every hour and retrieves the latest disaster data in JSON format.

[0543] Step 2:

[0544] Disaster information analysis:

[0545] The disaster information acquired by the server is input into a generative AI model, which then obtains the analysis results. This generative AI model uses natural language processing technology to identify the scale, extent of impact, and affected areas of the disaster. As input, the acquired disaster information data is converted into prompt statements, which are then input into the generative AI model. As output, the affected areas of the disaster and detailed information about them are obtained. For example, it generates information such as "Shinagawa Ward, Tokyo, has suffered damage from heavy rain."

[0546] Step 3:

[0547] Delivery Area Code Linking:

[0548] The server retrieves the postal code database provided by the mail-order business and the delivery area information provided by the delivery company, and associates each postal code with a corresponding delivery area code. Both databases are used as input, and a list of correspondences between postal codes and delivery area codes is generated as output. Specifically, the server compares these databases using a join operation and periodically updates the latest delivery area information.

[0549] Step 4:

[0550] Delivery availability:

[0551] The server generates a list of affected postal codes based on the disaster information analyzed by the AI ​​model. It uses the delivery area code associated with the disaster information from the analysis as input, and generates a list of postal codes flagged as undeliverable or delayed as output. Specifically, the server loops through the list of affected postal codes and flags each one as undeliverable or deferred.

[0552] Step 5:

[0553] Customer Notice:

[0554] The server checks customer order history and generates a list of customers requesting delivery in the affected areas. It uses customer order history data and a list of affected postal codes as input. It generates a list of customers with information to notify of delivery delays or cancellations as output. Specifically, the server automatically sends delivery delay notifications to each customer using an email sending API or chat notification function.

[0555] This will enable the system to respond quickly and accurately even in the event of a natural disaster, improving customer satisfaction and streamlining logistics.

[0556] (Application example 1)

[0557] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0558] In recent years, the frequent occurrence of natural disasters has increasingly had a major impact on mail-order logistics. This has created a need for fast and accurate notification of delivery status to customers. However, conventional systems are unable to quickly collect and analyze disaster information or determine whether or not delivery can be made, which can lead to a decline in customer satisfaction. Furthermore, the resulting delays and cancellations of logistics are a major issue for businesses. To solve these issues, a system is needed that can efficiently collect and analyze disaster information and quickly notify customers.

[0559] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0560] In this invention, the server includes means for collecting and analyzing disaster information acquired when a natural disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, and means for sending push notifications to customers via a smartphone application. This makes it possible to notify customers of delivery status quickly and accurately even when a disaster occurs, thereby improving customer satisfaction and streamlining logistics.

[0561] "Natural disaster information" refers to information about disasters collected from disaster reports by the Japan Meteorological Agency and local governments, social media, breaking news, etc.

[0562] "Means of collection and analysis" refers to the system by which data is acquired using a server or related technology, and then analyzed to create usable information.

[0563] A "delivery area code" is a code that indicates whether an item can be delivered to a specific area or postal code.

[0564] A "postal code" is a code consisting of a series of numbers that identifies an area or address.

[0565] The "means for determining whether delivery is possible" is a mechanism that determines whether delivery of goods to a specific area is possible based on collected disaster information.

[0566] "Means of notification" refers to a system for communicating information such as delivery delays or cancellations to customers.

[0567] A "smartphone application" is software that is installed on a smartphone and enables the user to use certain functions.

[0568] "Push notifications" are real-time messages or notifications sent from an application directly to a user's smartphone.

[0569] A "server" is a computer that provides services to other computers and devices on a network.

[0570] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0571] System Configuration

[0572] The system consists of the following main components:

[0573] 1. Disaster information collection and analysis methods

[0574] When a disaster occurs, the server collects information from public data sources (e.g., disaster reports from the Japan Meteorological Agency and local governments) and private data sources (e.g., social media and breaking news). The server uses generative AI to analyze the collected data and obtain detailed information about the affected area.

[0575] 2. Delivery area code linking method

[0576] The server connects the mail-order company's database with the delivery company's database, and associates each postal code with a corresponding delivery area code, thereby clearly managing which delivery area code a specific postal code corresponds to.

[0577] 3. Means of determining delivery availability

[0578] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the AI. For each postal code, it references the delivery area code and determines whether delivery is possible there.

[0579] 4. Customer Notification Means

[0580] The server generates a list of affected customers based on delivery area information linked to the customer's order history, and notifies each customer of delivery delays or cancellations via email, their personal page, chat, or smartphone application.

[0581] Program processing

[0582] 1. Disaster information collection and analysis

[0583] The server collects the latest disaster information using news APIs, social media APIs, and data from the Japan Meteorological Agency. The generation AI analyzes this information and identifies areas that may be affected by the disaster. For example, "The information obtained by the server reveals that local city A has been hit by heavy rain."

[0584] 2. Linking delivery area codes

[0585] The server obtains the delivery area information provided by the delivery company and compares it with its own postal code database. For example, "Regional city A (postal code 123-4567) is linked to the regional area code."

[0586] 3. Determining whether delivery is possible

[0587] The server generates a list of affected zip codes and flags each shipping area code from that list as undeliverable or delayed, for example, "zip codes 123-4567 will be marked as undeliverable."

[0588] 4. Notice to Customer

[0589] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer via email or smartphone application. For example, "Send a delivery delay notification to customer A via a smartphone application."

[0590] Specific examples

[0591] The server obtains information about the heavy rain disaster in Regional City A from the API, and the generation AI analyzes that information and adds all postal codes in Regional City A to the affected list. Furthermore, the server recognizes Regional City A (postal code 123-4567) as a "regional area" from the delivery company's database and flags the corresponding postal code as undeliverable. Finally, the server extracts the customer list for the corresponding postal code and sends a notification to the smartphone app stating, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[0592] Example prompts for generative AI models

[0593] Heavy rain has hit local city A, affecting the area with zip code 123-4567. Delivery may be delayed or canceled. Please promptly notify customers in the affected area via email and push notifications.

[0594] With these configurations, this system is able to quickly and accurately notify customers of delivery status even in the event of a disaster, thereby improving customer satisfaction and streamlining logistics.

[0595] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0596] Step 1:

[0597] The server collects disaster information. The server obtains disaster information from public data sources (e.g., the Japan Meteorological Agency, local government disaster reports) and private data sources (e.g., SNS APIs, news APIs). This information includes details such as the type of disaster, the location of the disaster, and the extent of the impact. The input is disaster information from each API, and the output is disaster data that is centrally managed within the server.

[0598] Step 2:

[0599] The disaster information collected by the server is analyzed using a generative AI model. The generative AI model analyzes the collected information and identifies areas that may be affected. Specifically, it uses natural language processing and machine learning algorithms to process text data and generate a list of affected postal codes. The input is the disaster information from Step 1, and the output is the list of affected postal codes.

[0600] Step 3:

[0601] The server links the generated list of postal codes to existing delivery area codes. The server references a database linked to delivery companies to determine which delivery area code corresponds to each postal code. This process determines which delivery area a specific region falls into. The input is the list of postal codes from step 2, and the output is a list of delivery area codes linked to each postal code.

[0602] Step 4:

[0603] The server determines whether delivery is possible. Based on the delivery area code obtained in step 3, the server references the collected and analyzed disaster information to determine whether delivery to that area is possible. A flag is set for each area code to indicate whether delivery will be delayed or canceled. The input is the delivery area code from step 3 and the disaster information from step 2, and the output is a list of area codes with delivery possibility flags.

[0604] Step 5:

[0605] The server checks the customer's order history. The server extracts delivery area information for each customer from the customer database and generates a list of customers who belong to the affected area. Specifically, it extracts and lists the order histories of customers who belong to the affected postal codes. The input is the customer database and the delivery availability flag from step 4, and the output is a list of customers to be notified.

[0606] Step 6:

[0607] The server notifies affected customers. Based on the generated customer list, the server sends notifications to each customer via email or smartphone application. The message contains detailed information about the delivery delay or cancellation and recommended action to take. The input is the list of customers to be notified in step 5, and the output is the notification sent to the customer. For example, the server sends a notification via a smartphone app saying, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[0608] Through the above processing steps, customers can be notified of delivery status quickly and accurately even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[0609] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0610] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[0611] System Configuration

[0612] The present invention comprises the following main components:

[0613] 1. Disaster information collection and analysis methods

[0614] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0615] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[0616] 2. Delivery area code linking method

[0617] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0618] This allows for clear management of which delivery area code a particular postal code falls under.

[0619] 3. Means of determining delivery availability

[0620] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[0621] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0622] 4. Customer Notification Means

[0623] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0624] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0625] 5. Emotion Engine

[0626] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[0627] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[0628] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[0629] Program processing

[0630] 1. Disaster information collection and analysis

[0631] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[0632] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[0633] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered flooding damage due to heavy rain."

[0634] 2. Linking delivery area codes

[0635] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[0636] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[0637] 3. Determining whether delivery is possible

[0638] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[0639] For example, "Postal code 123-4567 will be marked as undeliverable."

[0640] 4. Notice to Customer

[0641] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[0642] Notify each customer by email, etc. For example, "Notify customer A by email that delivery of order number ABC123 will be delayed."

[0643] 5. Collecting Emotional Data

[0644] The server collects the user's response to the notification, such as the content of the email reply or the comments on the user's personal page.

[0645] For example, "The server collects reply emails from user B and analyzes their contents."

[0646] 6. Emotional Data Analysis and Response

[0647] The server analyzes the data collected by the emotion engine and evaluates the user's emotional state.

[0648] For example, "The server recognizes from the analysis results that user B is highly dissatisfied."

[0649] Based on the analysis results, the server automatically generates a notification to instruct customer support to take appropriate action, such as "Configure sending of additional follow-up emails to User B, who is very dissatisfied."

[0650] Specific examples

[0651] Disaster information collection and analysis

[0652] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0653] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0654] Linking delivery area codes

[0655] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0656] Judgment on delivery availability

[0657] The server flags "123-4567" as undeliverable.

[0658] customer notification

[0659] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0660] Collecting Emotional Data

[0661] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0662] For example, a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[0663] Customer support coordination

[0664] The server determines that the user is extremely dissatisfied and automatically generates and sends a follow-up email.

[0665] For example, "The server will send an additional follow-up email to the user with an apology."

[0666] In this way, the system of the present invention can respond to customers quickly and accurately even in the event of a disaster, and can also respond while taking into consideration the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[0667] The processing flow will be explained below.

[0668] Step 1:

[0669] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[0670] Step 2:

[0671] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[0672] Step 3:

[0673] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[0674] Step 4:

[0675] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[0676] Step 5:

[0677] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[0678] Step 6:

[0679] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[0680] Step 7:

[0681] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[0682] Step 8:

[0683] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[0684] Step 9:

[0685] The server collects emotional data from users who receive notifications. The collected data includes how users reacted to notifications (e.g., the content of reply emails, comments on their personal page, responses in chat, etc.). For example, "User A left a comment on their personal page saying, 'Delays in delivery are a problem.'"

[0686] Step 10:

[0687] The server uses an emotion engine to analyze the collected emotional data and measure the user's level of satisfaction or dissatisfaction. For example, "The server recognizes from User A's comments that User A is very dissatisfied."

[0688] Step 11:

[0689] The server automatically adjusts the content and methods of customer support based on the analysis results, for example, "for highly dissatisfied users, it will automatically generate and send additional follow-up emails or phone calls."

[0690] Step 12:

[0691] The server sends follow-up notifications to the user to improve customer satisfaction. For example, "Send an apology email to User A, and notify customer support if further action is required."

[0692] In this way, the system of the present invention, through a series of processing steps, can respond to customers quickly and accurately even in the event of a natural disaster, and can respond while taking into account the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[0693] Example 2

[0694] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0695] In conventional mail order systems, it was difficult to provide fast and accurate information on delivery availability in the event of a natural disaster, resulting in problems such as a decline in customer satisfaction and logistics disruptions. Furthermore, there was a lack of consideration for customer feelings, making it difficult to provide appropriate follow-up for dissatisfied customers.

[0696] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0697] In this invention, the server includes means for collecting and analyzing disaster information acquired when a disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotion data and optimizing customer service, means for analyzing disaster information using a generative AI model, and means for collecting natural disaster information from public and private data sources. This makes it possible to quickly and accurately provide delivery possibility information even when a natural disaster occurs, and to respond in consideration of the emotional state of the customer.

[0698] The "disaster information collection and analysis means" is a device that collects disaster information from public and private data sources when a disaster occurs and analyzes it using a generative AI model.

[0699] A "delivery area code" is a unique code for identifying each delivery area, and is an identifier used to associate with a postal code.

[0700] A "postal code" is a unique number that represents a specific region or area, and is an identifier linked to a delivery area code.

[0701] The "delivery possibility determination means" is a device that determines whether delivery is possible to a specific delivery area or postal code based on the collected and analyzed disaster information.

[0702] The "customer notification means" is a device that notifies the customer of the information on whether delivery is possible or not using an appropriate means (e.g., email, personal page, chat).

[0703] The "emotion data collection and analysis means" is a device that collects the reactions shown by customers to notifications and analyzes their emotional state using an emotion engine.

[0704] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze disaster information and emotional data.

[0705] "Public data sources" are data provided by public institutions such as the Japan Meteorological Agency and local government disaster reports.

[0706] "Private data sources" are data provided by private companies such as social media and breaking news.

[0707] An "emotion engine" is an artificial intelligence system that analyzes the emotional state of customers and is used to optimize customer service.

[0708] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[0709] The present invention comprises the following main components:

[0710] 1. Disaster information collection and analysis methods

[0711] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0712] The server uses a generative AI model to analyze the collected data and obtain detailed information about the affected area.

[0713] 2. Delivery area code linking method

[0714] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0715] This allows for clear management of which delivery area code a particular postal code falls under.

[0716] 3. Means of determining delivery availability

[0717] The server generates a list of postal codes for affected areas based on disaster information analyzed by the generative AI model.

[0718] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0719] 4. Customer Notification Means

[0720] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0721] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0722] 5. Emotion Engine

[0723] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[0724] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[0725] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[0726] Specific examples

[0727] Disaster information collection and analysis

[0728] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0729] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0730] Linking delivery area codes

[0731] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[0732] Judgment on delivery availability

[0733] The server flags Shinagawa-ku (zip code 123-4567) as undeliverable.

[0734] customer notification

[0735] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0736] Collecting Emotional Data

[0737] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0738] For example, suppose that a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[0739] Customer support coordination

[0740] The server determines that the user is very dissatisfied and automatically generates and sends a follow-up email.

[0741] For example, "The server will send an additional follow-up email to the user with an apology."

[0742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0743] Step 1:

[0744] The server calls data from news APIs, SNS APIs, and the Japan Meteorological Agency to collect the latest disaster information. Specifically, it uses an API key to access each data source and obtain new disaster information. The obtained data is stored on the server in formats such as JSON and XML. The input is the API endpoint and key, and the output is a dataset of disaster information.

[0745] Step 2:

[0746] The server inputs the collected disaster information into a generative AI model to identify affected areas. Specifically, the data is preprocessed and converted into a format suitable for the model, and then input into the model. A list of affected areas is generated and output. The input is the preprocessed disaster information data, and the output is a list of affected postal codes.

[0747] Step 3:

[0748] The server accesses the delivery company's database to obtain delivery area information. Specifically, it uses an SQL query to extract delivery area data. It then compares the obtained delivery area information with its own postal code database and sets the delivery area code corresponding to each postal code. The input is the delivery company's area database, and the output is a mapping between postal codes and area codes.

[0749] Step 4:

[0750] The server uses the generated list of postal codes in disaster-affected areas to refer to the delivery area code for each postal code and determine whether delivery is possible. Specifically, it uses mapping data between postal codes and area codes to identify affected areas. The input is the list of disaster-affected areas and the mapping data between postal codes and area codes, and the output is a list with a flag indicating whether delivery is possible or not.

[0751] Step 5:

[0752] The server generates a list of customers in the affected areas based on their order history. Specifically, it extracts order data linked to affected postal codes and creates a list of affected customers. The input is a list of postal codes in the affected areas and an order history database, and the output is a list of affected customers.

[0753] Step 6:

[0754] The server notifies each customer whether delivery is possible or not using email, My Page, chat, etc. Specifically, it sends email using an SMTP server or calls a chatbot API to notify. The input is a list of customers to be notified and the notification content, and the output is a notification message to each customer.

[0755] Step 7:

[0756] The server collects the reactions of users who received the notifications. Specifically, it analyzes the logs of the mail server and web server to extract user feedback. The input is each user's notification message and their reaction data (email replies, personal page comments, etc.), and the output is the collected feedback data.

[0757] Step 8:

[0758] The server analyzes the collected feedback data using an emotion engine and evaluates the user's emotional state. Specifically, it performs text sentiment analysis using natural language processing technology to measure dissatisfaction and satisfaction. The input is the collected feedback data, and the output is the evaluation result of the user's emotional state.

[0759] Step 9:

[0760] The server determines the customer support response based on the sentiment analysis results and automatically sets the appropriate action. Specifically, it executes a script that generates and sends a follow-up email. The input is the sentiment analysis results and the follow-up content, and the output is a follow-up message to the user.

[0761] (Application example 2)

[0762] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0763] When a natural disaster occurs, mail-order sales systems must quickly and accurately provide customers with information on whether or not delivery is possible. However, in many cases, collecting disaster information and determining whether or not delivery is possible is done manually, which takes time and effort and can result in delays in customer response. Furthermore, a uniform response that ignores the customer's emotional state can lead to a decrease in customer satisfaction. In response to this, the objective of this invention is to provide customer support that automatically collects and analyzes disaster information and takes into account the customer's emotional state.

[0764] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing disaster information obtained when a natural disaster occurs, means for linking deliverable area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotional data, and means for adjusting responses according to the customer's emotional state. This makes it possible to quickly and accurately provide customers with information on whether delivery is possible even when a disaster occurs, and to respond flexibly in accordance with the customer's emotional state.

[0765] "Natural disaster information" refers to information on natural disasters such as earthquakes, floods, typhoons, and heavy rains obtained from public and private data sources.

[0766] "Disaster information collection and analysis means" is a function for collecting and analyzing disaster information from various data sources when a natural disaster occurs.

[0767] A "delivery area code" is a code that indicates whether delivery is possible in a specific area, and is linked to a postal code.

[0768] The "means for determining whether delivery is possible" is a function that determines whether delivery is possible to a specific area based on collected and analyzed disaster information.

[0769] "Customer notification means" refers to a means for informing customers of the availability of delivery, and includes communication means such as email and messages.

[0770] "Emotional data" is data that indicates the emotional state of a customer, collected from their reactions and opinions.

[0771] "Emotional data collection and analysis means" is a function for collecting customer reaction data and analyzing it to evaluate the emotional state of the customer.

[0772] The "response adjustment means" is a function for adjusting the customer support response in accordance with the analyzed emotional state of the customer.

[0773] The present invention is a system that utilizes AI technology to provide customers with prompt and accurate delivery availability information regarding the operation of a mail-order sales system in the event of a natural disaster. Furthermore, by combining it with an emotion engine, it also includes a function to recognize the user's emotional state and improve the quality of customer service. Specific embodiments of the system are described below.

[0774] First, as a means of collecting and analyzing disaster information, the server collects the latest disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The collected information is analyzed by a generative AI model using TensorFlow to identify areas that may be affected by the disaster.

[0775] Next, to link delivery area codes with postal codes, the server retrieves delivery area information provided by the delivery company's database and compares it with its own postal code database. This process is performed using a backend system using Django.

[0776] As a means of determining whether delivery is possible based on the collected and analyzed disaster information, the server generates a list of postal codes in the affected areas and, based on that list, sets a flag for each postal code indicating that delivery should be canceled or delayed.

[0777] The customer notification system reviews customer order history and generates a list of customers requesting delivery in the affected area. This list of customers will be notified of delivery delays or cancellations via email or message using communication methods such as Twilio.

[0778] Furthermore, as a means of collecting and analyzing emotional data, the server collects the reactions of customers who receive notifications. This reaction data includes email replies, comments on their personal pages, and responses in chat. The collected emotional data is then analyzed again using TensorFlow to evaluate the customer's emotional state.

[0779] Finally, as a means of adjusting responses according to the customer's emotional state, the server automatically adjusts the content and methods of customer support responses based on the analysis results. For example, if a customer is highly dissatisfied, additional follow-up emails or special coupon offers will be automatically generated and sent. This series of processes enables quick and accurate responses even in the event of a disaster, improving customer satisfaction.

[0780] Specific examples

[0781] 1. Disaster information collection and analysis

[0782] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0783] The generating AI will analyze that information and add all postal codes in Shinagawa Ward to the affected list.

[0784] 2. Linking delivery area codes

[0785] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[0786] 3. Determining whether delivery is possible

[0787] The server flags "zip code 123-4567" as undeliverable.

[0788] 4. Customer Notification

[0789] The server extracts the list of customers with the relevant postal code and sends a notification email stating that "Delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0790] 5. Collecting Emotional Data

[0791] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[0792] 6. Customer Support Coordination

[0793] If the user is determined to be highly dissatisfied, a follow-up email containing a special coupon will be sent.

[0794] Prompt Sentence Examples

[0795] 1. Prompts for disaster information collection and analysis

[0796] "Based on the latest heavy rain information obtained from the Japan Meteorological Agency API, identify the affected area in Shinagawa Ward, Tokyo."

[0797] 2. Input prompt sentence to emotion engine

[0798] "Analyze this email response to assess the customer's level of dissatisfaction and emotional state."

[0799] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0800] Step 1:

[0801] The server collects natural disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The input data is disaster information from each API and is stored on the server. This collected data is stored on the server in its raw form.

[0802] Step 2:

[0803] The server analyzes the collected disaster information using a generative AI model powered by TensorFlow. The input data is the disaster information collected in step 1, and through analysis, potentially affected areas are identified. The output data is a list of affected areas, including detailed information about the identified areas.

[0804] Step 3:

[0805] The server retrieves delivery area information from the delivery company's database and compares it with its own postal code database. The input data is the delivery company's delivery area information and the company's postal code information, and by comparing these, a delivery area code corresponding to each postal code is generated. The output data is a pair of the matched delivery area code and postal code.

[0806] Step 4:

[0807] The server determines whether delivery is possible or not based on the generated affected area list and delivery area code. The input data is a pair of the affected area list and delivery area code, and based on that, it determines whether delivery is possible (or not) for each specific postal code. The output data is a flag set for each postal code indicating whether delivery has been canceled or delayed.

[0808] Step 5:

[0809] The server checks customer order history and generates a list of customers requesting delivery to the affected area. The input data is customer order history and delivery area information, and the affected customer list is created based on these. The output data is the affected customer list.

[0810] Step 6:

[0811] The server uses a communication method such as Twilio to notify affected customers by email or message. The input data is a list of affected customers and delivery availability information, and individual notifications are sent to each customer based on that. The output data is a record of the notifications sent to customers.

[0812] Step 7:

[0813] The user receives a delivery success or failure notification from the server. The input data is the notification sent from the server, which the user confirms. The output data is the user's confirmation and their reaction (for example, a reply to an email or a comment on their personal page).

[0814] Step 8:

[0815] The server collects the user's reactions upon receiving the notification and analyzes them using an emotion engine. The input data is the user's reactions (email replies, comments on their personal page, etc.), which are analyzed by the emotion engine using TensorFlow. The output data is the evaluation results regarding the customer's emotional state.

[0816] Step 9:

[0817] The server adjusts customer support responses based on the results of sentiment analysis. The input data are the sentiment analysis results and customer support response patterns, and based on these, responses tailored to specific customers (for example, generating follow-up emails or special coupons) are automatically generated. The output data is the automatically generated customer response actions.

[0818] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0819] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0820] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0821] [Third embodiment]

[0822] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0823] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0824] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0825] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0826] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0827] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0828] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0829] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0830] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0831] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0832] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0833] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0834] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0835] System Configuration

[0836] The present invention comprises the following main components:

[0837] 1. Disaster information collection and analysis methods

[0838] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[0839] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[0840] 2. Delivery area code linking method

[0841] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[0842] This allows for clear management of which delivery area code a particular postal code falls under.

[0843] 3. Means of determining delivery availability

[0844] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[0845] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[0846] 4. Customer Notification Means

[0847] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[0848] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[0849] Program processing

[0850] 1. Disaster information collection and analysis

[0851] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[0852] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[0853] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered damage from heavy rain."

[0854] 2. Linking delivery area codes

[0855] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[0856] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[0857] 3. Determining whether delivery is possible

[0858] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[0859] For example, "Postal code 123-4567 will be marked as undeliverable."

[0860] 4. Notice to Customer

[0861] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[0862] Notify each customer by email, etc. For example, "Send a delivery delay notification to customer A by email."

[0863] Specific examples

[0864] Disaster information collection and analysis

[0865] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[0866] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[0867] Linking delivery area codes

[0868] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0869] Judgment on delivery availability

[0870] The server flags "123-4567" as undeliverable.

[0871] customer notification

[0872] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0873] This system will enable mail-order businesses to respond to customers quickly and accurately even during natural disasters, improving customer satisfaction and streamlining logistics.

[0874] The processing flow will be explained below.

[0875] Step 1:

[0876] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[0877] Step 2:

[0878] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[0879] Step 3:

[0880] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[0881] Step 4:

[0882] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[0883] Step 5:

[0884] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[0885] Step 6:

[0886] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[0887] Step 7:

[0888] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[0889] Step 8:

[0890] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[0891] Step 9:

[0892] The server checks whether the notification was sent successfully and determines whether it needs to be sent again. If the notification is not received, it will try to notify the customer by other means (e.g., SMS, phone call) to improve the accuracy of customer support.

[0893] In this way, the system of the present invention, through a series of processing steps, enables quick and accurate response to customers even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[0894] Example 1

[0895] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0896] When a natural disaster occurs, it is difficult for mail order businesses to quickly and accurately provide customers with information about whether or not their deliveries will be successful. In particular, when the disaster has a wide impact, it is difficult to immediately assess the situation in each region and provide appropriate notifications. As a result, customers often become dissatisfied because they are unable to properly grasp information about delivery delays or cancellations.

[0897] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0898] In this invention, the server includes means for collecting disaster information from public and private data sources, means for analyzing the collected disaster information using a generative AI model, means for linking delivery area codes with multiple postal codes, means for generating a list of affected postal codes based on the analyzed disaster information and determining whether delivery is possible for each delivery area code, and means for generating a list of affected customers based on delivery area information linked to customer order history and notifying them by means of email, chat, etc. This enables mail-order businesses to quickly and accurately provide customers with delivery possibility information even during natural disasters.

[0899] "Official data sources" are official sources of information provided by government agencies or local governments.

[0900] "Private data sources" are information sources provided by private organizations and individuals, such as news media and social media.

[0901] "Disaster information" refers to specific data and reports on natural disasters, such as the extent of damage, the extent of impact, and the location of the disaster.

[0902] A "generative AI model" is an artificial intelligence model that is trained using machine learning to perform a specific task.

[0903] "Analysis" is the process of identifying the scale and scope of a disaster based on collected data.

[0904] A "delivery area code" is a code that indicates a certain area and is used to determine whether delivery is possible within that area.

[0905] "Postal Codes" are a series of numbers used to designate a particular area and are utilized to uniquely identify multiple areas.

[0906] A "delivery area code" is a code that identifies a delivery area and includes multiple postal codes.

[0907] "Delivery availability" is a status indicating whether delivery is possible to a specific area.

[0908] "Customer" means a person who purchases goods or services.

[0909] "Order History" refers to a record of past orders placed by a customer.

[0910] "Delivery area information" is information relating to the area to be delivered.

[0911] The "list of affected customers" is a list of customers whose deliveries may be affected, identified based on disaster information.

[0912] "Notification" is the act of informing someone of information, and is done via email, chat, etc.

[0913] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that uses AI technology to provide customers with fast and accurate information on whether delivery is possible. This system has a multi-functional configuration that collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0914] 1. Collecting disaster information

[0915] The server collects disaster information from public and private data sources. To do this, it uses the Japan Meteorological Agency's API, SNS API, and news API. Specifically, the server accesses these APIs every hour and runs a regular job to obtain the latest disaster data. This information is used as basic data for quickly understanding the disaster situation.

[0916] 2. Disaster Information Analysis

[0917] The server uses the generative AI model to analyze the acquired disaster data. This analysis makes it possible to identify the scale of the disaster, the extent of the impact, and the affected areas. Specifically, the server creates a prompt for the generative AI model, inputs it into the AI ​​model, and obtains the analysis results. For example, "The server analyzes the information acquired by the generative AI and identifies that Shinagawa Ward and surrounding areas in Tokyo are affected by heavy rain."

[0918] 3. Linking delivery area codes

[0919] The server checks the databases provided by the mail-order business and the delivery company. It links each postal code with a corresponding delivery area code, and this is how delivery areas are managed. Specifically, the server periodically performs a database join operation to obtain the latest delivery area information. For example, "The server links Shinagawa Ward (postal code 123-4567) to the area code for Tokyo's 23 wards."

[0920] 4. Delivery Determination

[0921] The server generates a list of affected postal codes based on the disaster information analyzed by the AI. Based on this list, it sets a flag for delivery suspension or delay for each delivery area code. For example, "The server sets a flag for delivery ineligible for the area with postal codes 123-4567." Specifically, the server loops through the postal code list and sets a delivery flag for each postal code.

[0922] 5. Notice to Customer

[0923] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer of delivery delays or cancellations using methods such as email, personal pages, and chat. For example, the server might "send an email to customer A notifying them of a delivery delay." Specifically, the server uses an email sending API to automatically send an email with the specified content.

[0924] Examples:

[0925] Disaster information collection:

[0926] The server accesses the Japan Meteorological Agency API at 9:00 a.m. and obtains information about the heavy rain disaster in Shinagawa Ward, Tokyo.

[0927] Disaster information analysis:

[0928] The server inputs the acquired heavy rain information into the generation AI, which analyzes and determines that all postal codes in Shinagawa Ward are affected.

[0929] Delivery Area Code Linking:

[0930] The server recognizes Shinagawa Ward (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[0931] Delivery availability:

[0932] The server flags "123-4567" as undeliverable.

[0933] Customer Notice:

[0934] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[0935] Example prompt sentence:

[0936] "Please collect the latest disaster information. Use the Japan Meteorological Agency API, news API, and SNS API to obtain disaster information affecting the 23 wards of Tokyo, and analyze it to identify which areas are affected."

[0937] This will enable the system to respond quickly and accurately even in the event of a natural disaster, contributing to improved customer satisfaction and more efficient logistics.

[0938] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0939] Step 1:

[0940] Disaster information collection:

[0941] The server collects the latest disaster information from public data sources (such as the Japan Meteorological Agency API) and private data sources (such as news APIs and SNS APIs). It uses the API endpoints and necessary authentication information as input, and obtains the latest disaster information data as output. Specifically, the server runs a periodic job that accesses these APIs every hour and retrieves the latest disaster data in JSON format.

[0942] Step 2:

[0943] Disaster information analysis:

[0944] The disaster information acquired by the server is input into a generative AI model, which then obtains the analysis results. This generative AI model uses natural language processing technology to identify the scale, extent of impact, and affected areas of the disaster. As input, the acquired disaster information data is converted into prompt statements, which are then input into the generative AI model. As output, the affected areas of the disaster and detailed information about them are obtained. For example, it generates information such as "Shinagawa Ward, Tokyo, has suffered damage from heavy rain."

[0945] Step 3:

[0946] Delivery Area Code Linking:

[0947] The server retrieves the postal code database provided by the mail-order business and the delivery area information provided by the delivery company, and associates each postal code with a corresponding delivery area code. Both databases are used as input, and a list of correspondences between postal codes and delivery area codes is generated as output. Specifically, the server compares these databases using a join operation and periodically updates the latest delivery area information.

[0948] Step 4:

[0949] Delivery availability:

[0950] The server generates a list of affected postal codes based on the disaster information analyzed by the AI ​​model. It uses the delivery area code associated with the disaster information from the analysis as input, and generates a list of postal codes flagged as undeliverable or delayed as output. Specifically, the server loops through the list of affected postal codes and flags each one as undeliverable or deferred.

[0951] Step 5:

[0952] Customer Notice:

[0953] The server checks customer order history and generates a list of customers requesting delivery in the affected areas. It uses customer order history data and a list of affected postal codes as input. It generates a list of customers with information to notify of delivery delays or cancellations as output. Specifically, the server automatically sends delivery delay notifications to each customer using an email sending API or chat notification function.

[0954] This will enable the system to respond quickly and accurately even in the event of a natural disaster, improving customer satisfaction and streamlining logistics.

[0955] (Application example 1)

[0956] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0957] In recent years, the frequent occurrence of natural disasters has increasingly had a major impact on mail-order logistics. This has created a need for fast and accurate notification of delivery status to customers. However, conventional systems are unable to quickly collect and analyze disaster information or determine whether or not delivery can be made, which can lead to a decline in customer satisfaction. Furthermore, the resulting delays and cancellations of logistics are a major issue for businesses. To solve these issues, a system is needed that can efficiently collect and analyze disaster information and quickly notify customers.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0959] In this invention, the server includes means for collecting and analyzing disaster information acquired when a natural disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, and means for sending push notifications to customers via a smartphone application. This makes it possible to notify customers of delivery status quickly and accurately even when a disaster occurs, thereby improving customer satisfaction and streamlining logistics.

[0960] "Natural disaster information" refers to information about disasters collected from disaster reports by the Japan Meteorological Agency and local governments, social media, breaking news, etc.

[0961] "Means of collection and analysis" refers to the system by which data is acquired using a server or related technology, and then analyzed to create usable information.

[0962] A "delivery area code" is a code that indicates whether an item can be delivered to a specific area or postal code.

[0963] A "postal code" is a code consisting of a series of numbers that identifies an area or address.

[0964] The "means for determining whether delivery is possible" is a mechanism that determines whether delivery of goods to a specific area is possible based on collected disaster information.

[0965] "Means of notification" refers to a system for communicating information such as delivery delays or cancellations to customers.

[0966] A "smartphone application" is software that is installed on a smartphone and enables the user to use certain functions.

[0967] "Push notifications" are real-time messages or notifications sent from an application directly to a user's smartphone.

[0968] A "server" is a computer that provides services to other computers and devices on a network.

[0969] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[0970] System Configuration

[0971] The system consists of the following main components:

[0972] 1. Disaster information collection and analysis methods

[0973] When a disaster occurs, the server collects information from public data sources (e.g., disaster reports from the Japan Meteorological Agency and local governments) and private data sources (e.g., social media and breaking news). The server uses generative AI to analyze the collected data and obtain detailed information about the affected area.

[0974] 2. Delivery area code linking method

[0975] The server connects the mail-order company's database with the delivery company's database, and associates each postal code with a corresponding delivery area code, thereby clearly managing which delivery area code a specific postal code corresponds to.

[0976] 3. Means of determining delivery availability

[0977] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the AI. For each postal code, it references the delivery area code and determines whether delivery is possible there.

[0978] 4. Customer Notification Means

[0979] The server generates a list of affected customers based on delivery area information linked to the customer's order history, and notifies each customer of delivery delays or cancellations via email, their personal page, chat, or smartphone application.

[0980] Program processing

[0981] 1. Disaster information collection and analysis

[0982] The server collects the latest disaster information using news APIs, social media APIs, and data from the Japan Meteorological Agency. The generation AI analyzes this information and identifies areas that may be affected by the disaster. For example, "The information obtained by the server reveals that local city A has been hit by heavy rain."

[0983] 2. Linking delivery area codes

[0984] The server obtains the delivery area information provided by the delivery company and compares it with its own postal code database. For example, "Regional city A (postal code 123-4567) is linked to the regional area code."

[0985] 3. Determining whether delivery is possible

[0986] The server generates a list of affected zip codes and flags each shipping area code from that list as undeliverable or delayed, for example, "zip codes 123-4567 will be marked as undeliverable."

[0987] 4. Notice to Customer

[0988] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer via email or smartphone application. For example, "Send a delivery delay notification to customer A via a smartphone application."

[0989] Specific examples

[0990] The server obtains information about the heavy rain disaster in Regional City A from the API, and the generation AI analyzes that information and adds all postal codes in Regional City A to the affected list. Furthermore, the server recognizes Regional City A (postal code 123-4567) as a "regional area" from the delivery company's database and flags the corresponding postal code as undeliverable. Finally, the server extracts the customer list for the corresponding postal code and sends a notification to the smartphone app stating, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[0991] Example prompts for generative AI models

[0992] Heavy rain has hit local city A, affecting the area with zip code 123-4567. Delivery may be delayed or canceled. Please promptly notify customers in the affected area via email and push notifications.

[0993] With these configurations, this system is able to quickly and accurately notify customers of delivery status even in the event of a disaster, thereby improving customer satisfaction and streamlining logistics.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1:

[0996] The server collects disaster information. The server obtains disaster information from public data sources (e.g., the Japan Meteorological Agency, local government disaster reports) and private data sources (e.g., SNS APIs, news APIs). This information includes details such as the type of disaster, the location of the disaster, and the extent of the impact. The input is disaster information from each API, and the output is disaster data that is centrally managed within the server.

[0997] Step 2:

[0998] The disaster information collected by the server is analyzed using a generative AI model. The generative AI model analyzes the collected information and identifies areas that may be affected. Specifically, it uses natural language processing and machine learning algorithms to process text data and generate a list of affected postal codes. The input is the disaster information from Step 1, and the output is the list of affected postal codes.

[0999] Step 3:

[1000] The server links the generated list of postal codes to existing delivery area codes. The server references a database linked to delivery companies to determine which delivery area code corresponds to each postal code. This process determines which delivery area a specific region falls into. The input is the list of postal codes from step 2, and the output is a list of delivery area codes linked to each postal code.

[1001] Step 4:

[1002] The server determines whether delivery is possible. Based on the delivery area code obtained in step 3, the server references the collected and analyzed disaster information to determine whether delivery to that area is possible. A flag is set for each area code to indicate whether delivery will be delayed or canceled. The input is the delivery area code from step 3 and the disaster information from step 2, and the output is a list of area codes with delivery possibility flags.

[1003] Step 5:

[1004] The server checks the customer's order history. The server extracts delivery area information for each customer from the customer database and generates a list of customers who belong to the affected area. Specifically, it extracts and lists the order histories of customers who belong to the affected postal codes. The input is the customer database and the delivery availability flag from step 4, and the output is a list of customers to be notified.

[1005] Step 6:

[1006] The server notifies affected customers. Based on the generated customer list, the server sends notifications to each customer via email or smartphone application. The message contains detailed information about the delivery delay or cancellation and recommended action to take. The input is the list of customers to be notified in step 5, and the output is the notification sent to the customer. For example, the server sends a notification via a smartphone app saying, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[1007] Through the above processing steps, customers can be notified of delivery status quickly and accurately even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[1008] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1009] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[1010] System Configuration

[1011] The present invention comprises the following main components:

[1012] 1. Disaster information collection and analysis methods

[1013] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[1014] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[1015] 2. Delivery area code linking method

[1016] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[1017] This allows for clear management of which delivery area code a particular postal code falls under.

[1018] 3. Means of determining delivery availability

[1019] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[1020] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[1021] 4. Customer Notification Means

[1022] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[1023] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[1024] 5. Emotion Engine

[1025] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[1026] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[1027] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[1028] Program processing

[1029] 1. Disaster information collection and analysis

[1030] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[1031] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[1032] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered flooding damage due to heavy rain."

[1033] 2. Linking delivery area codes

[1034] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[1035] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[1036] 3. Determining whether delivery is possible

[1037] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[1038] For example, "Postal code 123-4567 will be marked as undeliverable."

[1039] 4. Notice to Customer

[1040] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[1041] Notify each customer by email, etc. For example, "Notify customer A by email that delivery of order number ABC123 will be delayed."

[1042] 5. Collecting Emotional Data

[1043] The server collects the user's response to the notification, such as the content of the email reply or the comments on the user's personal page.

[1044] For example, "The server collects reply emails from user B and analyzes their contents."

[1045] 6. Emotional Data Analysis and Response

[1046] The server analyzes the data collected by the emotion engine and evaluates the user's emotional state.

[1047] For example, "The server recognizes from the analysis results that user B is highly dissatisfied."

[1048] Based on the analysis results, the server automatically generates a notification to instruct customer support to take appropriate action, such as "Configure sending of additional follow-up emails to User B, who is very dissatisfied."

[1049] Specific examples

[1050] Disaster information collection and analysis

[1051] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1052] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[1053] Linking delivery area codes

[1054] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[1055] Judgment on delivery availability

[1056] The server flags "123-4567" as undeliverable.

[1057] customer notification

[1058] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1059] Collecting Emotional Data

[1060] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1061] For example, a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[1062] Customer support coordination

[1063] The server determines that the user is extremely dissatisfied and automatically generates and sends a follow-up email.

[1064] For example, "The server will send an additional follow-up email to the user with an apology."

[1065] In this way, the system of the present invention can respond to customers quickly and accurately even in the event of a disaster, and can also respond while taking into consideration the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[1066] The processing flow will be explained below.

[1067] Step 1:

[1068] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[1069] Step 2:

[1070] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[1071] Step 3:

[1072] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[1073] Step 4:

[1074] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[1075] Step 5:

[1076] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[1077] Step 6:

[1078] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[1079] Step 7:

[1080] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[1081] Step 8:

[1082] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[1083] Step 9:

[1084] The server collects emotional data from users who receive notifications. The collected data includes how users reacted to notifications (e.g., the content of reply emails, comments on their personal page, responses in chat, etc.). For example, "User A left a comment on their personal page saying, 'Delays in delivery are a problem.'"

[1085] Step 10:

[1086] The server uses an emotion engine to analyze the collected emotional data and measure the user's level of satisfaction or dissatisfaction. For example, "The server recognizes from User A's comments that User A is very dissatisfied."

[1087] Step 11:

[1088] The server automatically adjusts the content and methods of customer support based on the analysis results, for example, "for highly dissatisfied users, it will automatically generate and send additional follow-up emails or phone calls."

[1089] Step 12:

[1090] The server sends follow-up notifications to the user to improve customer satisfaction. For example, "Send an apology email to User A, and notify customer support if further action is required."

[1091] In this way, the system of the present invention, through a series of processing steps, can respond to customers quickly and accurately even in the event of a natural disaster, and can respond while taking into account the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[1092] Example 2

[1093] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1094] In conventional mail order systems, it was difficult to provide fast and accurate information on delivery availability in the event of a natural disaster, resulting in problems such as a decline in customer satisfaction and logistics disruptions. Furthermore, there was a lack of consideration for customer feelings, making it difficult to provide appropriate follow-up for dissatisfied customers.

[1095] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1096] In this invention, the server includes means for collecting and analyzing disaster information acquired when a disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotion data and optimizing customer service, means for analyzing disaster information using a generative AI model, and means for collecting natural disaster information from public and private data sources. This makes it possible to quickly and accurately provide delivery possibility information even when a natural disaster occurs, and to respond in consideration of the emotional state of the customer.

[1097] The "disaster information collection and analysis means" is a device that collects disaster information from public and private data sources when a disaster occurs and analyzes it using a generative AI model.

[1098] A "delivery area code" is a unique code for identifying each delivery area, and is an identifier used to associate with a postal code.

[1099] A "postal code" is a unique number that represents a specific region or area, and is an identifier linked to a delivery area code.

[1100] The "delivery possibility determination means" is a device that determines whether delivery is possible to a specific delivery area or postal code based on the collected and analyzed disaster information.

[1101] The "customer notification means" is a device that notifies the customer of the information on whether delivery is possible or not using an appropriate means (e.g., email, personal page, chat).

[1102] The "emotion data collection and analysis means" is a device that collects the reactions shown by customers to notifications and analyzes their emotional state using an emotion engine.

[1103] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze disaster information and emotional data.

[1104] "Public data sources" are data provided by public institutions such as the Japan Meteorological Agency and local government disaster reports.

[1105] "Private data sources" are data provided by private companies such as social media and breaking news.

[1106] An "emotion engine" is an artificial intelligence system that analyzes the emotional state of customers and is used to optimize customer service.

[1107] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[1108] The present invention comprises the following main components:

[1109] 1. Disaster information collection and analysis methods

[1110] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[1111] The server uses a generative AI model to analyze the collected data and obtain detailed information about the affected area.

[1112] 2. Delivery area code linking method

[1113] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[1114] This allows for clear management of which delivery area code a particular postal code falls under.

[1115] 3. Means of determining delivery availability

[1116] The server generates a list of postal codes for affected areas based on disaster information analyzed by the generative AI model.

[1117] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[1118] 4. Customer Notification Means

[1119] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[1120] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[1121] 5. Emotion Engine

[1122] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[1123] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[1124] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[1125] Specific examples

[1126] Disaster information collection and analysis

[1127] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1128] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[1129] Linking delivery area codes

[1130] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[1131] Judgment on delivery availability

[1132] The server flags Shinagawa-ku (zip code 123-4567) as undeliverable.

[1133] customer notification

[1134] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1135] Collecting Emotional Data

[1136] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1137] For example, suppose that a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[1138] Customer support coordination

[1139] The server determines that the user is very dissatisfied and automatically generates and sends a follow-up email.

[1140] For example, "The server will send an additional follow-up email to the user with an apology."

[1141] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1142] Step 1:

[1143] The server calls data from news APIs, SNS APIs, and the Japan Meteorological Agency to collect the latest disaster information. Specifically, it uses an API key to access each data source and obtain new disaster information. The obtained data is stored on the server in formats such as JSON and XML. The input is the API endpoint and key, and the output is a dataset of disaster information.

[1144] Step 2:

[1145] The server inputs the collected disaster information into a generative AI model to identify affected areas. Specifically, the data is preprocessed and converted into a format suitable for the model, and then input into the model. A list of affected areas is generated and output. The input is the preprocessed disaster information data, and the output is a list of affected postal codes.

[1146] Step 3:

[1147] The server accesses the delivery company's database to obtain delivery area information. Specifically, it uses an SQL query to extract delivery area data. It then compares the obtained delivery area information with its own postal code database and sets the delivery area code corresponding to each postal code. The input is the delivery company's area database, and the output is a mapping between postal codes and area codes.

[1148] Step 4:

[1149] The server uses the generated list of postal codes in disaster-affected areas to refer to the delivery area code for each postal code and determine whether delivery is possible. Specifically, it uses mapping data between postal codes and area codes to identify affected areas. The input is the list of disaster-affected areas and the mapping data between postal codes and area codes, and the output is a list with a flag indicating whether delivery is possible or not.

[1150] Step 5:

[1151] The server generates a list of customers in the affected areas based on their order history. Specifically, it extracts order data linked to affected postal codes and creates a list of affected customers. The input is a list of postal codes in the affected areas and an order history database, and the output is a list of affected customers.

[1152] Step 6:

[1153] The server notifies each customer whether delivery is possible or not using email, My Page, chat, etc. Specifically, it sends email using an SMTP server or calls a chatbot API to notify. The input is a list of customers to be notified and the notification content, and the output is a notification message to each customer.

[1154] Step 7:

[1155] The server collects the reactions of users who received the notifications. Specifically, it analyzes the logs of the mail server and web server to extract user feedback. The input is each user's notification message and their reaction data (email replies, personal page comments, etc.), and the output is the collected feedback data.

[1156] Step 8:

[1157] The server analyzes the collected feedback data using an emotion engine and evaluates the user's emotional state. Specifically, it performs text sentiment analysis using natural language processing technology to measure dissatisfaction and satisfaction. The input is the collected feedback data, and the output is the evaluation result of the user's emotional state.

[1158] Step 9:

[1159] The server determines the customer support response based on the sentiment analysis results and automatically sets the appropriate action. Specifically, it executes a script that generates and sends a follow-up email. The input is the sentiment analysis results and the follow-up content, and the output is a follow-up message to the user.

[1160] (Application example 2)

[1161] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1162] When a natural disaster occurs, mail-order sales systems must quickly and accurately provide customers with information on whether or not delivery is possible. However, in many cases, collecting disaster information and determining whether or not delivery is possible is done manually, which takes time and effort and can result in delays in customer response. Furthermore, a uniform response that ignores the customer's emotional state can lead to a decrease in customer satisfaction. In response to this, the objective of this invention is to provide customer support that automatically collects and analyzes disaster information and takes into account the customer's emotional state.

[1163] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing disaster information obtained when a natural disaster occurs, means for linking deliverable area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotional data, and means for adjusting responses according to the customer's emotional state. This makes it possible to quickly and accurately provide customers with information on whether delivery is possible even when a disaster occurs, and to respond flexibly in accordance with the customer's emotional state.

[1164] "Natural disaster information" refers to information on natural disasters such as earthquakes, floods, typhoons, and heavy rains obtained from public and private data sources.

[1165] "Disaster information collection and analysis means" is a function for collecting and analyzing disaster information from various data sources when a natural disaster occurs.

[1166] A "delivery area code" is a code that indicates whether delivery is possible in a specific area, and is linked to a postal code.

[1167] The "means for determining whether delivery is possible" is a function that determines whether delivery is possible to a specific area based on collected and analyzed disaster information.

[1168] "Customer notification means" refers to a means for informing customers of the availability of delivery, and includes communication means such as email and messages.

[1169] "Emotional data" is data that indicates the emotional state of a customer, collected from their reactions and opinions.

[1170] "Emotional data collection and analysis means" is a function for collecting customer reaction data and analyzing it to evaluate the emotional state of the customer.

[1171] The "response adjustment means" is a function for adjusting the customer support response in accordance with the analyzed emotional state of the customer.

[1172] The present invention is a system that utilizes AI technology to provide customers with prompt and accurate delivery availability information regarding the operation of a mail-order sales system in the event of a natural disaster. Furthermore, by combining it with an emotion engine, it also includes a function to recognize the user's emotional state and improve the quality of customer service. Specific embodiments of the system are described below.

[1173] First, as a means of collecting and analyzing disaster information, the server collects the latest disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The collected information is analyzed by a generative AI model using TensorFlow to identify areas that may be affected by the disaster.

[1174] Next, to link delivery area codes with postal codes, the server retrieves delivery area information provided by the delivery company's database and compares it with its own postal code database. This process is performed using a backend system using Django.

[1175] As a means of determining whether delivery is possible based on the collected and analyzed disaster information, the server generates a list of postal codes in the affected areas and, based on that list, sets a flag for each postal code indicating that delivery should be canceled or delayed.

[1176] The customer notification system reviews customer order history and generates a list of customers requesting delivery in the affected area. This list of customers will be notified of delivery delays or cancellations via email or message using communication methods such as Twilio.

[1177] Furthermore, as a means of collecting and analyzing emotional data, the server collects the reactions of customers who receive notifications. This reaction data includes email replies, comments on their personal pages, and responses in chat. The collected emotional data is then analyzed again using TensorFlow to evaluate the customer's emotional state.

[1178] Finally, as a means of adjusting responses according to the customer's emotional state, the server automatically adjusts the content and methods of customer support responses based on the analysis results. For example, if a customer is highly dissatisfied, additional follow-up emails or special coupon offers will be automatically generated and sent. This series of processes enables quick and accurate responses even in the event of a disaster, improving customer satisfaction.

[1179] Specific examples

[1180] 1. Disaster information collection and analysis

[1181] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1182] The generating AI will analyze that information and add all postal codes in Shinagawa Ward to the affected list.

[1183] 2. Linking delivery area codes

[1184] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[1185] 3. Determining whether delivery is possible

[1186] The server flags "zip code 123-4567" as undeliverable.

[1187] 4. Customer Notification

[1188] The server extracts the list of customers with the relevant postal code and sends a notification email stating that "Delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1189] 5. Collecting Emotional Data

[1190] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1191] 6. Customer Support Coordination

[1192] If the user is determined to be highly dissatisfied, a follow-up email containing a special coupon will be sent.

[1193] Prompt Sentence Examples

[1194] 1. Prompts for disaster information collection and analysis

[1195] "Based on the latest heavy rain information obtained from the Japan Meteorological Agency API, identify the affected area in Shinagawa Ward, Tokyo."

[1196] 2. Input prompt sentence to emotion engine

[1197] "Analyze this email response to assess the customer's level of dissatisfaction and emotional state."

[1198] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1199] Step 1:

[1200] The server collects natural disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The input data is disaster information from each API and is stored on the server. This collected data is stored on the server in its raw form.

[1201] Step 2:

[1202] The server analyzes the collected disaster information using a generative AI model powered by TensorFlow. The input data is the disaster information collected in step 1, and through analysis, potentially affected areas are identified. The output data is a list of affected areas, including detailed information about the identified areas.

[1203] Step 3:

[1204] The server retrieves delivery area information from the delivery company's database and compares it with its own postal code database. The input data is the delivery company's delivery area information and the company's postal code information, and by comparing these, a delivery area code corresponding to each postal code is generated. The output data is a pair of the matched delivery area code and postal code.

[1205] Step 4:

[1206] The server determines whether delivery is possible or not based on the generated affected area list and delivery area code. The input data is a pair of the affected area list and delivery area code, and based on that, it determines whether delivery is possible (or not) for each specific postal code. The output data is a flag set for each postal code indicating whether delivery has been canceled or delayed.

[1207] Step 5:

[1208] The server checks customer order history and generates a list of customers requesting delivery to the affected area. The input data is customer order history and delivery area information, and the affected customer list is created based on these. The output data is the affected customer list.

[1209] Step 6:

[1210] The server uses a communication method such as Twilio to notify affected customers by email or message. The input data is a list of affected customers and delivery availability information, and individual notifications are sent to each customer based on that. The output data is a record of the notifications sent to customers.

[1211] Step 7:

[1212] The user receives a delivery success or failure notification from the server. The input data is the notification sent from the server, which the user confirms. The output data is the user's confirmation and their reaction (for example, a reply to an email or a comment on their personal page).

[1213] Step 8:

[1214] The server collects the user's reactions upon receiving the notification and analyzes them using an emotion engine. The input data is the user's reactions (email replies, comments on their personal page, etc.), which are analyzed by the emotion engine using TensorFlow. The output data is the evaluation results regarding the customer's emotional state.

[1215] Step 9:

[1216] The server adjusts customer support responses based on the results of sentiment analysis. The input data are the sentiment analysis results and customer support response patterns, and based on these, responses tailored to specific customers (for example, generating follow-up emails or special coupons) are automatically generated. The output data is the automatically generated customer response actions.

[1217] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1218] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1219] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1220] [Fourth embodiment]

[1221] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1222] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1223] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1224] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1225] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1227] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1228] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1229] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1230] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1231] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1232] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1233] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1234] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[1235] System Configuration

[1236] The present invention comprises the following main components:

[1237] 1. Disaster information collection and analysis methods

[1238] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[1239] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[1240] 2. Delivery area code linking method

[1241] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[1242] This allows for clear management of which delivery area code a particular postal code falls under.

[1243] 3. Means of determining delivery availability

[1244] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[1245] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[1246] 4. Customer Notification Means

[1247] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[1248] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[1249] Program processing

[1250] 1. Disaster information collection and analysis

[1251] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[1252] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[1253] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered damage from heavy rain."

[1254] 2. Linking delivery area codes

[1255] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[1256] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[1257] 3. Determining whether delivery is possible

[1258] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[1259] For example, "Postal code 123-4567 will be marked as undeliverable."

[1260] 4. Notice to Customer

[1261] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[1262] Notify each customer by email, etc. For example, "Send a delivery delay notification to customer A by email."

[1263] Specific examples

[1264] Disaster information collection and analysis

[1265] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1266] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[1267] Linking delivery area codes

[1268] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[1269] Judgment on delivery availability

[1270] The server flags "123-4567" as undeliverable.

[1271] customer notification

[1272] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1273] This system will enable mail-order businesses to respond to customers quickly and accurately even during natural disasters, improving customer satisfaction and streamlining logistics.

[1274] The processing flow will be explained below.

[1275] Step 1:

[1276] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[1277] Step 2:

[1278] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[1279] Step 3:

[1280] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[1281] Step 4:

[1282] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[1283] Step 5:

[1284] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[1285] Step 6:

[1286] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[1287] Step 7:

[1288] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[1289] Step 8:

[1290] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[1291] Step 9:

[1292] The server checks whether the notification was sent successfully and determines whether it needs to be sent again. If the notification is not received, it will try to notify the customer by other means (e.g., SMS, phone call) to improve the accuracy of customer support.

[1293] In this way, the system of the present invention, through a series of processing steps, enables quick and accurate response to customers even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[1294] Example 1

[1295] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1296] When a natural disaster occurs, it is difficult for mail order businesses to quickly and accurately provide customers with information about whether or not their deliveries will be successful. In particular, when the disaster has a wide impact, it is difficult to immediately assess the situation in each region and provide appropriate notifications. As a result, customers often become dissatisfied because they are unable to properly grasp information about delivery delays or cancellations.

[1297] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1298] In this invention, the server includes means for collecting disaster information from public and private data sources, means for analyzing the collected disaster information using a generative AI model, means for linking delivery area codes with multiple postal codes, means for generating a list of affected postal codes based on the analyzed disaster information and determining whether delivery is possible for each delivery area code, and means for generating a list of affected customers based on delivery area information linked to customer order history and notifying them by means of email, chat, etc. This enables mail-order businesses to quickly and accurately provide customers with delivery possibility information even during natural disasters.

[1299] "Official data sources" are official sources of information provided by government agencies or local governments.

[1300] "Private data sources" are information sources provided by private organizations and individuals, such as news media and social media.

[1301] "Disaster information" refers to specific data and reports on natural disasters, such as the extent of damage, the extent of impact, and the location of the disaster.

[1302] A "generative AI model" is an artificial intelligence model that is trained using machine learning to perform a specific task.

[1303] "Analysis" is the process of identifying the scale and scope of a disaster based on collected data.

[1304] A "delivery area code" is a code that indicates a certain area and is used to determine whether delivery is possible within that area.

[1305] "Postal Codes" are a series of numbers used to designate a particular area and are utilized to uniquely identify multiple areas.

[1306] A "delivery area code" is a code that identifies a delivery area and includes multiple postal codes.

[1307] "Delivery availability" is a status indicating whether delivery is possible to a specific area.

[1308] "Customer" means a person who purchases goods or services.

[1309] "Order History" refers to a record of past orders placed by a customer.

[1310] "Delivery area information" is information relating to the area to be delivered.

[1311] The "list of affected customers" is a list of customers whose deliveries may be affected, identified based on disaster information.

[1312] "Notification" is the act of informing someone of information, and is done via email, chat, etc.

[1313] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that uses AI technology to provide customers with fast and accurate information on whether delivery is possible. This system has a multi-functional configuration that collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[1314] 1. Collecting disaster information

[1315] The server collects disaster information from public and private data sources. To do this, it uses the Japan Meteorological Agency's API, SNS API, and news API. Specifically, the server accesses these APIs every hour and runs a regular job to obtain the latest disaster data. This information is used as basic data for quickly understanding the disaster situation.

[1316] 2. Disaster Information Analysis

[1317] The server uses the generative AI model to analyze the acquired disaster data. This analysis makes it possible to identify the scale of the disaster, the extent of the impact, and the affected areas. Specifically, the server creates a prompt for the generative AI model, inputs it into the AI ​​model, and obtains the analysis results. For example, "The server analyzes the information acquired by the generative AI and identifies that Shinagawa Ward and surrounding areas in Tokyo are affected by heavy rain."

[1318] 3. Linking delivery area codes

[1319] The server checks the databases provided by the mail-order business and the delivery company. It links each postal code with a corresponding delivery area code, and this is how delivery areas are managed. Specifically, the server periodically performs a database join operation to obtain the latest delivery area information. For example, "The server links Shinagawa Ward (postal code 123-4567) to the area code for Tokyo's 23 wards."

[1320] 4. Delivery Determination

[1321] The server generates a list of affected postal codes based on the disaster information analyzed by the AI. Based on this list, it sets a flag for delivery suspension or delay for each delivery area code. For example, "The server sets a flag for delivery ineligible for the area with postal codes 123-4567." Specifically, the server loops through the postal code list and sets a delivery flag for each postal code.

[1322] 5. Notice to Customer

[1323] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer of delivery delays or cancellations using methods such as email, personal pages, and chat. For example, the server might "send an email to customer A notifying them of a delivery delay." Specifically, the server uses an email sending API to automatically send an email with the specified content.

[1324] Examples:

[1325] Disaster information collection:

[1326] The server accesses the Japan Meteorological Agency API at 9:00 a.m. and obtains information about the heavy rain disaster in Shinagawa Ward, Tokyo.

[1327] Disaster information analysis:

[1328] The server inputs the acquired heavy rain information into the generation AI, which analyzes and determines that all postal codes in Shinagawa Ward are affected.

[1329] Delivery Area Code Linking:

[1330] The server recognizes Shinagawa Ward (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[1331] Delivery availability:

[1332] The server flags "123-4567" as undeliverable.

[1333] Customer Notice:

[1334] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1335] Example prompt sentence:

[1336] "Please collect the latest disaster information. Use the Japan Meteorological Agency API, news API, and SNS API to obtain disaster information affecting the 23 wards of Tokyo, and analyze it to identify which areas are affected."

[1337] This will enable the system to respond quickly and accurately even in the event of a natural disaster, contributing to improved customer satisfaction and more efficient logistics.

[1338] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1339] Step 1:

[1340] Disaster information collection:

[1341] The server collects the latest disaster information from public data sources (such as the Japan Meteorological Agency API) and private data sources (such as news APIs and SNS APIs). It uses the API endpoints and necessary authentication information as input, and obtains the latest disaster information data as output. Specifically, the server runs a periodic job that accesses these APIs every hour and retrieves the latest disaster data in JSON format.

[1342] Step 2:

[1343] Disaster information analysis:

[1344] The disaster information acquired by the server is input into a generative AI model, which then obtains the analysis results. This generative AI model uses natural language processing technology to identify the scale, extent of impact, and affected areas of the disaster. As input, the acquired disaster information data is converted into prompt statements, which are then input into the generative AI model. As output, the affected areas of the disaster and detailed information about them are obtained. For example, it generates information such as "Shinagawa Ward, Tokyo, has suffered damage from heavy rain."

[1345] Step 3:

[1346] Delivery Area Code Linking:

[1347] The server retrieves the postal code database provided by the mail-order business and the delivery area information provided by the delivery company, and associates each postal code with a corresponding delivery area code. Both databases are used as input, and a list of correspondences between postal codes and delivery area codes is generated as output. Specifically, the server compares these databases using a join operation and periodically updates the latest delivery area information.

[1348] Step 4:

[1349] Delivery availability:

[1350] The server generates a list of affected postal codes based on the disaster information analyzed by the AI ​​model. It uses the delivery area code associated with the disaster information from the analysis as input, and generates a list of postal codes flagged as undeliverable or delayed as output. Specifically, the server loops through the list of affected postal codes and flags each one as undeliverable or deferred.

[1351] Step 5:

[1352] Customer Notice:

[1353] The server checks customer order history and generates a list of customers requesting delivery in the affected areas. It uses customer order history data and a list of affected postal codes as input. It generates a list of customers with information to notify of delivery delays or cancellations as output. Specifically, the server automatically sends delivery delay notifications to each customer using an email sending API or chat notification function.

[1354] This will enable the system to respond quickly and accurately even in the event of a natural disaster, improving customer satisfaction and streamlining logistics.

[1355] (Application example 1)

[1356] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1357] In recent years, the frequent occurrence of natural disasters has increasingly had a major impact on mail-order logistics. This has created a need for fast and accurate notification of delivery status to customers. However, conventional systems are unable to quickly collect and analyze disaster information or determine whether or not delivery can be made, which can lead to a decline in customer satisfaction. Furthermore, the resulting delays and cancellations of logistics are a major issue for businesses. To solve these issues, a system is needed that can efficiently collect and analyze disaster information and quickly notify customers.

[1358] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1359] In this invention, the server includes means for collecting and analyzing disaster information acquired when a natural disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, and means for sending push notifications to customers via a smartphone application. This makes it possible to notify customers of delivery status quickly and accurately even when a disaster occurs, thereby improving customer satisfaction and streamlining logistics.

[1360] "Natural disaster information" refers to information about disasters collected from disaster reports by the Japan Meteorological Agency and local governments, social media, breaking news, etc.

[1361] "Means of collection and analysis" refers to the system by which data is acquired using a server or related technology, and then analyzed to create usable information.

[1362] A "delivery area code" is a code that indicates whether an item can be delivered to a specific area or postal code.

[1363] A "postal code" is a code consisting of a series of numbers that identifies an area or address.

[1364] The "means for determining whether delivery is possible" is a mechanism that determines whether delivery of goods to a specific area is possible based on collected disaster information.

[1365] "Means of notification" refers to a system for communicating information such as delivery delays or cancellations to customers.

[1366] A "smartphone application" is software that is installed on a smartphone and enables the user to use certain functions.

[1367] "Push notifications" are real-time messages or notifications sent from an application directly to a user's smartphone.

[1368] A "server" is a computer that provides services to other computers and devices on a network.

[1369] This invention relates to the operation of mail-order sales systems in the event of a natural disaster, and is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible. This multi-functional system collects and analyzes disaster information, links delivery area codes, determines whether delivery is possible, and notifies customers.

[1370] System Configuration

[1371] The system consists of the following main components:

[1372] 1. Disaster information collection and analysis methods

[1373] When a disaster occurs, the server collects information from public data sources (e.g., disaster reports from the Japan Meteorological Agency and local governments) and private data sources (e.g., social media and breaking news). The server uses generative AI to analyze the collected data and obtain detailed information about the affected area.

[1374] 2. Delivery area code linking method

[1375] The server connects the mail-order company's database with the delivery company's database, and associates each postal code with a corresponding delivery area code, thereby clearly managing which delivery area code a specific postal code corresponds to.

[1376] 3. Means of determining delivery availability

[1377] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the AI. For each postal code, it references the delivery area code and determines whether delivery is possible there.

[1378] 4. Customer Notification Means

[1379] The server generates a list of affected customers based on delivery area information linked to the customer's order history, and notifies each customer of delivery delays or cancellations via email, their personal page, chat, or smartphone application.

[1380] Program processing

[1381] 1. Disaster information collection and analysis

[1382] The server collects the latest disaster information using news APIs, social media APIs, and data from the Japan Meteorological Agency. The generation AI analyzes this information and identifies areas that may be affected by the disaster. For example, "The information obtained by the server reveals that local city A has been hit by heavy rain."

[1383] 2. Linking delivery area codes

[1384] The server obtains the delivery area information provided by the delivery company and compares it with its own postal code database. For example, "Regional city A (postal code 123-4567) is linked to the regional area code."

[1385] 3. Determining whether delivery is possible

[1386] The server generates a list of affected zip codes and flags each shipping area code from that list as undeliverable or delayed, for example, "zip codes 123-4567 will be marked as undeliverable."

[1387] 4. Notice to Customer

[1388] The server checks customer order history and generates a list of customers requesting delivery in the affected area. It notifies each customer via email or smartphone application. For example, "Send a delivery delay notification to customer A via a smartphone application."

[1389] Specific examples

[1390] The server obtains information about the heavy rain disaster in Regional City A from the API, and the generation AI analyzes that information and adds all postal codes in Regional City A to the affected list. Furthermore, the server recognizes Regional City A (postal code 123-4567) as a "regional area" from the delivery company's database and flags the corresponding postal code as undeliverable. Finally, the server extracts the customer list for the corresponding postal code and sends a notification to the smartphone app stating, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[1391] Example prompts for generative AI models

[1392] Heavy rain has hit local city A, affecting the area with zip code 123-4567. Delivery may be delayed or canceled. Please promptly notify customers in the affected area via email and push notifications.

[1393] With these configurations, this system is able to quickly and accurately notify customers of delivery status even in the event of a disaster, thereby improving customer satisfaction and streamlining logistics.

[1394] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1395] Step 1:

[1396] The server collects disaster information. The server obtains disaster information from public data sources (e.g., the Japan Meteorological Agency, local government disaster reports) and private data sources (e.g., SNS APIs, news APIs). This information includes details such as the type of disaster, the location of the disaster, and the extent of the impact. The input is disaster information from each API, and the output is disaster data that is centrally managed within the server.

[1397] Step 2:

[1398] The disaster information collected by the server is analyzed using a generative AI model. The generative AI model analyzes the collected information and identifies areas that may be affected. Specifically, it uses natural language processing and machine learning algorithms to process text data and generate a list of affected postal codes. The input is the disaster information from Step 1, and the output is the list of affected postal codes.

[1399] Step 3:

[1400] The server links the generated list of postal codes to existing delivery area codes. The server references a database linked to delivery companies to determine which delivery area code corresponds to each postal code. This process determines which delivery area a specific region falls into. The input is the list of postal codes from step 2, and the output is a list of delivery area codes linked to each postal code.

[1401] Step 4:

[1402] The server determines whether delivery is possible. Based on the delivery area code obtained in step 3, the server references the collected and analyzed disaster information to determine whether delivery to that area is possible. A flag is set for each area code to indicate whether delivery will be delayed or canceled. The input is the delivery area code from step 3 and the disaster information from step 2, and the output is a list of area codes with delivery possibility flags.

[1403] Step 5:

[1404] The server checks the customer's order history. The server extracts delivery area information for each customer from the customer database and generates a list of customers who belong to the affected area. Specifically, it extracts and lists the order histories of customers who belong to the affected postal codes. The input is the customer database and the delivery availability flag from step 4, and the output is a list of customers to be notified.

[1405] Step 6:

[1406] The server notifies affected customers. Based on the generated customer list, the server sends notifications to each customer via email or smartphone application. The message contains detailed information about the delivery delay or cancellation and recommended action to take. The input is the list of customers to be notified in step 5, and the output is the notification sent to the customer. For example, the server sends a notification via a smartphone app saying, "Delivery of order number XYZ123 (destination: Regional City A 123-4567) will be delayed."

[1407] Through the above processing steps, customers can be notified of delivery status quickly and accurately even in the event of a natural disaster, thereby improving customer satisfaction and streamlining logistics.

[1408] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1409] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[1410] System Configuration

[1411] The present invention comprises the following main components:

[1412] 1. Disaster information collection and analysis methods

[1413] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[1414] The server uses generative AI to analyze the collected data and obtain detailed information about the affected areas.

[1415] 2. Delivery area code linking method

[1416] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[1417] This allows for clear management of which delivery area code a particular postal code falls under.

[1418] 3. Means of determining delivery availability

[1419] The server generates a list of postal codes for affected areas based on the disaster information analyzed by the generation AI.

[1420] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[1421] 4. Customer Notification Means

[1422] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[1423] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[1424] 5. Emotion Engine

[1425] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[1426] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[1427] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[1428] Program processing

[1429] 1. Disaster information collection and analysis

[1430] The server collects the latest disaster information using news APIs, SNS APIs, and data from the Japan Meteorological Agency.

[1431] The generative AI analyzes this information and identifies areas that may be affected by disasters.

[1432] For example, "The information obtained by the server reveals that Shinagawa Ward in Tokyo has suffered flooding damage due to heavy rain."

[1433] 2. Linking delivery area codes

[1434] The server retrieves the delivery area information provided by the delivery company and compares it with its own postal code database.

[1435] For example, "Shinagawa Ward (postal code 123-4567) is linked to the Tokyo 23 Wards area code."

[1436] 3. Determining whether delivery is possible

[1437] The server generates a list of affected postal codes and flags each delivery area code as either halted or delayed from that list.

[1438] For example, "Postal code 123-4567 will be marked as undeliverable."

[1439] 4. Notice to Customer

[1440] The server reviews customer order histories and generates a list of customers requesting delivery in the affected area.

[1441] Notify each customer by email, etc. For example, "Notify customer A by email that delivery of order number ABC123 will be delayed."

[1442] 5. Collecting Emotional Data

[1443] The server collects the user's response to the notification, such as the content of the email reply or the comments on the user's personal page.

[1444] For example, "The server collects reply emails from user B and analyzes their contents."

[1445] 6. Emotional Data Analysis and Response

[1446] The server analyzes the data collected by the emotion engine and evaluates the user's emotional state.

[1447] For example, "The server recognizes from the analysis results that user B is highly dissatisfied."

[1448] Based on the analysis results, the server automatically generates a notification to instruct customer support to take appropriate action, such as "Configure sending of additional follow-up emails to User B, who is very dissatisfied."

[1449] Specific examples

[1450] Disaster information collection and analysis

[1451] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1452] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[1453] Linking delivery area codes

[1454] The server recognizes Shinagawa Ward, Tokyo (postal code 123-4567) as one of the 23 wards of Tokyo from the delivery company's database.

[1455] Judgment on delivery availability

[1456] The server flags "123-4567" as undeliverable.

[1457] customer notification

[1458] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1459] Collecting Emotional Data

[1460] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1461] For example, a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[1462] Customer support coordination

[1463] The server determines that the user is extremely dissatisfied and automatically generates and sends a follow-up email.

[1464] For example, "The server will send an additional follow-up email to the user with an apology."

[1465] In this way, the system of the present invention can respond to customers quickly and accurately even in the event of a disaster, and can also respond while taking into consideration the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[1466] The processing flow will be explained below.

[1467] Step 1:

[1468] To link delivery area codes, the server obtains delivery area information provided by the delivery company. The delivery area information includes the postal code of each region and its corresponding delivery area code. By linking this information with the mail-order business's database, it is possible to clearly manage the delivery area code corresponding to a specific postal code.

[1469] Step 2:

[1470] The server uses the generation AI to collect the latest information when a natural disaster occurs from multiple data sources, including news APIs, social media APIs, and data from the Japan Meteorological Agency. The server periodically calls these APIs to collect the latest disaster information.

[1471] Step 3:

[1472] The server analyzes the collected disaster information using a generation AI to identify affected areas. The generation AI analyzes the text data of the disaster information to determine which areas are affected and to what extent. For example, it analyzes and identifies information such as "Shinagawa Ward, Tokyo, is suffering from flooding damage due to heavy rain."

[1473] Step 4:

[1474] The server generates a list of affected postal codes based on the analysis results. It compiles the postal codes of the identified areas and lists which areas will be affected by deliveries. For example, "List the postal codes for the entire Shinagawa Ward."

[1475] Step 5:

[1476] The server checks the list of affected postal codes against the available delivery area codes. It checks which delivery area codes correspond to each postal code and identifies the affected delivery area codes. For example, "Postal code 123-4567 corresponds to the delivery area code Tokyo 23 Wards."

[1477] Step 6:

[1478] The server determines whether delivery is possible for the identified delivery area code. It flags the affected area codes as undeliverable or delayed. For example, "it flags the area codes of the 23 wards of Tokyo as undeliverable."

[1479] Step 7:

[1480] The server checks the delivery area information linked to the customer's order history and generates a list of affected customers. It accesses the order history database and checks whether the delivery destination of each order is included in the affected area. For example, "Since the delivery destination for order number ABC123 is 123-4567, Shinagawa-ku, this order will also be affected."

[1481] Step 8:

[1482] The server notifies affected customers. Notification methods include email, personal pages, and chat, and sends information about delivery delays and cancellations to each customer. For example, "Customer A is notified by email that delivery of order number ABC123 will be delayed."

[1483] Step 9:

[1484] The server collects emotional data from users who receive notifications. The collected data includes how users reacted to notifications (e.g., the content of reply emails, comments on their personal page, responses in chat, etc.). For example, "User A left a comment on their personal page saying, 'Delays in delivery are a problem.'"

[1485] Step 10:

[1486] The server uses an emotion engine to analyze the collected emotional data and measure the user's level of satisfaction or dissatisfaction. For example, "The server recognizes from User A's comments that User A is very dissatisfied."

[1487] Step 11:

[1488] The server automatically adjusts the content and methods of customer support based on the analysis results, for example, "for highly dissatisfied users, it will automatically generate and send additional follow-up emails or phone calls."

[1489] Step 12:

[1490] The server sends follow-up notifications to the user to improve customer satisfaction. For example, "Send an apology email to User A, and notify customer support if further action is required."

[1491] In this way, the system of the present invention, through a series of processing steps, can respond to customers quickly and accurately even in the event of a natural disaster, and can respond while taking into account the emotional state of the customer, thereby improving customer satisfaction and streamlining logistics.

[1492] Example 2

[1493] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1494] In conventional mail order systems, it was difficult to provide fast and accurate information on delivery availability in the event of a natural disaster, resulting in problems such as a decline in customer satisfaction and logistics disruptions. Furthermore, there was a lack of consideration for customer feelings, making it difficult to provide appropriate follow-up for dissatisfied customers.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1496] In this invention, the server includes means for collecting and analyzing disaster information acquired when a disaster occurs, means for linking delivery area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotion data and optimizing customer service, means for analyzing disaster information using a generative AI model, and means for collecting natural disaster information from public and private data sources. This makes it possible to quickly and accurately provide delivery possibility information even when a natural disaster occurs, and to respond in consideration of the emotional state of the customer.

[1497] The "disaster information collection and analysis means" is a device that collects disaster information from public and private data sources when a disaster occurs and analyzes it using a generative AI model.

[1498] A "delivery area code" is a unique code for identifying each delivery area, and is an identifier used to associate with a postal code.

[1499] A "postal code" is a unique number that represents a specific region or area, and is an identifier linked to a delivery area code.

[1500] The "delivery possibility determination means" is a device that determines whether delivery is possible to a specific delivery area or postal code based on the collected and analyzed disaster information.

[1501] The "customer notification means" is a device that notifies the customer of the information on whether delivery is possible or not using an appropriate means (e.g., email, personal page, chat).

[1502] The "emotion data collection and analysis means" is a device that collects the reactions shown by customers to notifications and analyzes their emotional state using an emotion engine.

[1503] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze disaster information and emotional data.

[1504] "Public data sources" are data provided by public institutions such as the Japan Meteorological Agency and local government disaster reports.

[1505] "Private data sources" are data provided by private companies such as social media and breaking news.

[1506] An "emotion engine" is an artificial intelligence system that analyzes the emotional state of customers and is used to optimize customer service.

[1507] This invention is a system that utilizes AI technology to provide customers with fast and accurate information on whether delivery is possible, related to the operation of mail-order sales systems during natural disasters. Furthermore, by combining it with an emotion engine, it is equipped with a function that recognizes the user's emotional state and improves the quality of customer service. This system is comprised of multiple functional elements, including the collection and analysis of disaster information, linking to delivery area codes, determining whether delivery is possible, notifying customers, and optimizing customer service using the emotion engine.

[1508] The present invention comprises the following main components:

[1509] 1. Disaster information collection and analysis methods

[1510] When a disaster occurs, the server collects information from public data sources (e.g., the Japan Meteorological Agency, disaster reports from local governments) and private data sources (e.g., social media, breaking news).

[1511] The server uses a generative AI model to analyze the collected data and obtain detailed information about the affected area.

[1512] 2. Delivery area code linking method

[1513] The server connects the mail-order business's database with the delivery company's database, linking each postal code to a corresponding delivery area code.

[1514] This allows for clear management of which delivery area code a particular postal code falls under.

[1515] 3. Means of determining delivery availability

[1516] The server generates a list of postal codes for affected areas based on disaster information analyzed by the generative AI model.

[1517] For each postal code, the delivery area code is referenced to determine whether delivery is possible there.

[1518] 4. Customer Notification Means

[1519] The server generates a list of affected customers based on delivery area information linked to the customer's order history.

[1520] The server notifies each customer of delivery delays or cancellations using means such as email, personal pages, or chat.

[1521] 5. Emotion Engine

[1522] The server collects emotional data from users who receive notifications, including data on how users react to notifications (e.g., the content of reply emails, comments on their personal pages, and responses in chat).

[1523] The server uses an emotion engine to analyze the collected emotion data and measure the user's level of satisfaction or dissatisfaction.

[1524] The server then automatically adjusts the content and methods of customer support based on the analysis results, for example automatically generating additional follow-up emails or phone calls for highly dissatisfied users.

[1525] Specific examples

[1526] Disaster information collection and analysis

[1527] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1528] The generating AI analyzes the information and adds all postal codes in Shinagawa Ward to the affected list.

[1529] Linking delivery area codes

[1530] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[1531] Judgment on delivery availability

[1532] The server flags Shinagawa-ku (zip code 123-4567) as undeliverable.

[1533] customer notification

[1534] The server extracts a list of customers with the relevant postal code and sends an email notification stating that "delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1535] Collecting Emotional Data

[1536] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1537] For example, suppose that a user who received the notification "posted a comment on their personal page expressing dissatisfaction with the delivery delay."

[1538] Customer support coordination

[1539] The server determines that the user is very dissatisfied and automatically generates and sends a follow-up email.

[1540] For example, "The server will send an additional follow-up email to the user with an apology."

[1541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1542] Step 1:

[1543] The server calls data from news APIs, SNS APIs, and the Japan Meteorological Agency to collect the latest disaster information. Specifically, it uses an API key to access each data source and obtain new disaster information. The obtained data is stored on the server in formats such as JSON and XML. The input is the API endpoint and key, and the output is a dataset of disaster information.

[1544] Step 2:

[1545] The server inputs the collected disaster information into a generative AI model to identify affected areas. Specifically, the data is preprocessed and converted into a format suitable for the model, and then input into the model. A list of affected areas is generated and output. The input is the preprocessed disaster information data, and the output is a list of affected postal codes.

[1546] Step 3:

[1547] The server accesses the delivery company's database to obtain delivery area information. Specifically, it uses an SQL query to extract delivery area data. It then compares the obtained delivery area information with its own postal code database and sets the delivery area code corresponding to each postal code. The input is the delivery company's area database, and the output is a mapping between postal codes and area codes.

[1548] Step 4:

[1549] The server uses the generated list of postal codes in disaster-affected areas to refer to the delivery area code for each postal code and determine whether delivery is possible. Specifically, it uses mapping data between postal codes and area codes to identify affected areas. The input is the list of disaster-affected areas and the mapping data between postal codes and area codes, and the output is a list with a flag indicating whether delivery is possible or not.

[1550] Step 5:

[1551] The server generates a list of customers in the affected areas based on their order history. Specifically, it extracts order data linked to affected postal codes and creates a list of affected customers. The input is a list of postal codes in the affected areas and an order history database, and the output is a list of affected customers.

[1552] Step 6:

[1553] The server notifies each customer whether delivery is possible or not using email, My Page, chat, etc. Specifically, it sends email using an SMTP server or calls a chatbot API to notify. The input is a list of customers to be notified and the notification content, and the output is a notification message to each customer.

[1554] Step 7:

[1555] The server collects the reactions of users who received the notifications. Specifically, it analyzes the logs of the mail server and web server to extract user feedback. The input is each user's notification message and their reaction data (email replies, personal page comments, etc.), and the output is the collected feedback data.

[1556] Step 8:

[1557] The server analyzes the collected feedback data using an emotion engine and evaluates the user's emotional state. Specifically, it performs text sentiment analysis using natural language processing technology to measure dissatisfaction and satisfaction. The input is the collected feedback data, and the output is the evaluation result of the user's emotional state.

[1558] Step 9:

[1559] The server determines the customer support response based on the sentiment analysis results and automatically sets the appropriate action. Specifically, it executes a script that generates and sends a follow-up email. The input is the sentiment analysis results and the follow-up content, and the output is a follow-up message to the user.

[1560] (Application example 2)

[1561] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1562] When a natural disaster occurs, mail-order sales systems must quickly and accurately provide customers with information on whether or not delivery is possible. However, in many cases, collecting disaster information and determining whether or not delivery is possible is done manually, which takes time and effort and can result in delays in customer response. Furthermore, a uniform response that ignores the customer's emotional state can lead to a decrease in customer satisfaction. In response to this, the objective of this invention is to provide customer support that automatically collects and analyzes disaster information and takes into account the customer's emotional state.

[1563] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and analyzing disaster information obtained when a natural disaster occurs, means for linking deliverable area codes with postal codes, means for determining whether delivery is possible based on the collected disaster information, means for notifying customers of the information on whether delivery is possible, means for collecting and analyzing customer emotional data, and means for adjusting responses according to the customer's emotional state. This makes it possible to quickly and accurately provide customers with information on whether delivery is possible even when a disaster occurs, and to respond flexibly in accordance with the customer's emotional state.

[1564] "Natural disaster information" refers to information on natural disasters such as earthquakes, floods, typhoons, and heavy rains obtained from public and private data sources.

[1565] "Disaster information collection and analysis means" is a function for collecting and analyzing disaster information from various data sources when a natural disaster occurs.

[1566] A "delivery area code" is a code that indicates whether delivery is possible in a specific area, and is linked to a postal code.

[1567] The "means for determining whether delivery is possible" is a function that determines whether delivery is possible to a specific area based on collected and analyzed disaster information.

[1568] "Customer notification means" refers to a means for informing customers of the availability of delivery, and includes communication means such as email and messages.

[1569] "Emotional data" is data that indicates the emotional state of a customer, collected from their reactions and opinions.

[1570] "Emotional data collection and analysis means" is a function for collecting customer reaction data and analyzing it to evaluate the emotional state of the customer.

[1571] The "response adjustment means" is a function for adjusting the customer support response in accordance with the analyzed emotional state of the customer.

[1572] The present invention is a system that utilizes AI technology to provide customers with prompt and accurate delivery availability information regarding the operation of a mail-order sales system in the event of a natural disaster. Furthermore, by combining it with an emotion engine, it also includes a function to recognize the user's emotional state and improve the quality of customer service. Specific embodiments of the system are described below.

[1573] First, as a means of collecting and analyzing disaster information, the server collects the latest disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The collected information is analyzed by a generative AI model using TensorFlow to identify areas that may be affected by the disaster.

[1574] Next, to link delivery area codes with postal codes, the server retrieves delivery area information provided by the delivery company's database and compares it with its own postal code database. This process is performed using a backend system using Django.

[1575] As a means of determining whether delivery is possible based on the collected and analyzed disaster information, the server generates a list of postal codes in the affected areas and, based on that list, sets a flag for each postal code indicating that delivery should be canceled or delayed.

[1576] The customer notification system reviews customer order history and generates a list of customers requesting delivery in the affected area. This list of customers will be notified of delivery delays or cancellations via email or message using communication methods such as Twilio.

[1577] Furthermore, as a means of collecting and analyzing emotional data, the server collects the reactions of customers who receive notifications. This reaction data includes email replies, comments on their personal pages, and responses in chat. The collected emotional data is then analyzed again using TensorFlow to evaluate the customer's emotional state.

[1578] Finally, as a means of adjusting responses according to the customer's emotional state, the server automatically adjusts the content and methods of customer support responses based on the analysis results. For example, if a customer is highly dissatisfied, additional follow-up emails or special coupon offers will be automatically generated and sent. This series of processes enables quick and accurate responses even in the event of a disaster, improving customer satisfaction.

[1579] Specific examples

[1580] 1. Disaster information collection and analysis

[1581] The server retrieves information about heavy rain disasters in Shinagawa Ward, Tokyo from the API.

[1582] The generating AI will analyze that information and add all postal codes in Shinagawa Ward to the affected list.

[1583] 2. Linking delivery area codes

[1584] The server recognizes Shinagawa-ku, Tokyo (postal code 123-4567) as one of the "23 wards of Tokyo" from the delivery company's database.

[1585] 3. Determining whether delivery is possible

[1586] The server flags "zip code 123-4567" as undeliverable.

[1587] 4. Customer Notification

[1588] The server extracts the list of customers with the relevant postal code and sends a notification email stating that "Delivery of order number ABC123 (address: 123-4567, Shinagawa-ku, Tokyo) will be delayed."

[1589] 5. Collecting Emotional Data

[1590] The server collects email replies and comments on personal pages and analyzes them using an emotion engine.

[1591] 6. Customer Support Coordination

[1592] If the user is determined to be highly dissatisfied, a follow-up email containing a special coupon will be sent.

[1593] Prompt Sentence Examples

[1594] 1. Prompts for disaster information collection and analysis

[1595] "Based on the latest heavy rain information obtained from the Japan Meteorological Agency API, identify the affected area in Shinagawa Ward, Tokyo."

[1596] 2. Input prompt sentence to emotion engine

[1597] "Analyze this email response to assess the customer's level of dissatisfaction and emotional state."

[1598] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1599] Step 1:

[1600] The server collects natural disaster information from public and private data sources, such as the Japan Meteorological Agency API and SNS API. The input data is disaster information from each API and is stored on the server. This collected data is stored on the server in its raw form.

[1601] Step 2:

[1602] The server analyzes the collected disaster information using a generative AI model powered by TensorFlow. The input data is the disaster information collected in step 1, and through analysis, potentially affected areas are identified. The output data is a list of affected areas, including detailed information about the identified areas.

[1603] Step 3:

[1604] The server retrieves delivery area information from the delivery company's database and compares it with its own postal code database. The input data is the delivery company's delivery area information and the company's postal code information, and by comparing these, a delivery area code corresponding to each postal code is generated. The output data is a pair of the matched delivery area code and postal code.

[1605] Step 4:

[1606] The server determines whether delivery is possible or not based on the generated affected area list and delivery area code. The input data is a pair of the affected area list and delivery area code, and based on that, it determines whether delivery is possible (or not) for each specific postal code. The output data is a flag set for each postal code indicating whether delivery has been canceled or delayed.

[1607] Step 5:

[1608] The server checks customer order history and generates a list of customers requesting delivery to the affected area. The input data is customer order history and delivery area information, and the affected customer list is created based on these. The output data is the affected customer list.

[1609] Step 6:

[1610] The server uses a communication method such as Twilio to notify affected customers by email or message. The input data is a list of affected customers and delivery availability information, and individual notifications are sent to each customer based on that. The output data is a record of the notifications sent to customers.

[1611] Step 7:

[1612] The user receives a delivery success or failure notification from the server. The input data is the notification sent from the server, which the user confirms. The output data is the user's confirmation and their reaction (for example, a reply to an email or a comment on their personal page).

[1613] Step 8:

[1614] The server collects the user's reactions upon receiving the notification and analyzes them using an emotion engine. The input data is the user's reactions (email replies, comments on their personal page, etc.), which are analyzed by the emotion engine using TensorFlow. The output data is the evaluation results regarding the customer's emotional state.

[1615] Step 9:

[1616] The server adjusts customer support responses based on the results of sentiment analysis. The input data are the sentiment analysis results and customer support response patterns, and based on these, responses tailored to specific customers (for example, generating follow-up emails or special coupons) are automatically generated. The output data is the automatically generated customer response actions.

[1617] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1618] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1619] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1620] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1621] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1622] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1623] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1624] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1625] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1626] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1627] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1628] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1629] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1630] 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.

[1631] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1632] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1633] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1634] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1635] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1636] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1637] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1638] The following is further disclosed regarding the above embodiment.

[1639] (Claim 1)

[1640] A means of collecting and analyzing disaster information obtained when a natural disaster occurs,

[1641] A means of linking delivery area codes with postal codes,

[1642] A means of determining whether delivery is possible or not based on the collected disaster information, and

[1643] A means for notifying customers of delivery availability information;

[1644] A system including:

[1645] (Claim 2)

[1646] 10. The system of claim 1, wherein disaster information is collected and analyzed from public and private data sources.

[1647] (Claim 3)

[1648] The system of claim 1 generates a list of affected customers and notifies them based on delivery area information linked to the customer's order history.

[1649] "Example 1"

[1650] (Claim 1)

[1651] means of collecting disaster information from public and private data sources;

[1652] A means of analyzing the collected disaster information using a generative AI model;

[1653] A means of linking delivery area codes with multiple postal codes,

[1654] A means to determine whether delivery is possible or not based on the analyzed disaster information, and

[1655] A means for notifying customers of delivery availability inform...

Claims

1. A means of collecting and analyzing disaster information obtained when a natural disaster occurs, and A means of linking delivery area codes with postal codes, A means of determining whether delivery is possible or not based on the collected disaster information, and A means for notifying customers of delivery availability information; A system including:

2. 10. The system of claim 1, wherein disaster information is collected and analyzed from public and private data sources.

3. The system according to claim 1, wherein a list of affected customers is generated based on delivery area information linked to the customer's order history, and notification is sent.

Images