System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a prompt input by a user; means for analyzing the prompt using a generative AI model to extract a filtering condition; means for automatically generating a filtering rule to be applied to a mail server based on the filtering condition; and means for applying the filtering rule to the mail server.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] Current email filtering systems are based on limited keywords and rules, making it difficult to meet diverse user needs. Furthermore, managing emails requires a great deal of time and effort, so efficient management methods are needed. Furthermore, complex filtering settings are difficult for non-technical users. The purpose of this invention is to solve these problems and realize flexible and efficient email filtering that meets user needs. [Means for solving the problem]

[0005] This invention relates to a system that includes a means for receiving a prompt entered by a user in natural language, a means for analyzing the prompt using a generative AI model and extracting filtering conditions, a means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions, and a means for applying the filtering rules to the mail server. In particular, the generative AI model includes natural language understanding technology to accurately analyze the user's intent. Furthermore, the filtering rules are generated based on keywords in the sender, subject, and body of the message, making them easy to apply. This allows for efficient email management while meeting a variety of filtering needs.

[0006] A "prompt" is an instruction or request entered by a user using natural language.

[0007] A "generative AI model" is an artificial intelligence that is trained using large datasets and has the ability to parse and generate natural language.

[0008] "Natural language understanding technology" refers to technology that enables a generative AI model to analyze a user's natural language input and understand its intent and meaning.

[0009] "Filtering criteria" are the conditions or rules used to filter specific emails, such as sender, subject, or body keywords.

[0010] "Filtering rules" are specific rules for managing emails that are set based on filtering conditions and are applied to the email server.

[0011] A "mail server" is a server system for receiving, sending, storing, and managing email.

[0012] "User" means any individual or entity that uses the System. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main components: a server, a terminal, and a user.

[0035] Server-side processing

[0036] Receiving prompts

[0037] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[0038] Prompt Analysis

[0039] The server uses a generative AI model to analyze the incoming prompt. This model includes natural language understanding techniques to accurately understand the user's intent. For example, from the prompt "Filter my Amazon order history," the model extracts filtering criteria related to a specific sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders").

[0040] Creating filtering rules

[0041] Once the prompt is parsed, the server generates specific filtering rules based on the extracted conditions, such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject", which are automatically applied to the mail server.

[0042] Applying rules

[0043] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0044] Terminal side processing

[0045] Entering Prompts

[0046] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0047] Sending a prompt

[0048] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0049] Checking the Configuration

[0050] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0051] User processing

[0052] Preparation for use

[0053] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0054] Prompt Input

[0055] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0056] Checking the settings and using

[0057] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0058] Specific examples

[0059] Example 1: Filtering Amazon order history

[0060] User prompt input: "Filter my Amazon order history"

[0061] Server parsing: Extract sender (no-reply@amazon.com) and subject (order) from the prompt

[0062] Generate filtering rule: "if sender == 'no-reply@amazon.com' and 'Orders' in subject"

[0063] Apply rules: Apply rules to the mail server and start filtering

[0064] Example 2: Excluding Amazon promotional emails

[0065] User prompt input: "Exclude Amazon promotional emails"

[0066] Server analysis: Prompt for emails with sender (promotions@amazon.com) or body containing 'sale'

[0067] Generate filtering rule: "if sender == 'promotions@amazon.com' or 'sale' in body"

[0068] Apply rules: Apply rules to the mail server and start filtering

[0069] In this way, the system analyzes the user's natural language input and automatically generates and applies flexible and accurate filtering rules, thereby meeting a variety of email filtering needs and significantly reducing the burden on users.

[0070] The processing flow will be explained below.

[0071] Step 1: Enter the prompt and submit

[0072] User: Enters a natural language prompt through the device interface, entering a specific request such as "Filter my Amazon order history."

[0073] Terminal: Receives user-supplied prompts and constructs them as HTTP POST or API requests.

[0074] Terminal: Sends the constructed request to the server.

[0075] Step 2: Receiving the prompt

[0076] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[0077] Step 3: Prompt Parsing

[0078] Server: Inputs the received prompt into a generative AI model and begins analysis, using a model such as GPT-4.

[0079] Generative AI model: Analyzes prompts using natural language understanding techniques to extract user intent. Based on the extracted intent, it identifies filtering conditions. For example, from the prompt "Filter Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject contains 'order'."

[0080] Step 4: Creating filtering rules

[0081] Server: Generate specific filtering rules using the extracted filtering conditions. For example, create a rule in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject".

[0082] Server: Stores the generated rules in a database and converts them into an executable format.

[0083] Step 5: Applying rules

[0084] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[0085] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[0086] Step 6: Check your filtering settings

[0087] Mail server: After applying the rules, check that the filtering settings are working properly.

[0088] Server: Collects the confirmation results and notifies the device.

[0089] Step 7: Setup Complete Notification

[0090] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[0091] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[0092] Step 8: User review and use

[0093] User: Receives a notification from the device confirming that the filtering rules have been applied and confirms it.

[0094] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[0095] Example 1

[0096] 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."

[0097] Conventional email filtering systems have the drawback of requiring users to manually set rules, which is time-consuming and makes it difficult to achieve flexible and accurate filtering. Furthermore, the system requires specialized knowledge, making it difficult for general users to use. Furthermore, responding to diverse email filtering needs requires a huge amount of time and effort, making efficient email management difficult.

[0098] 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.

[0099] In this invention, the server includes means for receiving instructions input by a user in natural language, means for analyzing the instructions using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to the communication server based on the filtering conditions, and means for applying the filtering rules to the communication server. This allows the user to set highly accurate filtering settings simply by inputting in natural language, enabling efficient and flexible email sorting.

[0100] "User" refers to any person or entity utilizing the system to enter prompts in natural language.

[0101] An "instruction" is a message entered by a user in natural language that includes a specific filtering condition.

[0102] A "generative AI model" refers to an artificial intelligence algorithm for natural language understanding and analysis, primarily based on deep learning techniques.

[0103] "Filtering conditions" are specific conditions extracted based on user instructions, and include keywords in the sender, subject, or body of the email.

[0104] "Filtering rules" refer to email sorting rules that are automatically generated based on the extracted filtering conditions.

[0105] A "communication server" refers to a server that manages the sending and receiving of emails, and is the target to which filtering rules are applied.

[0106] "Means for receiving" refers to a system component for receiving instructions from a user.

[0107] "Means for analyzing" refers to a system component that analyzes received instructions using a generative AI model and extracts filtering conditions.

[0108] "Means for automatically generating" refers to a system component for generating filtering rules based on the parsed filtering conditions.

[0109] "Means for applying" refers to a system component for setting and applying the generated filtering rules to the communication server.

[0110] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main elements: a server, a terminal, and a user.

[0111] 1. Server-side processing

[0112] The server receives a natural language prompt input from the user's device, which includes specific filtering requests such as "filter my Amazon order history" or "exclude Amazon promotional emails."

[0113] First, the server puts a specific API endpoint into a waiting state. When a prompt is sent as a POST request, it reads and temporarily stores the prompt. Next, the server uses a generative AI model (e.g., a model using natural language processing technology) to analyze the prompt and understand the user's intent. As a result of the analysis, filtering conditions related to the sender, subject, and body of the message are extracted. For example, from the prompt "Filter my Amazon order history," the sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders") are extracted.

[0114] The server then automatically generates filtering rules based on the extracted conditions. These rules are generated in the format of "if sender == 'no-reply@amazon.com' and 'Orders' in subject". The generated filtering rules are added by the server to the mail server's configuration file and are automatically applied when receiving emails.

[0115] 2. Terminal processing

[0116] The terminal provides an interface that allows users to input filtering conditions in natural language. For example, users can simply enter specific conditions such as "Exclude Amazon promotional emails" and click the submit button. When the submit button is clicked, the terminal sends the input prompt text as a POST request to the server.

[0117] When the server completes the creation and application of filtering rules, it sends a notification to the device, which then displays a pop-up message or notification bar to inform the user that the settings have been completed.

[0118] 3. User-side processing

[0119] The user first launches the email application and confirms that the filter setting function is enabled. Next, the user enters filtering conditions in natural language and clicks the send button. For example, the user enters instructions such as "Save all important Amazon notifications." After receiving a notification from the server that the settings have been completed, the user checks their inbox and confirms that filtering has been performed correctly.

[0120] Using a generative AI model, the system converts users' natural language input into flexible, tailored filtering rules, allowing users to easily set up advanced filtering and efficiently manage their emails.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] Input: The user enters a prompt sentence in natural language.

[0124] Server: Receives the prompt statement.

[0125] Specific operation: The server monitors the API endpoint and receives the prompt text sent by the user through the terminal (e.g., "Filter my Amazon order history") as a POST request. The received prompt text is temporarily stored in a database or memory.

[0126] Output: The saved prompt statement.

[0127] Step 2:

[0128] Input: The saved prompt statement.

[0129] Server: Analyzes the prompt sentence using a generative AI model.

[0130] Specific operation: The server inputs the received prompt into a generative AI model and analyzes it using natural language understanding technology. The generative AI model (e.g., GPT-4) analyzes the prompt and extracts filtering conditions related to the sender address and subject. For example, from the prompt "Filter my Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject: Order."

[0131] Output: The extracted filtering conditions.

[0132] Step 3:

[0133] Input: The extracted filtering criteria.

[0134] Server: Automatically generates filtering rules based on filtering conditions.

[0135] Specific operation: The server automatically generates filtering rules based on the extracted filtering conditions. Specifically, it executes a script that generates filtering rules in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject" based on the conditions.

[0136] Output: The generated filtering rules.

[0137] Step 4:

[0138] Input: The generated filtering rules.

[0139] Server: The generated filtering rules are applied to the mail server.

[0140] What happens: The server runs a script to add the generated filtering rules to the mail server's configuration file. After adding the rules, the mail server will sort emails according to the new filtering rules.

[0141] Output: The applied filtering rules.

[0142] Step 5:

[0143] Input: The user's prompt and any filtering rules that have been applied.

[0144] Terminal: Receives notification that the filtering rules have been applied.

[0145] Specific operation: The server notifies the device that the application of the filtering rules has been completed. This notification is sent from the server to the device in JSON format, and the device notifies the user via a pop-up message or notification bar.

[0146] Output: A message informing you that the configuration is complete.

[0147] Step 6:

[0148] Input: Email with filtering applied.

[0149] User: Check the filtering results in your email application.

[0150] Specific behavior: The user launches an email application and checks the inbox or a specific folder. The user verifies that emails are properly sorted according to the configured filtering rules. For example, the user checks to see if the Amazon order history email has been properly moved to a specific folder.

[0151] Output: Check the filtering results.

[0152] (Application example 1)

[0153] 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."

[0154] Autonomous vehicles receive massive amounts of data from numerous sensors in real time. Managing this data efficiently and extracting only the necessary information is important for improving vehicle performance and ensuring safety. However, manually filtering each sensor's data is extremely time-consuming and the accuracy is unstable. To solve this issue, there is a need for a system that automates data filtering within autonomous vehicles and allows users to easily configure it.

[0155] 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.

[0156] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model to extract filtering conditions, and means for automatically generating filtering rules to be applied to an in-vehicle data processing system based on the filtering conditions, thereby enabling efficient data management within an autonomous vehicle and enabling only required data to be extracted quickly and accurately.

[0157] A "user" is a person who rides in an autonomous vehicle and configures data filtering.

[0158] "Natural language" refers to the language used by humans on a daily basis, and refers to human language, not a specific programming language or code.

[0159] A "prompt" is an instruction or request entered in natural language by a user to specify data filtering criteria.

[0160] A "means for receiving" is an interface or device for receiving a prompt from a user.

[0161] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze a user's natural language and extract specific data conditions.

[0162] "Analyzing means" refers to a processing device that uses a generative AI model to derive data filtering conditions from the prompts.

[0163] "Filtering conditions" are the conditions that the user specifies as the criteria for extracting or excluding data.

[0164] An "in-vehicle data processing system" is a system for processing sensor data and various information in real time within an autonomous vehicle.

[0165] The "filtering rules" are set rules for selecting and discarding data based on the extracted filtering conditions.

[0166] "Means for automatic generation" refers to programs or algorithms that use generative AI models to create specific filtering rules from filtering conditions.

[0167] The present invention provides a system for automatically generating filtering rules to be applied to a data processing system in an autonomous vehicle by analyzing a prompt input in natural language by a user. Specific embodiments of the system are described below.

[0168] Hardware and Software Configuration

[0169] The system consists of a server that receives user input and analyzes the data using a generative AI model, and a terminal where users can enter prompts. The terminal is a smartphone or tablet with a dedicated application installed. The server is installed on the cloud and has high-performance data processing capabilities.

[0170] Program processing explanation

[0171] Terminal side processing

[0172] 1. Enter the prompt:

[0173] Users launch the smartphone application and input data filtering criteria in natural language, such as "don't record license plate information of cars ahead" or "save only data related to multiple lane changes."

[0174] 2. Send prompt:

[0175] The device sends the input prompt to the cloud server as JSON format data using an HTTP POST request.

[0176] Server-side processing

[0177] 1. Receiving prompts:

[0178] The server receives the prompt received from the terminal.

[0179] 2. Prompt analysis:

[0180] The server uses a generative AI model to analyze the received prompt. The generative AI model includes natural language understanding technology and can accurately analyze the user's intent. For example, from the prompt "Do not record the license plate information of the car ahead," it can extract the condition to exclude data about the car ahead.

[0181] 3. Create filtering rules:

[0182] Based on the analysis results, filtering rules are automatically generated, such as "if 'vehicle ahead' in data and 'license plate information' in data then exclude."

[0183] 4. Rules apply:

[0184] The generated filtering rules are applied to the vehicle's data processing system, which then filters out sensor data that meets specific conditions.

[0185] User processing

[0186] 1. Preparation for use:

[0187] The user confirms through the application that the filtering conditions have been applied.

[0188] 2. Check the settings:

[0189] Verify that your filter settings were applied correctly and receive notifications to let you know that your settings have been applied.

[0190] 3. Continued Use:

[0191] The data processing system of the autonomous vehicle processes data according to filtering rules, allowing users to efficiently manage only the data they need.

[0192] Examples and prompts

[0193] Example 1: Do not record the license plate information of the car ahead

[0194] Example 2: Save only data related to multiple lane changes

[0195] Based on the above prompts, the system can perform real-time conditional filtering and provide data management according to the user's preferences.

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

[0197] Step 1:

[0198] The user starts the smartphone application and inputs data filtering conditions in natural language, such as prompts like "Don't record license plate information of cars ahead" or "Save only data related to multiple lane changes." These prompts are then input into the application as text data.

[0199] Input: A natural language prompt

[0200] Output: Input text data

[0201] Step 2:

[0202] The device sends the input prompt to the cloud server using an HTTP POST request, sending the input prompt text as JSON format data.

[0203] Input: Prompt sentence entered as text data

[0204] Output: JSON format data

[0205] Step 3:

[0206] The server receives the prompt (JSON format data) from the device. An API is implemented to receive this data.

[0207] Input: Prompt data in JSON format

[0208] Output: Received JSON data

[0209] Step 4:

[0210] The server uses a generative AI model to analyze the received prompt and extract filtering conditions. At this time, the generative AI model (including natural language understanding technology) analyzes the user's intent and extracts specific filtering conditions (e.g., "Ignore the license plate information of the car ahead") as text data.

[0211] Input: Received JSON data

[0212] Data processing: Analyzing prompts using generative AI models

[0213] Output: Text data as filtering criteria

[0214] Step 5:

[0215] The server automatically generates filtering rules based on the extracted filtering conditions. For example, it generates filtering rules in the format "if 'vehicle ahead' in data and 'license plate information' in data then exclude" and stores them as rule data.

[0216] Input: Text data as filtering criteria

[0217] Data Calculation: Generate rules from filtering conditions

[0218] Output: Rule data as filtering rules

[0219] Step 6:

[0220] The server applies the generated filtering rules to the data processing system in the vehicle by transmitting the rule data to the data filtering system installed in the vehicle, and the filtering rules are applied immediately.

[0221] Input: Rule data as filtering rules

[0222] Output: Filtering rules applied to the data processing system in the vehicle

[0223] Step 7:

[0224] The user confirms through the application that the filtering conditions have been applied. The device receives a notification from the server and displays a message confirming that the filtering settings have been applied correctly.

[0225] Input: Notification of completion of setup from the server

[0226] Output: Display confirming the configuration

[0227] Step 8:

[0228] Users can verify that the data processing system of the autonomous vehicle processes data according to the filtering rules and efficiently manage only the necessary data. This step allows users to confirm that the filtering settings are working as expected.

[0229] Input: Filtered data in the vehicle

[0230] Output: Check results filtered to only the required data

[0231] Through these steps, the system achieves efficient data filtering within an autonomous vehicle based on the user's natural language instructions.

[0232] 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.

[0233] This invention is a system that analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules that meet specific needs. This system is mainly composed of three elements: a server, a terminal, and a user.

[0234] Server-side processing

[0235] Receiving prompts

[0236] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[0237] Prompt and Sentiment Analysis

[0238] The server uses a generative AI model and an emotion engine to analyze the received prompt. The generative AI model includes natural language understanding technology, allowing it to accurately grasp the user's intent. At the same time, the emotion engine analyzes emotions from the user's prompt and recognizes emotional states such as anger, sadness, and joy. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[0239] Adjusting filtering conditions and generating rules

[0240] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[0241] Applying rules

[0242] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0243] Terminal side processing

[0244] Entering Prompts

[0245] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0246] Sending a prompt

[0247] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0248] Checking the Configuration

[0249] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0250] User processing

[0251] Preparation for use

[0252] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0253] Prompt Input

[0254] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0255] Checking the settings and using

[0256] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0257] Specific examples

[0258] Example 1: Filtering Amazon order history

[0259] User prompt input: "Filter my Amazon order history"

[0260] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[0261] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus additional conditions if stress is detected

[0262] Apply rules: Apply rules to the mail server and start filtering

[0263] Example 2: Excluding Amazon promotional emails

[0264] User prompt input: "Exclude Amazon promotional emails"

[0265] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[0266] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", with rules not adjusted based on sentiment

[0267] Apply rules: Apply rules to the mail server and start filtering

[0268] This system automatically generates and applies flexible and accurate filtering rules based on natural language input, taking into account the user's emotional state, thereby meeting diverse email filtering needs while significantly reducing the burden on users.

[0269] The processing flow will be explained below.

[0270] Step 1: Enter the prompt and submit

[0271] User: Enters filtering criteria in natural language through the device interface, providing specific requests such as "Filter my Amazon order history."

[0272] Terminal: Construct the user-supplied prompt as an HTTP POST or API request.

[0273] Terminal: Sends the constructed request to the server.

[0274] Step 2: Receiving the prompt

[0275] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[0276] Step 3: Prompt analysis and emotion recognition

[0277] Server: Inputs the received prompt into a generative AI model and begins analysis, for example using an AI model such as GPT-4.

[0278] Generative AI model: Uses natural language understanding techniques to analyze prompts and extract user intent. For example, from the prompt "Filter my Amazon order history," it extracts "From: no-reply@amazon.com" and "Subject contains 'order'."

[0279] Emotion Engine: Analyzes the user's emotions from prompts and recognizes their emotional state (happiness, sadness, anger, stress, etc.). This information is used to adjust filtering rules.

[0280] Step 4: Adjust filtering conditions and generate rules

[0281] Server: Generates specific filtering rules based on the extracted filtering conditions and the results of the emotion engine. For example, if the prompt "Filter Amazon order history" is stressful, the server sets a stricter filtering rule such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject."

[0282] Server: Stores the generated filtering rules in a database and converts them into an executable format.

[0283] Step 5: Applying rules

[0284] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[0285] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[0286] Step 6: Check your filtering settings

[0287] Mail server: After applying the rules, check that the filtering settings are working properly.

[0288] Server: Collects the confirmation results and notifies the device.

[0289] Step 7: Setup Complete Notification

[0290] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[0291] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[0292] Step 8: User review and use

[0293] User: Receives a notification on the device confirming that the filtering rules have been applied and confirms it.

[0294] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[0295] Example 2

[0296] 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."

[0297] Conventional email filtering systems required users to manually set detailed conditions, which often made the process complicated. Furthermore, they lacked the flexibility to filter according to the user's emotional state or stress level, making it difficult to accurately filter according to the user's intentions and emotions. This required users to go through the trouble of checking unwanted emails and risked filtering out necessary emails.

[0298] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for analyzing the user's emotions from the prompt using an emotion engine and recognizing the user's emotional state, means for automatically generating filtering rules to be applied to the mail server based on the filtering conditions and the emotional state, means for applying the filtering rules to the mail server, and means for notifying the user that application of the filtering rules has been completed. This enables flexible and accurate email filtering according to the user's natural language input and emotional state.

[0299] A "user" is a person who uses the system to configure email filtering.

[0300] "Natural language" refers to the language used by humans on a daily basis, not a specific program code or machine language.

[0301] A "prompt" refers to an instruction or request that a user enters in natural language.

[0302] A "generative AI model" is a system or program that uses artificial intelligence techniques to analyze input natural language prompts and extract specific conditions or information.

[0303] An "emotion engine" is a system or program that analyzes a user's emotional state from the user's prompts and recognizes emotions such as anger, sadness, and joy.

[0304] "Filtering conditions" are conditions or rules used to classify or filter out email based on specific criteria.

[0305] "Filtering rules" are settings for automatically receiving and classifying emails based on filtering conditions.

[0306] A "mail server" is a server that manages incoming and outgoing emails.

[0307] A "notification" is a message or alert from the server that tells the user that a particular operation or event has been completed.

[0308] This system analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules tailored to specific needs. This system is primarily composed of three elements: a server, a terminal, and a user.

[0309] Server-side implementation

[0310] The server receives a natural language prompt sent by the user, which includes a specific filtering request, such as "Filter my Amazon order history."

[0311] Parsing prompts

[0312] The server analyzes the received prompt using a generative AI model, which includes natural language understanding technology to accurately understand the user's intent.

[0313] Emotion Analysis

[0314] The server uses an emotion engine to analyze the user's emotions from the prompt and recognize their emotional state, such as anger, sadness, joy, etc. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[0315] Adjusting filtering conditions and generating rules

[0316] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[0317] Applying rules

[0318] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0319] Terminal side embodiment

[0320] Entering Prompts

[0321] The terminal provides an interface where users can input filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0322] Sending a prompt

[0323] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0324] Checking the Configuration

[0325] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0326] User-Side Embodiment

[0327] Preparation for use

[0328] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0329] Prompt Input

[0330] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0331] Checking the settings and using

[0332] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0333] Specific examples

[0334] Example 1: Filtering Amazon order history

[0335] User prompt input: "Filter my Amazon order history"

[0336] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[0337] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus apply additional conditions if stress is detected.

[0338] Apply rules: Apply rules to the mail server and start filtering.

[0339] Example 2: Excluding Amazon promotional emails

[0340] User prompt input: "Exclude Amazon promotional emails"

[0341] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[0342] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", to prevent rule adjustment based on sentiment.

[0343] Apply rules: Apply rules to the mail server and start filtering.

[0344] By applying this invention, flexible and accurate filtering rules can be automatically generated and applied based on natural language input, while also taking into account the user's emotional state. This makes it possible to meet a variety of email filtering needs and significantly reduce the burden on users.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1: Enter the prompt (terminal)

[0347] The terminal provides the user with an interface for entering natural language prompts. The user enters a prompt such as "Filter my Amazon order history" into the interface and clicks a submit button, which inputs the user's request into the terminal in natural language format.

[0348] Input: A natural language prompt entered by the user

[0349] Output: The natural language prompt received on the terminal

[0350] Step 2: Sending a prompt (terminal)

[0351] The terminal sends the input prompt to the server, which receives the user's request.

[0352] Input: Natural language prompts received on the device

[0353] Output: The natural language prompt sent to the server

[0354] Step 3: Parsing prompts and emotions (server)

[0355] The server receives the natural language prompt sent from the device and begins analysis using the generative AI model and emotion engine. The generative AI model analyzes the prompt, converts it into structured data, and accurately grasps the user's intention. The emotion engine also analyzes the user's emotion from the prompt and recognizes emotional states such as anger, sadness, and joy.

[0356] Input: Natural language prompt sent from the terminal

[0357] Output: Parsed filtering conditions and the user's emotional state

[0358] Step 4: Adjusting filtering conditions and generating rules (server)

[0359] The server extracts filtering conditions based on the prompt and emotion analysis results, and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, a rule can be added to filter the target email more strictly.

[0360] Input: Parsed filtering conditions and the user's emotional state

[0361] Output: Generated filtering rules

[0362] Step 5: Applying filtering rules (server)

[0363] The server applies the generated filtering rules to the mail server, which allows mail to be automatically sorted upon receipt.

[0364] Input: Generated filtering rules

[0365] Output: Filtering rules applied to the mail server

[0366] Step 6: Notification of settings (server)

[0367] The server sends a message to the device notifying it that the filtering rules have been applied, allowing the user to confirm that the settings have been applied successfully.

[0368] Input: Filtering rules applied to the mail server

[0369] Output: Notification message to terminal

[0370] Step 7: Check the settings (device)

[0371] The terminal receives a notification from the server and displays to the user that the filtering settings have been completed. This process allows the user to confirm the settings.

[0372] Input: Notification message from the server

[0373] Output: A message on the terminal saying the setup is complete

[0374] Step 8: Preparation for use (user)

[0375] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0376] Input: Display of completed setup on terminal

[0377] Output: Mail application with filter settings enabled

[0378] Step 9: Check filtering application and use (user)

[0379] The user checks their inbox to ensure that the filtering rules were applied properly. They verify that their emails are being filtered properly and adjust as necessary.

[0380] Input: Email application with filter settings enabled

[0381] Output: Inbox with filtering rules applied

[0382] This allows users to filter emails according to their needs and feelings with minimal burden.

[0383] (Application example 2)

[0384] 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."

[0385] In conventional autonomous vehicles, passengers need to adjust the in-car environment and driving conditions through detailed settings and operations, which often reduces passenger comfort and convenience. Furthermore, there is a lack of technology to accurately recognize passenger emotions and intentions and reflect them in vehicle operation, making it difficult to provide services that meet individual needs. This has made it difficult to improve passenger satisfaction.

[0386] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0387] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions, means for applying the filtering rules to an in-vehicle adjustment system or a driving control system of an autonomous vehicle, means for analyzing user emotions using the generative AI model and an emotion analysis engine and adjusting the in-vehicle environment, and means for adjusting the in-vehicle environment of the autonomous vehicle, thereby enabling the in-vehicle environment and driving conditions to be automatically adjusted based on the specific needs and emotions of passengers.

[0388] "User" refers to a passenger who utilizes the system to adjust the vehicle's environmental settings and driving controls.

[0389] "Natural language" refers to a linguistic form that is directly input using words that humans use on a daily basis.

[0390] A "prompt" refers to a natural language input sentence that a user uses to give instructions or requests to a system.

[0391] A "generative AI model" refers to an artificial intelligence model that analyzes natural language and accurately understands the user's intentions and requests.

[0392] "Filtering conditions" refer to specific conditions extracted from user prompts for operating or adjusting the system.

[0393] A "mail server" refers to a server that manages and stores email.

[0394] The "filtering rule" refers to a rule for automatically performing a specific process based on the extracted filtering condition.

[0395] "Autonomous vehicle" refers to a vehicle that is capable of driving autonomously.

[0396] "In-vehicle conditioning system" refers to a system for adjusting the interior environment of an autonomous vehicle.

[0397] "Driving control system" refers to a system that controls the driving situation, speed, direction, etc. of an autonomous vehicle.

[0398] "Sentiment analysis engine" refers to an engine for analyzing and recognizing emotions from user prompts.

[0399] "In-vehicle environment" refers to the physical environment inside an autonomous vehicle, including temperature, music, and lighting.

[0400] This invention is a system for an autonomous vehicle that analyzes prompts entered in natural language by passengers, recognizes their emotions, and automatically adjusts the in-vehicle environment and driving situation. This system consists of three elements: a server, a terminal, and a user.

[0401] Server-side processing

[0402] Receiving prompts

[0403] The server receives natural language prompts entered by the passenger at the terminal, including requests related to specific environmental and driving conditions, such as "Turn down the music while driving."

[0404] Prompt and Sentiment Analysis

[0405] The server analyzes the received prompts using a generative AI model and a sentiment analysis engine. The generative AI model incorporates natural language understanding technology to accurately grasp the passenger's intent. At the same time, the sentiment analysis engine analyzes emotions from the prompts and recognizes emotional states such as anger, anxiety, and joy.

[0406] Generating adjustment conditions

[0407] Based on the prompt and emotion analysis results, the server extracts the environmental and driving conditions and generates adjustments to the in-car environment and driving controls based on them. For example, if a passenger requests "quieter music while driving" and the emotion analysis engine detects stress, the server will adjust the music volume down.

[0408] Application of conditions

[0409] The server then applies the generated adjustment conditions to the in-car adjustment system or driving control system, and this process automatically adjusts the passenger environment and driving conditions.

[0410] Terminal side processing

[0411] Entering Prompts

[0412] The device provides an interface that allows passengers to input environmental and driving conditions in natural language, such as specific requests like "Make the music quieter while driving."

[0413] Sending a prompt

[0414] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0415] Checking the Configuration

[0416] Once the server has generated and applied the conditions, a notification is sent to the terminal, allowing passengers to confirm that the settings have been applied successfully.

[0417] User processing

[0418] Preparation for use

[0419] The passenger simply turns on the device and confirms that the settings are enabled, and the adjustment function becomes available.

[0420] Prompt Input

[0421] Passengers input their environment and driving conditions using natural language, such as "Hurry to the next rest area," and click send.

[0422] Checking the settings and using

[0423] Passengers receive a notification from the server that the settings have been completed, confirm that the adjustments have been made properly, and then check whether the in-car environment and driving conditions have been adjusted properly, and make further adjustments if necessary.

[0424] Specific examples

[0425] Example 1: Quieting the music while driving

[0426] Passenger prompt input: "Quiet music while driving."

[0427] Server analysis: Extract the volume adjustment intent from the prompt and detect stress using an emotion analysis engine

[0428] Generate adjustment conditions: Generate conditions to lower the volume

[0429] Conditions apply: Apply to the in-car adjustment system to reduce the music volume

[0430] Example 2: When rushing to the next rest area

[0431] Passenger prompt input: "Hurry to the next rest area."

[0432] Server analysis: Extracting speed throttling intent from prompts

[0433] Generate tuning conditions: Generate conditions that increase speed within a limited range

[0434] Condition application: Apply to the driving control system and adjust the speed

[0435] The system can automatically adjust the in-car environment and driving conditions based on passengers' specific needs and emotions, providing a comfortable and personalized autonomous driving experience.

[0436] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0437] Step 1:

[0438] Entering and submitting prompts

[0439] The user uses the terminal to input a natural language prompt about the environment or driving conditions, for example, "Turn down the music while driving," and clicks the send button. The terminal then sends this input to the server. The input is the natural language prompt, and the output is the transmission of the prompt data to the server.

[0440] Step 2:

[0441] Receiving prompts

[0442] The server receives natural language prompts sent from the terminal, where the input is the prompt data sent from the terminal and the output is the storage of the prompt data in the server.

[0443] Step 3:

[0444] Analysis using generative AI models

[0445] The server uses a generative AI model to analyze the received prompt. In this process, it understands the meaning of the prompt and extracts filtering conditions. The input is the received prompt data, and the output is the extracted filtering conditions.

[0446] Step 4:

[0447] Emotion recognition using an emotion analysis engine

[0448] The server uses an emotion analysis engine to recognize the user's emotion from the prompt, thereby understanding what emotional state the user is in (e.g., anger, stress, joy). The input is the prompt data, and the output is the analyzed emotion data.

[0449] Step 5:

[0450] Generating adjustment conditions

[0451] The server generates specific adjustment conditions based on the results of the generative AI model and the emotion analysis engine. For example, it creates specific operation conditions such as "lower the music volume" or "increase driving speed." The input is the filtering conditions and emotion data, and the output is the generated adjustment conditions.

[0452] Step 6:

[0453] Application of adjustment conditions

[0454] The server applies the generated adjustment conditions to the in-vehicle adjustment system or driving control system. This process reflects specific operations in the autonomous vehicle. The input is the adjustment conditions, and the output is the adjustment of the in-vehicle environment or driving situation.

[0455] Step 7:

[0456] Sending a notification of completion of setup

[0457] The server notifies the terminal that the adjustment has been completed. The user confirms through the terminal whether the adjustment was successful. The input is the information that the adjustment has been completed, and the output is a notification to the terminal.

[0458] Step 8:

[0459] Checking the settings and using

[0460] The user checks the notification on the device to see if the in-car environment and driving conditions have been adjusted as expected. If necessary, they can enter the prompt again to make adjustments. The input is the setting completion notification and the actual conditions in the car, and the output is the user's confirmation and re-entry if necessary.

[0461] Through these steps, users can easily adjust the environment and driving conditions of their autonomous vehicle using natural language prompts.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] [Second embodiment]

[0466] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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).

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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."

[0478] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main components: a server, a terminal, and a user.

[0479] Server-side processing

[0480] Receiving prompts

[0481] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[0482] Prompt Analysis

[0483] The server uses a generative AI model to analyze the incoming prompt. This model includes natural language understanding techniques to accurately understand the user's intent. For example, from the prompt "Filter my Amazon order history," the model extracts filtering criteria related to a specific sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders").

[0484] Creating filtering rules

[0485] Once the prompt is parsed, the server generates specific filtering rules based on the extracted conditions, such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject", which are automatically applied to the mail server.

[0486] Applying rules

[0487] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0488] Terminal side processing

[0489] Entering Prompts

[0490] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0491] Sending a prompt

[0492] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0493] Checking the Configuration

[0494] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0495] User processing

[0496] Preparation for use

[0497] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0498] Prompt Input

[0499] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0500] Checking the settings and using

[0501] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0502] Specific examples

[0503] Example 1: Filtering Amazon order history

[0504] User prompt input: "Filter my Amazon order history"

[0505] Server parsing: Extract sender (no-reply@amazon.com) and subject (order) from the prompt

[0506] Generate filtering rule: "if sender == 'no-reply@amazon.com' and 'Orders' in subject"

[0507] Apply rules: Apply rules to the mail server and start filtering

[0508] Example 2: Excluding Amazon promotional emails

[0509] User prompt input: "Exclude Amazon promotional emails"

[0510] Server analysis: Prompt for emails with sender (promotions@amazon.com) or body containing 'sale'

[0511] Generate filtering rule: "if sender == 'promotions@amazon.com' or 'sale' in body"

[0512] Apply rules: Apply rules to the mail server and start filtering

[0513] In this way, the system analyzes the user's natural language input and automatically generates and applies flexible and accurate filtering rules, thereby meeting a variety of email filtering needs and significantly reducing the burden on users.

[0514] The processing flow will be explained below.

[0515] Step 1: Enter the prompt and submit

[0516] User: Enters a natural language prompt through the device interface, entering a specific request such as "Filter my Amazon order history."

[0517] Terminal: Receives user-supplied prompts and constructs them as HTTP POST or API requests.

[0518] Terminal: Sends the constructed request to the server.

[0519] Step 2: Receiving the prompt

[0520] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[0521] Step 3: Prompt Parsing

[0522] Server: Inputs the received prompt into a generative AI model and begins analysis, using a model such as GPT-4.

[0523] Generative AI model: Analyzes prompts using natural language understanding techniques to extract user intent. Based on the extracted intent, it identifies filtering conditions. For example, from the prompt "Filter Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject contains 'order'."

[0524] Step 4: Creating filtering rules

[0525] Server: Generate specific filtering rules using the extracted filtering conditions. For example, create a rule in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject".

[0526] Server: Stores the generated rules in a database and converts them into an executable format.

[0527] Step 5: Applying rules

[0528] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[0529] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[0530] Step 6: Check your filtering settings

[0531] Mail server: After applying the rules, check that the filtering settings are working properly.

[0532] Server: Collects the confirmation results and notifies the device.

[0533] Step 7: Setup Complete Notification

[0534] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[0535] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[0536] Step 8: User review and use

[0537] User: Receives a notification from the device confirming that the filtering rules have been applied and confirms it.

[0538] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[0539] Example 1

[0540] 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."

[0541] Conventional email filtering systems have the drawback of requiring users to manually set rules, which is time-consuming and makes it difficult to achieve flexible and accurate filtering. Furthermore, the system requires specialized knowledge, making it difficult for general users to use. Furthermore, responding to diverse email filtering needs requires a huge amount of time and effort, making efficient email management difficult.

[0542] 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.

[0543] In this invention, the server includes means for receiving instructions input by a user in natural language, means for analyzing the instructions using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to the communication server based on the filtering conditions, and means for applying the filtering rules to the communication server. This allows the user to set highly accurate filtering settings simply by inputting in natural language, enabling efficient and flexible email sorting.

[0544] "User" refers to any person or entity utilizing the system to enter prompts in natural language.

[0545] An "instruction" is a message entered by a user in natural language that includes a specific filtering condition.

[0546] A "generative AI model" refers to an artificial intelligence algorithm for natural language understanding and analysis, primarily based on deep learning techniques.

[0547] "Filtering conditions" are specific conditions extracted based on user instructions, and include keywords in the sender, subject, or body of the email.

[0548] "Filtering rules" refer to email sorting rules that are automatically generated based on the extracted filtering conditions.

[0549] A "communication server" refers to a server that manages the sending and receiving of emails, and is the target to which filtering rules are applied.

[0550] "Means for receiving" refers to a system component for receiving instructions from a user.

[0551] "Means for analyzing" refers to a system component that analyzes received instructions using a generative AI model and extracts filtering conditions.

[0552] "Means for automatically generating" refers to a system component for generating filtering rules based on the parsed filtering conditions.

[0553] "Means for applying" refers to a system component for setting and applying the generated filtering rules to the communication server.

[0554] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main elements: a server, a terminal, and a user.

[0555] 1. Server-side processing

[0556] The server receives a natural language prompt input from the user's device, which includes specific filtering requests such as "filter my Amazon order history" or "exclude Amazon promotional emails."

[0557] First, the server puts a specific API endpoint into a waiting state. When a prompt is sent as a POST request, it reads and temporarily stores the prompt. Next, the server uses a generative AI model (e.g., a model using natural language processing technology) to analyze the prompt and understand the user's intent. As a result of the analysis, filtering conditions related to the sender, subject, and body of the message are extracted. For example, from the prompt "Filter my Amazon order history," the sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders") are extracted.

[0558] The server then automatically generates filtering rules based on the extracted conditions. These rules are generated in the format of "if sender == 'no-reply@amazon.com' and 'Orders' in subject". The generated filtering rules are added by the server to the mail server's configuration file and are automatically applied when receiving emails.

[0559] 2. Terminal processing

[0560] The terminal provides an interface that allows users to input filtering conditions in natural language. For example, users can simply enter specific conditions such as "Exclude Amazon promotional emails" and click the submit button. When the submit button is clicked, the terminal sends the input prompt text as a POST request to the server.

[0561] When the server completes the creation and application of filtering rules, it sends a notification to the device, which then displays a pop-up message or notification bar to inform the user that the settings have been completed.

[0562] 3. User-side processing

[0563] The user first launches the email application and confirms that the filter setting function is enabled. Next, the user enters filtering conditions in natural language and clicks the send button. For example, the user enters instructions such as "Save all important Amazon notifications." After receiving a notification from the server that the settings have been completed, the user checks their inbox and confirms that filtering has been performed correctly.

[0564] Using a generative AI model, the system converts users' natural language input into flexible, tailored filtering rules, allowing users to easily set up advanced filtering and efficiently manage their emails.

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1:

[0567] Input: The user enters a prompt sentence in natural language.

[0568] Server: Receives the prompt statement.

[0569] Specific operation: The server monitors the API endpoint and receives the prompt text sent by the user through the terminal (e.g., "Filter my Amazon order history") as a POST request. The received prompt text is temporarily stored in a database or memory.

[0570] Output: The saved prompt statement.

[0571] Step 2:

[0572] Input: The saved prompt statement.

[0573] Server: Analyzes the prompt sentence using a generative AI model.

[0574] Specific operation: The server inputs the received prompt into a generative AI model and analyzes it using natural language understanding technology. The generative AI model (e.g., GPT-4) analyzes the prompt and extracts filtering conditions related to the sender address and subject. For example, from the prompt "Filter my Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject: Order."

[0575] Output: The extracted filtering conditions.

[0576] Step 3:

[0577] Input: The extracted filtering criteria.

[0578] Server: Automatically generates filtering rules based on filtering conditions.

[0579] Specific operation: The server automatically generates filtering rules based on the extracted filtering conditions. Specifically, it executes a script that generates filtering rules in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject" based on the conditions.

[0580] Output: The generated filtering rules.

[0581] Step 4:

[0582] Input: The generated filtering rules.

[0583] Server: The generated filtering rules are applied to the mail server.

[0584] What happens: The server runs a script to add the generated filtering rules to the mail server's configuration file. After adding the rules, the mail server will sort emails according to the new filtering rules.

[0585] Output: The applied filtering rules.

[0586] Step 5:

[0587] Input: The user's prompt and any filtering rules that have been applied.

[0588] Terminal: Receives notification that the filtering rules have been applied.

[0589] Specific operation: The server notifies the device that the application of the filtering rules has been completed. This notification is sent from the server to the device in JSON format, and the device notifies the user via a pop-up message or notification bar.

[0590] Output: A message informing you that the configuration is complete.

[0591] Step 6:

[0592] Input: Email with filtering applied.

[0593] User: Check the filtering results in your email application.

[0594] Specific behavior: The user launches an email application and checks the inbox or a specific folder. The user verifies that emails are properly sorted according to the configured filtering rules. For example, the user checks to see if the Amazon order history email has been properly moved to a specific folder.

[0595] Output: Check the filtering results.

[0596] (Application example 1)

[0597] 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."

[0598] Autonomous vehicles receive massive amounts of data from numerous sensors in real time. Managing this data efficiently and extracting only the necessary information is important for improving vehicle performance and ensuring safety. However, manually filtering each sensor's data is extremely time-consuming and the accuracy is unstable. To solve this issue, there is a need for a system that automates data filtering within autonomous vehicles and allows users to easily configure it.

[0599] 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.

[0600] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model to extract filtering conditions, and means for automatically generating filtering rules to be applied to an in-vehicle data processing system based on the filtering conditions, thereby enabling efficient data management within an autonomous vehicle and enabling only required data to be extracted quickly and accurately.

[0601] A "user" is a person who rides in an autonomous vehicle and configures data filtering.

[0602] "Natural language" refers to the language used by humans on a daily basis, and refers to human language, not a specific programming language or code.

[0603] A "prompt" is an instruction or request entered in natural language by a user to specify data filtering criteria.

[0604] A "means for receiving" is an interface or device for receiving a prompt from a user.

[0605] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze a user's natural language and extract specific data conditions.

[0606] "Analyzing means" refers to a processing device that uses a generative AI model to derive data filtering conditions from the prompts.

[0607] "Filtering conditions" are the conditions that the user specifies as the criteria for extracting or excluding data.

[0608] An "in-vehicle data processing system" is a system for processing sensor data and various information in real time within an autonomous vehicle.

[0609] The "filtering rules" are set rules for selecting and discarding data based on the extracted filtering conditions.

[0610] "Means for automatic generation" refers to programs or algorithms that use generative AI models to create specific filtering rules from filtering conditions.

[0611] The present invention provides a system for automatically generating filtering rules to be applied to a data processing system in an autonomous vehicle by analyzing a prompt input in natural language by a user. Specific embodiments of the system are described below.

[0612] Hardware and Software Configuration

[0613] The system consists of a server that receives user input and analyzes the data using a generative AI model, and a terminal where users can enter prompts. The terminal is a smartphone or tablet with a dedicated application installed. The server is installed on the cloud and has high-performance data processing capabilities.

[0614] Program processing explanation

[0615] Terminal side processing

[0616] 1. Enter the prompt:

[0617] Users launch the smartphone application and input data filtering criteria in natural language, such as "don't record license plate information of cars ahead" or "save only data related to multiple lane changes."

[0618] 2. Send prompt:

[0619] The device sends the input prompt to the cloud server as JSON format data using an HTTP POST request.

[0620] Server-side processing

[0621] 1. Receiving prompts:

[0622] The server receives the prompt received from the terminal.

[0623] 2. Prompt analysis:

[0624] The server uses a generative AI model to analyze the received prompt. The generative AI model includes natural language understanding technology and can accurately analyze the user's intent. For example, from the prompt "Do not record the license plate information of the car ahead," it can extract the condition to exclude data about the car ahead.

[0625] 3. Create filtering rules:

[0626] Based on the analysis results, filtering rules are automatically generated, such as "if 'vehicle ahead' in data and 'license plate information' in data then exclude."

[0627] 4. Rules apply:

[0628] The generated filtering rules are applied to the vehicle's data processing system, which then filters out sensor data that meets specific conditions.

[0629] User processing

[0630] 1. Preparation for use:

[0631] The user confirms through the application that the filtering conditions have been applied.

[0632] 2. Check the settings:

[0633] Verify that your filter settings were applied correctly and receive notifications to let you know that your settings have been applied.

[0634] 3. Continued Use:

[0635] The data processing system of the autonomous vehicle processes data according to filtering rules, allowing users to efficiently manage only the data they need.

[0636] Examples and prompts

[0637] Example 1: Do not record the license plate information of the car ahead

[0638] Example 2: Save only data related to multiple lane changes

[0639] Based on the above prompts, the system can perform real-time conditional filtering and provide data management according to the user's preferences.

[0640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0641] Step 1:

[0642] The user starts the smartphone application and inputs data filtering conditions in natural language, such as prompts like "Don't record license plate information of cars ahead" or "Save only data related to multiple lane changes." These prompts are then input into the application as text data.

[0643] Input: A natural language prompt

[0644] Output: Input text data

[0645] Step 2:

[0646] The device sends the input prompt to the cloud server using an HTTP POST request, sending the input prompt text as JSON format data.

[0647] Input: Prompt sentence entered as text data

[0648] Output: JSON format data

[0649] Step 3:

[0650] The server receives the prompt (JSON format data) from the device. An API is implemented to receive this data.

[0651] Input: Prompt data in JSON format

[0652] Output: Received JSON data

[0653] Step 4:

[0654] The server uses a generative AI model to analyze the received prompt and extract filtering conditions. At this time, the generative AI model (including natural language understanding technology) analyzes the user's intent and extracts specific filtering conditions (e.g., "Ignore the license plate information of the car ahead") as text data.

[0655] Input: Received JSON data

[0656] Data processing: Analyzing prompts using generative AI models

[0657] Output: Text data as filtering criteria

[0658] Step 5:

[0659] The server automatically generates filtering rules based on the extracted filtering conditions. For example, it generates filtering rules in the format "if 'vehicle ahead' in data and 'license plate information' in data then exclude" and stores them as rule data.

[0660] Input: Text data as filtering criteria

[0661] Data Calculation: Generate rules from filtering conditions

[0662] Output: Rule data as filtering rules

[0663] Step 6:

[0664] The server applies the generated filtering rules to the data processing system in the vehicle by transmitting the rule data to the data filtering system installed in the vehicle, and the filtering rules are applied immediately.

[0665] Input: Rule data as filtering rules

[0666] Output: Filtering rules applied to the data processing system in the vehicle

[0667] Step 7:

[0668] The user confirms through the application that the filtering conditions have been applied. The device receives a notification from the server and displays a message confirming that the filtering settings have been applied correctly.

[0669] Input: Notification of completion of setup from the server

[0670] Output: Display confirming the configuration

[0671] Step 8:

[0672] Users can verify that the data processing system of the autonomous vehicle processes data according to the filtering rules and efficiently manage only the necessary data. This step allows users to confirm that the filtering settings are working as expected.

[0673] Input: Filtered data in the vehicle

[0674] Output: Check results filtered to only the required data

[0675] Through these steps, the system achieves efficient data filtering within an autonomous vehicle based on the user's natural language instructions.

[0676] 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.

[0677] This invention is a system that analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules that meet specific needs. This system is mainly composed of three elements: a server, a terminal, and a user.

[0678] Server-side processing

[0679] Receiving prompts

[0680] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[0681] Prompt and Sentiment Analysis

[0682] The server uses a generative AI model and an emotion engine to analyze the received prompt. The generative AI model includes natural language understanding technology, allowing it to accurately grasp the user's intent. At the same time, the emotion engine analyzes emotions from the user's prompt and recognizes emotional states such as anger, sadness, and joy. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[0683] Adjusting filtering conditions and generating rules

[0684] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[0685] Applying rules

[0686] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0687] Terminal side processing

[0688] Entering Prompts

[0689] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0690] Sending a prompt

[0691] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0692] Checking the Configuration

[0693] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0694] User processing

[0695] Preparation for use

[0696] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0697] Prompt Input

[0698] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0699] Checking the settings and using

[0700] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0701] Specific examples

[0702] Example 1: Filtering Amazon order history

[0703] User prompt input: "Filter my Amazon order history"

[0704] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[0705] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus additional conditions if stress is detected

[0706] Apply rules: Apply rules to the mail server and start filtering

[0707] Example 2: Excluding Amazon promotional emails

[0708] User prompt input: "Exclude Amazon promotional emails"

[0709] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[0710] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", with rules not adjusted based on sentiment

[0711] Apply rules: Apply rules to the mail server and start filtering

[0712] This system automatically generates and applies flexible and accurate filtering rules based on natural language input, taking into account the user's emotional state, thereby meeting diverse email filtering needs while significantly reducing the burden on users.

[0713] The processing flow will be explained below.

[0714] Step 1: Enter the prompt and submit

[0715] User: Enters filtering criteria in natural language through the device interface, providing specific requests such as "Filter my Amazon order history."

[0716] Terminal: Construct the user-supplied prompt as an HTTP POST or API request.

[0717] Terminal: Sends the constructed request to the server.

[0718] Step 2: Receiving the prompt

[0719] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[0720] Step 3: Prompt analysis and emotion recognition

[0721] Server: Inputs the received prompt into a generative AI model and begins analysis, for example using an AI model such as GPT-4.

[0722] Generative AI model: Uses natural language understanding techniques to analyze prompts and extract user intent. For example, from the prompt "Filter my Amazon order history," it extracts "From: no-reply@amazon.com" and "Subject contains 'order'."

[0723] Emotion Engine: Analyzes the user's emotions from prompts and recognizes their emotional state (happiness, sadness, anger, stress, etc.). This information is used to adjust filtering rules.

[0724] Step 4: Adjust filtering conditions and generate rules

[0725] Server: Generates specific filtering rules based on the extracted filtering conditions and the results of the emotion engine. For example, if the prompt "Filter Amazon order history" is stressful, the server sets a stricter filtering rule such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject."

[0726] Server: Stores the generated filtering rules in a database and converts them into an executable format.

[0727] Step 5: Applying rules

[0728] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[0729] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[0730] Step 6: Check your filtering settings

[0731] Mail server: After applying the rules, check that the filtering settings are working properly.

[0732] Server: Collects the confirmation results and notifies the device.

[0733] Step 7: Setup Complete Notification

[0734] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[0735] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[0736] Step 8: User review and use

[0737] User: Receives a notification on the device confirming that the filtering rules have been applied and confirms it.

[0738] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[0739] Example 2

[0740] 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."

[0741] Conventional email filtering systems required users to manually set detailed conditions, which often made the process complicated. Furthermore, they lacked the flexibility to filter according to the user's emotional state or stress level, making it difficult to accurately filter according to the user's intentions and emotions. This required users to go through the trouble of checking unwanted emails and risked filtering out necessary emails.

[0742] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for analyzing the user's emotions from the prompt using an emotion engine and recognizing the user's emotional state, means for automatically generating filtering rules to be applied to the mail server based on the filtering conditions and the emotional state, means for applying the filtering rules to the mail server, and means for notifying the user that application of the filtering rules has been completed. This enables flexible and accurate email filtering according to the user's natural language input and emotional state.

[0743] A "user" is a person who uses the system to configure email filtering.

[0744] "Natural language" refers to the language used by humans on a daily basis, not a specific program code or machine language.

[0745] A "prompt" refers to an instruction or request that a user enters in natural language.

[0746] A "generative AI model" is a system or program that uses artificial intelligence techniques to analyze input natural language prompts and extract specific conditions or information.

[0747] An "emotion engine" is a system or program that analyzes a user's emotional state from the user's prompts and recognizes emotions such as anger, sadness, and joy.

[0748] "Filtering conditions" are conditions or rules used to classify or filter out email based on specific criteria.

[0749] "Filtering rules" are settings for automatically receiving and classifying emails based on filtering conditions.

[0750] A "mail server" is a server that manages incoming and outgoing emails.

[0751] A "notification" is a message or alert from the server that tells the user that a particular operation or event has been completed.

[0752] This system analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules tailored to specific needs. This system is primarily composed of three elements: a server, a terminal, and a user.

[0753] Server-side implementation

[0754] The server receives a natural language prompt sent by the user, which includes a specific filtering request, such as "Filter my Amazon order history."

[0755] Parsing prompts

[0756] The server analyzes the received prompt using a generative AI model, which includes natural language understanding technology to accurately understand the user's intent.

[0757] Emotion Analysis

[0758] The server uses an emotion engine to analyze the user's emotions from the prompt and recognize their emotional state, such as anger, sadness, joy, etc. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[0759] Adjusting filtering conditions and generating rules

[0760] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[0761] Applying rules

[0762] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0763] Terminal side embodiment

[0764] Entering Prompts

[0765] The terminal provides an interface where users can input filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0766] Sending a prompt

[0767] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0768] Checking the Configuration

[0769] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0770] User-Side Embodiment

[0771] Preparation for use

[0772] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0773] Prompt Input

[0774] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0775] Checking the settings and using

[0776] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0777] Specific examples

[0778] Example 1: Filtering Amazon order history

[0779] User prompt input: "Filter my Amazon order history"

[0780] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[0781] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus apply additional conditions if stress is detected.

[0782] Apply rules: Apply rules to the mail server and start filtering.

[0783] Example 2: Excluding Amazon promotional emails

[0784] User prompt input: "Exclude Amazon promotional emails"

[0785] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[0786] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", to prevent rule adjustment based on sentiment.

[0787] Apply rules: Apply rules to the mail server and start filtering.

[0788] By applying this invention, flexible and accurate filtering rules can be automatically generated and applied based on natural language input, while also taking into account the user's emotional state. This makes it possible to meet a variety of email filtering needs and significantly reduce the burden on users.

[0789] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0790] Step 1: Enter the prompt (terminal)

[0791] The terminal provides the user with an interface for entering natural language prompts. The user enters a prompt such as "Filter my Amazon order history" into the interface and clicks a submit button, which inputs the user's request into the terminal in natural language format.

[0792] Input: A natural language prompt entered by the user

[0793] Output: The natural language prompt received on the terminal

[0794] Step 2: Sending a prompt (terminal)

[0795] The terminal sends the input prompt to the server, which receives the user's request.

[0796] Input: Natural language prompts received on the device

[0797] Output: The natural language prompt sent to the server

[0798] Step 3: Parsing prompts and emotions (server)

[0799] The server receives the natural language prompt sent from the device and begins analysis using the generative AI model and emotion engine. The generative AI model analyzes the prompt, converts it into structured data, and accurately grasps the user's intention. The emotion engine also analyzes the user's emotion from the prompt and recognizes emotional states such as anger, sadness, and joy.

[0800] Input: Natural language prompt sent from the terminal

[0801] Output: Parsed filtering conditions and the user's emotional state

[0802] Step 4: Adjusting filtering conditions and generating rules (server)

[0803] The server extracts filtering conditions based on the prompt and emotion analysis results, and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, a rule can be added to filter the target email more strictly.

[0804] Input: Parsed filtering conditions and the user's emotional state

[0805] Output: Generated filtering rules

[0806] Step 5: Applying filtering rules (server)

[0807] The server applies the generated filtering rules to the mail server, which allows mail to be automatically sorted upon receipt.

[0808] Input: Generated filtering rules

[0809] Output: Filtering rules applied to the mail server

[0810] Step 6: Notification of settings (server)

[0811] The server sends a message to the device notifying it that the filtering rules have been applied, allowing the user to confirm that the settings have been applied successfully.

[0812] Input: Filtering rules applied to the mail server

[0813] Output: Notification message to terminal

[0814] Step 7: Check the settings (device)

[0815] The terminal receives a notification from the server and displays to the user that the filtering settings have been completed. This process allows the user to confirm the settings.

[0816] Input: Notification message from the server

[0817] Output: A message on the terminal saying the setup is complete

[0818] Step 8: Preparation for use (user)

[0819] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0820] Input: Display of completed setup on terminal

[0821] Output: Mail application with filter settings enabled

[0822] Step 9: Check filtering application and use (user)

[0823] The user checks their inbox to ensure that the filtering rules were applied properly. They verify that their emails are being filtered properly and adjust as necessary.

[0824] Input: Email application with filter settings enabled

[0825] Output: Inbox with filtering rules applied

[0826] This allows users to filter emails according to their needs and feelings with minimal burden.

[0827] (Application example 2)

[0828] 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."

[0829] In conventional autonomous vehicles, passengers need to adjust the in-car environment and driving conditions through detailed settings and operations, which often reduces passenger comfort and convenience. Furthermore, there is a lack of technology to accurately recognize passenger emotions and intentions and reflect them in vehicle operation, making it difficult to provide services that meet individual needs. This has made it difficult to improve passenger satisfaction.

[0830] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0831] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions, means for applying the filtering rules to an in-vehicle adjustment system or a driving control system of an autonomous vehicle, means for analyzing user emotions using the generative AI model and an emotion analysis engine and adjusting the in-vehicle environment, and means for adjusting the in-vehicle environment of the autonomous vehicle, thereby enabling the in-vehicle environment and driving conditions to be automatically adjusted based on the specific needs and emotions of passengers.

[0832] "User" refers to a passenger who utilizes the system to adjust the vehicle's environmental settings and driving controls.

[0833] "Natural language" refers to a linguistic form that is directly input using words that humans use on a daily basis.

[0834] A "prompt" refers to a natural language input sentence that a user uses to give instructions or requests to a system.

[0835] A "generative AI model" refers to an artificial intelligence model that analyzes natural language and accurately understands the user's intentions and requests.

[0836] "Filtering conditions" refer to specific conditions extracted from user prompts for operating or adjusting the system.

[0837] A "mail server" refers to a server that manages and stores email.

[0838] The "filtering rule" refers to a rule for automatically performing a specific process based on the extracted filtering condition.

[0839] "Autonomous vehicle" refers to a vehicle that is capable of driving autonomously.

[0840] "In-vehicle conditioning system" refers to a system for adjusting the interior environment of an autonomous vehicle.

[0841] "Driving control system" refers to a system that controls the driving situation, speed, direction, etc. of an autonomous vehicle.

[0842] "Sentiment analysis engine" refers to an engine for analyzing and recognizing emotions from user prompts.

[0843] "In-vehicle environment" refers to the physical environment inside an autonomous vehicle, including temperature, music, and lighting.

[0844] This invention is a system for an autonomous vehicle that analyzes prompts entered in natural language by passengers, recognizes their emotions, and automatically adjusts the in-vehicle environment and driving situation. This system consists of three elements: a server, a terminal, and a user.

[0845] Server-side processing

[0846] Receiving prompts

[0847] The server receives natural language prompts entered by the passenger at the terminal, including requests related to specific environmental and driving conditions, such as "Turn down the music while driving."

[0848] Prompt and Sentiment Analysis

[0849] The server analyzes the received prompts using a generative AI model and a sentiment analysis engine. The generative AI model incorporates natural language understanding technology to accurately grasp the passenger's intent. At the same time, the sentiment analysis engine analyzes emotions from the prompts and recognizes emotional states such as anger, anxiety, and joy.

[0850] Generating adjustment conditions

[0851] Based on the prompt and emotion analysis results, the server extracts the environmental and driving conditions and generates adjustments to the in-car environment and driving controls based on them. For example, if a passenger requests "quieter music while driving" and the emotion analysis engine detects stress, the server will adjust the music volume down.

[0852] Application of conditions

[0853] The server then applies the generated adjustment conditions to the in-car adjustment system or driving control system, and this process automatically adjusts the passenger environment and driving conditions.

[0854] Terminal side processing

[0855] Entering Prompts

[0856] The device provides an interface that allows passengers to input environmental and driving conditions in natural language, such as specific requests like "Make the music quieter while driving."

[0857] Sending a prompt

[0858] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0859] Checking the Configuration

[0860] Once the server has generated and applied the conditions, a notification is sent to the terminal, allowing passengers to confirm that the settings have been applied successfully.

[0861] User processing

[0862] Preparation for use

[0863] The passenger simply turns on the device and confirms that the settings are enabled, and the adjustment function becomes available.

[0864] Prompt Input

[0865] Passengers input their environment and driving conditions using natural language, such as "Hurry to the next rest area," and click send.

[0866] Checking the settings and using

[0867] Passengers receive a notification from the server that the settings have been completed, confirm that the adjustments have been made properly, and then check whether the in-car environment and driving conditions have been adjusted properly, and make further adjustments if necessary.

[0868] Specific examples

[0869] Example 1: Quieting the music while driving

[0870] Passenger prompt input: "Quiet music while driving."

[0871] Server analysis: Extract the volume adjustment intent from the prompt and detect stress using an emotion analysis engine

[0872] Generate adjustment conditions: Generate conditions to lower the volume

[0873] Conditions apply: Apply to the in-car adjustment system to reduce the music volume

[0874] Example 2: When rushing to the next rest area

[0875] Passenger prompt input: "Hurry to the next rest area."

[0876] Server analysis: Extracting speed throttling intent from prompts

[0877] Generate tuning conditions: Generate conditions that increase speed within a limited range

[0878] Condition application: Apply to the driving control system and adjust the speed

[0879] The system can automatically adjust the in-car environment and driving conditions based on passengers' specific needs and emotions, providing a comfortable and personalized autonomous driving experience.

[0880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0881] Step 1:

[0882] Entering and submitting prompts

[0883] The user uses the terminal to input a natural language prompt about the environment or driving conditions, for example, "Turn down the music while driving," and clicks the send button. The terminal then sends this input to the server. The input is the natural language prompt, and the output is the transmission of the prompt data to the server.

[0884] Step 2:

[0885] Receiving prompts

[0886] The server receives natural language prompts sent from the terminal, where the input is the prompt data sent from the terminal and the output is the storage of the prompt data in the server.

[0887] Step 3:

[0888] Analysis using generative AI models

[0889] The server uses a generative AI model to analyze the received prompt. In this process, it understands the meaning of the prompt and extracts filtering conditions. The input is the received prompt data, and the output is the extracted filtering conditions.

[0890] Step 4:

[0891] Emotion recognition using an emotion analysis engine

[0892] The server uses an emotion analysis engine to recognize the user's emotion from the prompt, thereby understanding what emotional state the user is in (e.g., anger, stress, joy). The input is the prompt data, and the output is the analyzed emotion data.

[0893] Step 5:

[0894] Generating adjustment conditions

[0895] The server generates specific adjustment conditions based on the results of the generative AI model and the emotion analysis engine. For example, it creates specific operation conditions such as "lower the music volume" or "increase driving speed." The input is the filtering conditions and emotion data, and the output is the generated adjustment conditions.

[0896] Step 6:

[0897] Application of adjustment conditions

[0898] The server applies the generated adjustment conditions to the in-vehicle adjustment system or driving control system. This process reflects specific operations in the autonomous vehicle. The input is the adjustment conditions, and the output is the adjustment of the in-vehicle environment or driving situation.

[0899] Step 7:

[0900] Sending a notification of completion of setup

[0901] The server notifies the terminal that the adjustment has been completed. The user confirms through the terminal whether the adjustment was successful. The input is the information that the adjustment has been completed, and the output is a notification to the terminal.

[0902] Step 8:

[0903] Checking the settings and using

[0904] The user checks the notification on the device to see if the in-car environment and driving conditions have been adjusted as expected. If necessary, they can enter the prompt again to make adjustments. The input is the setting completion notification and the actual conditions in the car, and the output is the user's confirmation and re-entry if necessary.

[0905] Through these steps, users can easily adjust the environment and driving conditions of their autonomous vehicle using natural language prompts.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] [Third embodiment]

[0910] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0911] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0912] 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).

[0913] 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.

[0914] 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.

[0915] 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).

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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."

[0922] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main components: a server, a terminal, and a user.

[0923] Server-side processing

[0924] Receiving prompts

[0925] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[0926] Prompt Analysis

[0927] The server uses a generative AI model to analyze the incoming prompt. This model includes natural language understanding techniques to accurately understand the user's intent. For example, from the prompt "Filter my Amazon order history," the model extracts filtering criteria related to a specific sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders").

[0928] Creating filtering rules

[0929] Once the prompt is parsed, the server generates specific filtering rules based on the extracted conditions, such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject", which are automatically applied to the mail server.

[0930] Applying rules

[0931] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[0932] Terminal side processing

[0933] Entering Prompts

[0934] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[0935] Sending a prompt

[0936] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[0937] Checking the Configuration

[0938] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[0939] User processing

[0940] Preparation for use

[0941] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[0942] Prompt Input

[0943] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[0944] Checking the settings and using

[0945] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[0946] Specific examples

[0947] Example 1: Filtering Amazon order history

[0948] User prompt input: "Filter my Amazon order history"

[0949] Server parsing: Extract sender (no-reply@amazon.com) and subject (order) from the prompt

[0950] Generate filtering rule: "if sender == 'no-reply@amazon.com' and 'Orders' in subject"

[0951] Apply rules: Apply rules to the mail server and start filtering

[0952] Example 2: Excluding Amazon promotional emails

[0953] User prompt input: "Exclude Amazon promotional emails"

[0954] Server analysis: Prompt for emails with sender (promotions@amazon.com) or body containing 'sale'

[0955] Generate filtering rule: "if sender == 'promotions@amazon.com' or 'sale' in body"

[0956] Apply rules: Apply rules to the mail server and start filtering

[0957] In this way, the system analyzes the user's natural language input and automatically generates and applies flexible and accurate filtering rules, thereby meeting a variety of email filtering needs and significantly reducing the burden on users.

[0958] The processing flow will be explained below.

[0959] Step 1: Enter the prompt and submit

[0960] User: Enters a natural language prompt through the device interface, entering a specific request such as "Filter my Amazon order history."

[0961] Terminal: Receives user-supplied prompts and constructs them as HTTP POST or API requests.

[0962] Terminal: Sends the constructed request to the server.

[0963] Step 2: Receiving the prompt

[0964] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[0965] Step 3: Prompt Parsing

[0966] Server: Inputs the received prompt into a generative AI model and begins analysis, using a model such as GPT-4.

[0967] Generative AI model: Analyzes prompts using natural language understanding techniques to extract user intent. Based on the extracted intent, it identifies filtering conditions. For example, from the prompt "Filter Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject contains 'order'."

[0968] Step 4: Creating filtering rules

[0969] Server: Generate specific filtering rules using the extracted filtering conditions. For example, create a rule in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject".

[0970] Server: Stores the generated rules in a database and converts them into an executable format.

[0971] Step 5: Applying rules

[0972] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[0973] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[0974] Step 6: Check your filtering settings

[0975] Mail server: After applying the rules, check that the filtering settings are working properly.

[0976] Server: Collects the confirmation results and notifies the device.

[0977] Step 7: Setup Complete Notification

[0978] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[0979] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[0980] Step 8: User review and use

[0981] User: Receives a notification from the device confirming that the filtering rules have been applied and confirms it.

[0982] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[0983] Example 1

[0984] 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."

[0985] Conventional email filtering systems have the drawback of requiring users to manually set rules, which is time-consuming and makes it difficult to achieve flexible and accurate filtering. Furthermore, the system requires specialized knowledge, making it difficult for general users to use. Furthermore, responding to diverse email filtering needs requires a huge amount of time and effort, making efficient email management difficult.

[0986] 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.

[0987] In this invention, the server includes means for receiving instructions input by a user in natural language, means for analyzing the instructions using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to the communication server based on the filtering conditions, and means for applying the filtering rules to the communication server. This allows the user to set highly accurate filtering settings simply by inputting in natural language, enabling efficient and flexible email sorting.

[0988] "User" refers to any person or entity utilizing the system to enter prompts in natural language.

[0989] An "instruction" is a message entered by a user in natural language that includes a specific filtering condition.

[0990] A "generative AI model" refers to an artificial intelligence algorithm for natural language understanding and analysis, primarily based on deep learning techniques.

[0991] "Filtering conditions" are specific conditions extracted based on user instructions, and include keywords in the sender, subject, or body of the email.

[0992] "Filtering rules" refer to email sorting rules that are automatically generated based on the extracted filtering conditions.

[0993] A "communication server" refers to a server that manages the sending and receiving of emails, and is the target to which filtering rules are applied.

[0994] "Means for receiving" refers to a system component for receiving instructions from a user.

[0995] "Means for analyzing" refers to a system component that analyzes received instructions using a generative AI model and extracts filtering conditions.

[0996] "Means for automatically generating" refers to a system component for generating filtering rules based on the parsed filtering conditions.

[0997] "Means for applying" refers to a system component for setting and applying the generated filtering rules to the communication server.

[0998] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main elements: a server, a terminal, and a user.

[0999] 1. Server-side processing

[1000] The server receives a natural language prompt input from the user's device, which includes specific filtering requests such as "filter my Amazon order history" or "exclude Amazon promotional emails."

[1001] First, the server puts a specific API endpoint into a waiting state. When a prompt is sent as a POST request, it reads and temporarily stores the prompt. Next, the server uses a generative AI model (e.g., a model using natural language processing technology) to analyze the prompt and understand the user's intent. As a result of the analysis, filtering conditions related to the sender, subject, and body of the message are extracted. For example, from the prompt "Filter my Amazon order history," the sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders") are extracted.

[1002] The server then automatically generates filtering rules based on the extracted conditions. These rules are generated in the format of "if sender == 'no-reply@amazon.com' and 'Orders' in subject". The generated filtering rules are added by the server to the mail server's configuration file and are automatically applied when receiving emails.

[1003] 2. Terminal processing

[1004] The terminal provides an interface that allows users to input filtering conditions in natural language. For example, users can simply enter specific conditions such as "Exclude Amazon promotional emails" and click the submit button. When the submit button is clicked, the terminal sends the input prompt text as a POST request to the server.

[1005] When the server completes the creation and application of filtering rules, it sends a notification to the device, which then displays a pop-up message or notification bar to inform the user that the settings have been completed.

[1006] 3. User-side processing

[1007] The user first launches the email application and confirms that the filter setting function is enabled. Next, the user enters filtering conditions in natural language and clicks the send button. For example, the user enters instructions such as "Save all important Amazon notifications." After receiving a notification from the server that the settings have been completed, the user checks their inbox and confirms that filtering has been performed correctly.

[1008] Using a generative AI model, the system converts users' natural language input into flexible, tailored filtering rules, allowing users to easily set up advanced filtering and efficiently manage their emails.

[1009] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1010] Step 1:

[1011] Input: The user enters a prompt sentence in natural language.

[1012] Server: Receives the prompt statement.

[1013] Specific operation: The server monitors the API endpoint and receives the prompt text sent by the user through the terminal (e.g., "Filter my Amazon order history") as a POST request. The received prompt text is temporarily stored in a database or memory.

[1014] Output: The saved prompt statement.

[1015] Step 2:

[1016] Input: The saved prompt statement.

[1017] Server: Analyzes the prompt sentence using a generative AI model.

[1018] Specific operation: The server inputs the received prompt into a generative AI model and analyzes it using natural language understanding technology. The generative AI model (e.g., GPT-4) analyzes the prompt and extracts filtering conditions related to the sender address and subject. For example, from the prompt "Filter my Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject: Order."

[1019] Output: The extracted filtering conditions.

[1020] Step 3:

[1021] Input: The extracted filtering criteria.

[1022] Server: Automatically generates filtering rules based on filtering conditions.

[1023] Specific operation: The server automatically generates filtering rules based on the extracted filtering conditions. Specifically, it executes a script that generates filtering rules in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject" based on the conditions.

[1024] Output: The generated filtering rules.

[1025] Step 4:

[1026] Input: The generated filtering rules.

[1027] Server: The generated filtering rules are applied to the mail server.

[1028] What happens: The server runs a script to add the generated filtering rules to the mail server's configuration file. After adding the rules, the mail server will sort emails according to the new filtering rules.

[1029] Output: The applied filtering rules.

[1030] Step 5:

[1031] Input: The user's prompt and any filtering rules that have been applied.

[1032] Terminal: Receives notification that the filtering rules have been applied.

[1033] Specific operation: The server notifies the device that the application of the filtering rules has been completed. This notification is sent from the server to the device in JSON format, and the device notifies the user via a pop-up message or notification bar.

[1034] Output: A message informing you that the configuration is complete.

[1035] Step 6:

[1036] Input: Email with filtering applied.

[1037] User: Check the filtering results in your email application.

[1038] Specific behavior: The user launches an email application and checks the inbox or a specific folder. The user verifies that emails are properly sorted according to the configured filtering rules. For example, the user checks to see if the Amazon order history email has been properly moved to a specific folder.

[1039] Output: Check the filtering results.

[1040] (Application example 1)

[1041] 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."

[1042] Autonomous vehicles receive massive amounts of data from numerous sensors in real time. Managing this data efficiently and extracting only the necessary information is important for improving vehicle performance and ensuring safety. However, manually filtering each sensor's data is extremely time-consuming and the accuracy is unstable. To solve this issue, there is a need for a system that automates data filtering within autonomous vehicles and allows users to easily configure it.

[1043] 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.

[1044] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model to extract filtering conditions, and means for automatically generating filtering rules to be applied to an in-vehicle data processing system based on the filtering conditions, thereby enabling efficient data management within an autonomous vehicle and enabling only required data to be extracted quickly and accurately.

[1045] A "user" is a person who rides in an autonomous vehicle and configures data filtering.

[1046] "Natural language" refers to the language used by humans on a daily basis, and refers to human language, not a specific programming language or code.

[1047] A "prompt" is an instruction or request entered in natural language by a user to specify data filtering criteria.

[1048] A "means for receiving" is an interface or device for receiving a prompt from a user.

[1049] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze a user's natural language and extract specific data conditions.

[1050] "Analyzing means" refers to a processing device that uses a generative AI model to derive data filtering conditions from the prompts.

[1051] "Filtering conditions" are the conditions that the user specifies as the criteria for extracting or excluding data.

[1052] An "in-vehicle data processing system" is a system for processing sensor data and various information in real time within an autonomous vehicle.

[1053] The "filtering rules" are set rules for selecting and discarding data based on the extracted filtering conditions.

[1054] "Means for automatic generation" refers to programs or algorithms that use generative AI models to create specific filtering rules from filtering conditions.

[1055] The present invention provides a system for automatically generating filtering rules to be applied to a data processing system in an autonomous vehicle by analyzing a prompt input in natural language by a user. Specific embodiments of the system are described below.

[1056] Hardware and Software Configuration

[1057] The system consists of a server that receives user input and analyzes the data using a generative AI model, and a terminal where users can enter prompts. The terminal is a smartphone or tablet with a dedicated application installed. The server is installed on the cloud and has high-performance data processing capabilities.

[1058] Program processing explanation

[1059] Terminal side processing

[1060] 1. Enter the prompt:

[1061] Users launch the smartphone application and input data filtering criteria in natural language, such as "don't record license plate information of cars ahead" or "save only data related to multiple lane changes."

[1062] 2. Send prompt:

[1063] The device sends the input prompt to the cloud server as JSON format data using an HTTP POST request.

[1064] Server-side processing

[1065] 1. Receiving prompts:

[1066] The server receives the prompt received from the terminal.

[1067] 2. Prompt analysis:

[1068] The server uses a generative AI model to analyze the received prompt. The generative AI model includes natural language understanding technology and can accurately analyze the user's intent. For example, from the prompt "Do not record the license plate information of the car ahead," it can extract the condition to exclude data about the car ahead.

[1069] 3. Create filtering rules:

[1070] Based on the analysis results, filtering rules are automatically generated, such as "if 'vehicle ahead' in data and 'license plate information' in data then exclude."

[1071] 4. Rules apply:

[1072] The generated filtering rules are applied to the vehicle's data processing system, which then filters out sensor data that meets specific conditions.

[1073] User processing

[1074] 1. Preparation for use:

[1075] The user confirms through the application that the filtering conditions have been applied.

[1076] 2. Check the settings:

[1077] Verify that your filter settings were applied correctly and receive notifications to let you know that your settings have been applied.

[1078] 3. Continued Use:

[1079] The data processing system of the autonomous vehicle processes data according to filtering rules, allowing users to efficiently manage only the data they need.

[1080] Examples and prompts

[1081] Example 1: Do not record the license plate information of the car ahead

[1082] Example 2: Save only data related to multiple lane changes

[1083] Based on the above prompts, the system can perform real-time conditional filtering and provide data management according to the user's preferences.

[1084] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1085] Step 1:

[1086] The user starts the smartphone application and inputs data filtering conditions in natural language, such as prompts like "Don't record license plate information of cars ahead" or "Save only data related to multiple lane changes." These prompts are then input into the application as text data.

[1087] Input: A natural language prompt

[1088] Output: Input text data

[1089] Step 2:

[1090] The device sends the input prompt to the cloud server using an HTTP POST request, sending the input prompt text as JSON format data.

[1091] Input: Prompt sentence entered as text data

[1092] Output: JSON format data

[1093] Step 3:

[1094] The server receives the prompt (JSON format data) from the device. An API is implemented to receive this data.

[1095] Input: Prompt data in JSON format

[1096] Output: Received JSON data

[1097] Step 4:

[1098] The server uses a generative AI model to analyze the received prompt and extract filtering conditions. At this time, the generative AI model (including natural language understanding technology) analyzes the user's intent and extracts specific filtering conditions (e.g., "Ignore the license plate information of the car ahead") as text data.

[1099] Input: Received JSON data

[1100] Data processing: Analyzing prompts using generative AI models

[1101] Output: Text data as filtering criteria

[1102] Step 5:

[1103] The server automatically generates filtering rules based on the extracted filtering conditions. For example, it generates filtering rules in the format "if 'vehicle ahead' in data and 'license plate information' in data then exclude" and stores them as rule data.

[1104] Input: Text data as filtering criteria

[1105] Data Calculation: Generate rules from filtering conditions

[1106] Output: Rule data as filtering rules

[1107] Step 6:

[1108] The server applies the generated filtering rules to the data processing system in the vehicle by transmitting the rule data to the data filtering system installed in the vehicle, and the filtering rules are applied immediately.

[1109] Input: Rule data as filtering rules

[1110] Output: Filtering rules applied to the data processing system in the vehicle

[1111] Step 7:

[1112] The user confirms through the application that the filtering conditions have been applied. The device receives a notification from the server and displays a message confirming that the filtering settings have been applied correctly.

[1113] Input: Notification of completion of setup from the server

[1114] Output: Display confirming the configuration

[1115] Step 8:

[1116] Users can verify that the data processing system of the autonomous vehicle processes data according to the filtering rules and efficiently manage only the necessary data. This step allows users to confirm that the filtering settings are working as expected.

[1117] Input: Filtered data in the vehicle

[1118] Output: Check results filtered to only the required data

[1119] Through these steps, the system achieves efficient data filtering within an autonomous vehicle based on the user's natural language instructions.

[1120] 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.

[1121] This invention is a system that analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules that meet specific needs. This system is mainly composed of three elements: a server, a terminal, and a user.

[1122] Server-side processing

[1123] Receiving prompts

[1124] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[1125] Prompt and Sentiment Analysis

[1126] The server uses a generative AI model and an emotion engine to analyze the received prompt. The generative AI model includes natural language understanding technology, allowing it to accurately grasp the user's intent. At the same time, the emotion engine analyzes emotions from the user's prompt and recognizes emotional states such as anger, sadness, and joy. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[1127] Adjusting filtering conditions and generating rules

[1128] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[1129] Applying rules

[1130] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[1131] Terminal side processing

[1132] Entering Prompts

[1133] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[1134] Sending a prompt

[1135] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1136] Checking the Configuration

[1137] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[1138] User processing

[1139] Preparation for use

[1140] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1141] Prompt Input

[1142] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[1143] Checking the settings and using

[1144] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[1145] Specific examples

[1146] Example 1: Filtering Amazon order history

[1147] User prompt input: "Filter my Amazon order history"

[1148] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[1149] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus additional conditions if stress is detected

[1150] Apply rules: Apply rules to the mail server and start filtering

[1151] Example 2: Excluding Amazon promotional emails

[1152] User prompt input: "Exclude Amazon promotional emails"

[1153] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[1154] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", with rules not adjusted based on sentiment

[1155] Apply rules: Apply rules to the mail server and start filtering

[1156] This system automatically generates and applies flexible and accurate filtering rules based on natural language input, taking into account the user's emotional state, thereby meeting diverse email filtering needs while significantly reducing the burden on users.

[1157] The processing flow will be explained below.

[1158] Step 1: Enter the prompt and submit

[1159] User: Enters filtering criteria in natural language through the device interface, providing specific requests such as "Filter my Amazon order history."

[1160] Terminal: Construct the user-supplied prompt as an HTTP POST or API request.

[1161] Terminal: Sends the constructed request to the server.

[1162] Step 2: Receiving the prompt

[1163] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[1164] Step 3: Prompt analysis and emotion recognition

[1165] Server: Inputs the received prompt into a generative AI model and begins analysis, for example using an AI model such as GPT-4.

[1166] Generative AI model: Uses natural language understanding techniques to analyze prompts and extract user intent. For example, from the prompt "Filter my Amazon order history," it extracts "From: no-reply@amazon.com" and "Subject contains 'order'."

[1167] Emotion Engine: Analyzes the user's emotions from prompts and recognizes their emotional state (happiness, sadness, anger, stress, etc.). This information is used to adjust filtering rules.

[1168] Step 4: Adjust filtering conditions and generate rules

[1169] Server: Generates specific filtering rules based on the extracted filtering conditions and the results of the emotion engine. For example, if the prompt "Filter Amazon order history" is stressful, the server sets a stricter filtering rule such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject."

[1170] Server: Stores the generated filtering rules in a database and converts them into an executable format.

[1171] Step 5: Applying rules

[1172] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[1173] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[1174] Step 6: Check your filtering settings

[1175] Mail server: After applying the rules, check that the filtering settings are working properly.

[1176] Server: Collects the confirmation results and notifies the device.

[1177] Step 7: Setup Complete Notification

[1178] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[1179] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[1180] Step 8: User review and use

[1181] User: Receives a notification on the device confirming that the filtering rules have been applied and confirms it.

[1182] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[1183] Example 2

[1184] 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."

[1185] Conventional email filtering systems required users to manually set detailed conditions, which often made the process complicated. Furthermore, they lacked the flexibility to filter according to the user's emotional state or stress level, making it difficult to accurately filter according to the user's intentions and emotions. This required users to go through the trouble of checking unwanted emails and risked filtering out necessary emails.

[1186] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for analyzing the user's emotions from the prompt using an emotion engine and recognizing the user's emotional state, means for automatically generating filtering rules to be applied to the mail server based on the filtering conditions and the emotional state, means for applying the filtering rules to the mail server, and means for notifying the user that application of the filtering rules has been completed. This enables flexible and accurate email filtering according to the user's natural language input and emotional state.

[1187] A "user" is a person who uses the system to configure email filtering.

[1188] "Natural language" refers to the language used by humans on a daily basis, not a specific program code or machine language.

[1189] A "prompt" refers to an instruction or request that a user enters in natural language.

[1190] A "generative AI model" is a system or program that uses artificial intelligence techniques to analyze input natural language prompts and extract specific conditions or information.

[1191] An "emotion engine" is a system or program that analyzes a user's emotional state from the user's prompts and recognizes emotions such as anger, sadness, and joy.

[1192] "Filtering conditions" are conditions or rules used to classify or filter out email based on specific criteria.

[1193] "Filtering rules" are settings for automatically receiving and classifying emails based on filtering conditions.

[1194] A "mail server" is a server that manages incoming and outgoing emails.

[1195] A "notification" is a message or alert from the server that tells the user that a particular operation or event has been completed.

[1196] This system analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules tailored to specific needs. This system is primarily composed of three elements: a server, a terminal, and a user.

[1197] Server-side implementation

[1198] The server receives a natural language prompt sent by the user, which includes a specific filtering request, such as "Filter my Amazon order history."

[1199] Parsing prompts

[1200] The server analyzes the received prompt using a generative AI model, which includes natural language understanding technology to accurately understand the user's intent.

[1201] Emotion Analysis

[1202] The server uses an emotion engine to analyze the user's emotions from the prompt and recognize their emotional state, such as anger, sadness, joy, etc. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[1203] Adjusting filtering conditions and generating rules

[1204] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[1205] Applying rules

[1206] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[1207] Terminal side embodiment

[1208] Entering Prompts

[1209] The terminal provides an interface where users can input filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[1210] Sending a prompt

[1211] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1212] Checking the Configuration

[1213] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[1214] User-Side Embodiment

[1215] Preparation for use

[1216] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1217] Prompt Input

[1218] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[1219] Checking the settings and using

[1220] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[1221] Specific examples

[1222] Example 1: Filtering Amazon order history

[1223] User prompt input: "Filter my Amazon order history"

[1224] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[1225] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus apply additional conditions if stress is detected.

[1226] Apply rules: Apply rules to the mail server and start filtering.

[1227] Example 2: Excluding Amazon promotional emails

[1228] User prompt input: "Exclude Amazon promotional emails"

[1229] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[1230] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", to prevent rule adjustment based on sentiment.

[1231] Apply rules: Apply rules to the mail server and start filtering.

[1232] By applying this invention, flexible and accurate filtering rules can be automatically generated and applied based on natural language input, while also taking into account the user's emotional state. This makes it possible to meet a variety of email filtering needs and significantly reduce the burden on users.

[1233] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1234] Step 1: Enter the prompt (terminal)

[1235] The terminal provides the user with an interface for entering natural language prompts. The user enters a prompt such as "Filter my Amazon order history" into the interface and clicks a submit button, which inputs the user's request into the terminal in natural language format.

[1236] Input: A natural language prompt entered by the user

[1237] Output: The natural language prompt received on the terminal

[1238] Step 2: Sending a prompt (terminal)

[1239] The terminal sends the input prompt to the server, which receives the user's request.

[1240] Input: Natural language prompts received on the device

[1241] Output: The natural language prompt sent to the server

[1242] Step 3: Parsing prompts and emotions (server)

[1243] The server receives the natural language prompt sent from the device and begins analysis using the generative AI model and emotion engine. The generative AI model analyzes the prompt, converts it into structured data, and accurately grasps the user's intention. The emotion engine also analyzes the user's emotion from the prompt and recognizes emotional states such as anger, sadness, and joy.

[1244] Input: Natural language prompt sent from the terminal

[1245] Output: Parsed filtering conditions and the user's emotional state

[1246] Step 4: Adjusting filtering conditions and generating rules (server)

[1247] The server extracts filtering conditions based on the prompt and emotion analysis results, and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, a rule can be added to filter the target email more strictly.

[1248] Input: Parsed filtering conditions and the user's emotional state

[1249] Output: Generated filtering rules

[1250] Step 5: Applying filtering rules (server)

[1251] The server applies the generated filtering rules to the mail server, which allows mail to be automatically sorted upon receipt.

[1252] Input: Generated filtering rules

[1253] Output: Filtering rules applied to the mail server

[1254] Step 6: Notification of settings (server)

[1255] The server sends a message to the device notifying it that the filtering rules have been applied, allowing the user to confirm that the settings have been applied successfully.

[1256] Input: Filtering rules applied to the mail server

[1257] Output: Notification message to terminal

[1258] Step 7: Check the settings (device)

[1259] The terminal receives a notification from the server and displays to the user that the filtering settings have been completed. This process allows the user to confirm the settings.

[1260] Input: Notification message from the server

[1261] Output: A message on the terminal saying the setup is complete

[1262] Step 8: Preparation for use (user)

[1263] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1264] Input: Display of completed setup on terminal

[1265] Output: Mail application with filter settings enabled

[1266] Step 9: Check filtering application and use (user)

[1267] The user checks their inbox to ensure that the filtering rules were applied properly. They verify that their emails are being filtered properly and adjust as necessary.

[1268] Input: Email application with filter settings enabled

[1269] Output: Inbox with filtering rules applied

[1270] This allows users to filter emails according to their needs and feelings with minimal burden.

[1271] (Application example 2)

[1272] 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."

[1273] In conventional autonomous vehicles, passengers need to adjust the in-car environment and driving conditions through detailed settings and operations, which often reduces passenger comfort and convenience. Furthermore, there is a lack of technology to accurately recognize passenger emotions and intentions and reflect them in vehicle operation, making it difficult to provide services that meet individual needs. This has made it difficult to improve passenger satisfaction.

[1274] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1275] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions, means for applying the filtering rules to an in-vehicle adjustment system or a driving control system of an autonomous vehicle, means for analyzing user emotions using the generative AI model and an emotion analysis engine and adjusting the in-vehicle environment, and means for adjusting the in-vehicle environment of the autonomous vehicle, thereby enabling the in-vehicle environment and driving conditions to be automatically adjusted based on the specific needs and emotions of passengers.

[1276] "User" refers to a passenger who utilizes the system to adjust the vehicle's environmental settings and driving controls.

[1277] "Natural language" refers to a linguistic form that is directly input using words that humans use on a daily basis.

[1278] A "prompt" refers to a natural language input sentence that a user uses to give instructions or requests to a system.

[1279] A "generative AI model" refers to an artificial intelligence model that analyzes natural language and accurately understands the user's intentions and requests.

[1280] "Filtering conditions" refer to specific conditions extracted from user prompts for operating or adjusting the system.

[1281] A "mail server" refers to a server that manages and stores email.

[1282] The "filtering rule" refers to a rule for automatically performing a specific process based on the extracted filtering condition.

[1283] "Autonomous vehicle" refers to a vehicle that is capable of driving autonomously.

[1284] "In-vehicle conditioning system" refers to a system for adjusting the interior environment of an autonomous vehicle.

[1285] "Driving control system" refers to a system that controls the driving situation, speed, direction, etc. of an autonomous vehicle.

[1286] "Sentiment analysis engine" refers to an engine for analyzing and recognizing emotions from user prompts.

[1287] "In-vehicle environment" refers to the physical environment inside an autonomous vehicle, including temperature, music, and lighting.

[1288] This invention is a system for an autonomous vehicle that analyzes prompts entered in natural language by passengers, recognizes their emotions, and automatically adjusts the in-vehicle environment and driving situation. This system consists of three elements: a server, a terminal, and a user.

[1289] Server-side processing

[1290] Receiving prompts

[1291] The server receives natural language prompts entered by the passenger at the terminal, including requests related to specific environmental and driving conditions, such as "Turn down the music while driving."

[1292] Prompt and Sentiment Analysis

[1293] The server analyzes the received prompts using a generative AI model and a sentiment analysis engine. The generative AI model incorporates natural language understanding technology to accurately grasp the passenger's intent. At the same time, the sentiment analysis engine analyzes emotions from the prompts and recognizes emotional states such as anger, anxiety, and joy.

[1294] Generating adjustment conditions

[1295] Based on the prompt and emotion analysis results, the server extracts the environmental and driving conditions and generates adjustments to the in-car environment and driving controls based on them. For example, if a passenger requests "quieter music while driving" and the emotion analysis engine detects stress, the server will adjust the music volume down.

[1296] Application of conditions

[1297] The server then applies the generated adjustment conditions to the in-car adjustment system or driving control system, and this process automatically adjusts the passenger environment and driving conditions.

[1298] Terminal side processing

[1299] Entering Prompts

[1300] The device provides an interface that allows passengers to input environmental and driving conditions in natural language, such as specific requests like "Make the music quieter while driving."

[1301] Sending a prompt

[1302] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1303] Checking the Configuration

[1304] Once the server has generated and applied the conditions, a notification is sent to the terminal, allowing passengers to confirm that the settings have been applied successfully.

[1305] User processing

[1306] Preparation for use

[1307] The passenger simply turns on the device and confirms that the settings are enabled, and the adjustment function becomes available.

[1308] Prompt Input

[1309] Passengers input their environment and driving conditions using natural language, such as "Hurry to the next rest area," and click send.

[1310] Checking the settings and using

[1311] Passengers receive a notification from the server that the settings have been completed, confirm that the adjustments have been made properly, and then check whether the in-car environment and driving conditions have been adjusted properly, and make further adjustments if necessary.

[1312] Specific examples

[1313] Example 1: Quieting the music while driving

[1314] Passenger prompt input: "Quiet music while driving."

[1315] Server analysis: Extract the volume adjustment intent from the prompt and detect stress using an emotion analysis engine

[1316] Generate adjustment conditions: Generate conditions to lower the volume

[1317] Conditions apply: Apply to the in-car adjustment system to reduce the music volume

[1318] Example 2: When rushing to the next rest area

[1319] Passenger prompt input: "Hurry to the next rest area."

[1320] Server analysis: Extracting speed throttling intent from prompts

[1321] Generate tuning conditions: Generate conditions that increase speed within a limited range

[1322] Condition application: Apply to the driving control system and adjust the speed

[1323] The system can automatically adjust the in-car environment and driving conditions based on passengers' specific needs and emotions, providing a comfortable and personalized autonomous driving experience.

[1324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1325] Step 1:

[1326] Entering and submitting prompts

[1327] The user uses the terminal to input a natural language prompt about the environment or driving conditions, for example, "Turn down the music while driving," and clicks the send button. The terminal then sends this input to the server. The input is the natural language prompt, and the output is the transmission of the prompt data to the server.

[1328] Step 2:

[1329] Receiving prompts

[1330] The server receives natural language prompts sent from the terminal, where the input is the prompt data sent from the terminal and the output is the storage of the prompt data in the server.

[1331] Step 3:

[1332] Analysis using generative AI models

[1333] The server uses a generative AI model to analyze the received prompt. In this process, it understands the meaning of the prompt and extracts filtering conditions. The input is the received prompt data, and the output is the extracted filtering conditions.

[1334] Step 4:

[1335] Emotion recognition using an emotion analysis engine

[1336] The server uses an emotion analysis engine to recognize the user's emotion from the prompt, thereby understanding what emotional state the user is in (e.g., anger, stress, joy). The input is the prompt data, and the output is the analyzed emotion data.

[1337] Step 5:

[1338] Generating adjustment conditions

[1339] The server generates specific adjustment conditions based on the results of the generative AI model and the emotion analysis engine. For example, it creates specific operation conditions such as "lower the music volume" or "increase driving speed." The input is the filtering conditions and emotion data, and the output is the generated adjustment conditions.

[1340] Step 6:

[1341] Application of adjustment conditions

[1342] The server applies the generated adjustment conditions to the in-vehicle adjustment system or driving control system. This process reflects specific operations in the autonomous vehicle. The input is the adjustment conditions, and the output is the adjustment of the in-vehicle environment or driving situation.

[1343] Step 7:

[1344] Sending a notification of completion of setup

[1345] The server notifies the terminal that the adjustment has been completed. The user confirms through the terminal whether the adjustment was successful. The input is the information that the adjustment has been completed, and the output is a notification to the terminal.

[1346] Step 8:

[1347] Checking the settings and using

[1348] The user checks the notification on the device to see if the in-car environment and driving conditions have been adjusted as expected. If necessary, they can enter the prompt again to make adjustments. The input is the setting completion notification and the actual conditions in the car, and the output is the user's confirmation and re-entry if necessary.

[1349] Through these steps, users can easily adjust the environment and driving conditions of their autonomous vehicle using natural language prompts.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] [Fourth embodiment]

[1354] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1355] 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.

[1356] 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).

[1357] 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.

[1358] 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.

[1359] 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).

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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."

[1367] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main components: a server, a terminal, and a user.

[1368] Server-side processing

[1369] Receiving prompts

[1370] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[1371] Prompt Analysis

[1372] The server uses a generative AI model to analyze the incoming prompt. This model includes natural language understanding techniques to accurately understand the user's intent. For example, from the prompt "Filter my Amazon order history," the model extracts filtering criteria related to a specific sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders").

[1373] Creating filtering rules

[1374] Once the prompt is parsed, the server generates specific filtering rules based on the extracted conditions, such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject", which are automatically applied to the mail server.

[1375] Applying rules

[1376] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[1377] Terminal side processing

[1378] Entering Prompts

[1379] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[1380] Sending a prompt

[1381] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1382] Checking the Configuration

[1383] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[1384] User processing

[1385] Preparation for use

[1386] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1387] Prompt Input

[1388] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[1389] Checking the settings and using

[1390] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[1391] Specific examples

[1392] Example 1: Filtering Amazon order history

[1393] User prompt input: "Filter my Amazon order history"

[1394] Server parsing: Extract sender (no-reply@amazon.com) and subject (order) from the prompt

[1395] Generate filtering rule: "if sender == 'no-reply@amazon.com' and 'Orders' in subject"

[1396] Apply rules: Apply rules to the mail server and start filtering

[1397] Example 2: Excluding Amazon promotional emails

[1398] User prompt input: "Exclude Amazon promotional emails"

[1399] Server analysis: Prompt for emails with sender (promotions@amazon.com) or body containing 'sale'

[1400] Generate filtering rule: "if sender == 'promotions@amazon.com' or 'sale' in body"

[1401] Apply rules: Apply rules to the mail server and start filtering

[1402] In this way, the system analyzes the user's natural language input and automatically generates and applies flexible and accurate filtering rules, thereby meeting a variety of email filtering needs and significantly reducing the burden on users.

[1403] The processing flow will be explained below.

[1404] Step 1: Enter the prompt and submit

[1405] User: Enters a natural language prompt through the device interface, entering a specific request such as "Filter my Amazon order history."

[1406] Terminal: Receives user-supplied prompts and constructs them as HTTP POST or API requests.

[1407] Terminal: Sends the constructed request to the server.

[1408] Step 2: Receiving the prompt

[1409] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[1410] Step 3: Prompt Parsing

[1411] Server: Inputs the received prompt into a generative AI model and begins analysis, using a model such as GPT-4.

[1412] Generative AI model: Analyzes prompts using natural language understanding techniques to extract user intent. Based on the extracted intent, it identifies filtering conditions. For example, from the prompt "Filter Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject contains 'order'."

[1413] Step 4: Creating filtering rules

[1414] Server: Generate specific filtering rules using the extracted filtering conditions. For example, create a rule in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject".

[1415] Server: Stores the generated rules in a database and converts them into an executable format.

[1416] Step 5: Applying rules

[1417] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[1418] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[1419] Step 6: Check your filtering settings

[1420] Mail server: After applying the rules, check that the filtering settings are working properly.

[1421] Server: Collects the confirmation results and notifies the device.

[1422] Step 7: Setup Complete Notification

[1423] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[1424] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[1425] Step 8: User review and use

[1426] User: Receives a notification from the device confirming that the filtering rules have been applied and confirms it.

[1427] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[1428] Example 1

[1429] 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."

[1430] Conventional email filtering systems have the drawback of requiring users to manually set rules, which is time-consuming and makes it difficult to achieve flexible and accurate filtering. Furthermore, the system requires specialized knowledge, making it difficult for general users to use. Furthermore, responding to diverse email filtering needs requires a huge amount of time and effort, making efficient email management difficult.

[1431] 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.

[1432] In this invention, the server includes means for receiving instructions input by a user in natural language, means for analyzing the instructions using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to the communication server based on the filtering conditions, and means for applying the filtering rules to the communication server. This allows the user to set highly accurate filtering settings simply by inputting in natural language, enabling efficient and flexible email sorting.

[1433] "User" refers to any person or entity utilizing the system to enter prompts in natural language.

[1434] An "instruction" is a message entered by a user in natural language that includes a specific filtering condition.

[1435] A "generative AI model" refers to an artificial intelligence algorithm for natural language understanding and analysis, primarily based on deep learning techniques.

[1436] "Filtering conditions" are specific conditions extracted based on user instructions, and include keywords in the sender, subject, or body of the email.

[1437] "Filtering rules" refer to email sorting rules that are automatically generated based on the extracted filtering conditions.

[1438] A "communication server" refers to a server that manages the sending and receiving of emails, and is the target to which filtering rules are applied.

[1439] "Means for receiving" refers to a system component for receiving instructions from a user.

[1440] "Means for analyzing" refers to a system component that analyzes received instructions using a generative AI model and extracts filtering conditions.

[1441] "Means for automatically generating" refers to a system component for generating filtering rules based on the parsed filtering conditions.

[1442] "Means for applying" refers to a system component for setting and applying the generated filtering rules to the communication server.

[1443] This invention is a system that analyzes prompts entered by users in natural language and automatically generates flexible email filtering rules tailored to specific needs. This system consists of three main elements: a server, a terminal, and a user.

[1444] 1. Server-side processing

[1445] The server receives a natural language prompt input from the user's device, which includes specific filtering requests such as "filter my Amazon order history" or "exclude Amazon promotional emails."

[1446] First, the server puts a specific API endpoint into a waiting state. When a prompt is sent as a POST request, it reads and temporarily stores the prompt. Next, the server uses a generative AI model (e.g., a model using natural language processing technology) to analyze the prompt and understand the user's intent. As a result of the analysis, filtering conditions related to the sender, subject, and body of the message are extracted. For example, from the prompt "Filter my Amazon order history," the sender (e.g., no-reply@amazon.com) and subject (e.g., "Orders") are extracted.

[1447] The server then automatically generates filtering rules based on the extracted conditions. These rules are generated in the format of "if sender == 'no-reply@amazon.com' and 'Orders' in subject". The generated filtering rules are added by the server to the mail server's configuration file and are automatically applied when receiving emails.

[1448] 2. Terminal processing

[1449] The terminal provides an interface that allows users to input filtering conditions in natural language. For example, users can simply enter specific conditions such as "Exclude Amazon promotional emails" and click the submit button. When the submit button is clicked, the terminal sends the input prompt text as a POST request to the server.

[1450] When the server completes the creation and application of filtering rules, it sends a notification to the device, which then displays a pop-up message or notification bar to inform the user that the settings have been completed.

[1451] 3. User-side processing

[1452] The user first launches the email application and confirms that the filter setting function is enabled. Next, the user enters filtering conditions in natural language and clicks the send button. For example, the user enters instructions such as "Save all important Amazon notifications." After receiving a notification from the server that the settings have been completed, the user checks their inbox and confirms that filtering has been performed correctly.

[1453] Using a generative AI model, the system converts users' natural language input into flexible, tailored filtering rules, allowing users to easily set up advanced filtering and efficiently manage their emails.

[1454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1455] Step 1:

[1456] Input: The user enters a prompt sentence in natural language.

[1457] Server: Receives the prompt statement.

[1458] Specific operation: The server monitors the API endpoint and receives the prompt text sent by the user through the terminal (e.g., "Filter my Amazon order history") as a POST request. The received prompt text is temporarily stored in a database or memory.

[1459] Output: The saved prompt statement.

[1460] Step 2:

[1461] Input: The saved prompt statement.

[1462] Server: Analyzes the prompt sentence using a generative AI model.

[1463] Specific operation: The server inputs the received prompt into a generative AI model and analyzes it using natural language understanding technology. The generative AI model (e.g., GPT-4) analyzes the prompt and extracts filtering conditions related to the sender address and subject. For example, from the prompt "Filter my Amazon order history," it extracts "Sender: no-reply@amazon.com" and "Subject: Order."

[1464] Output: The extracted filtering conditions.

[1465] Step 3:

[1466] Input: The extracted filtering criteria.

[1467] Server: Automatically generates filtering rules based on filtering conditions.

[1468] Specific operation: The server automatically generates filtering rules based on the extracted filtering conditions. Specifically, it executes a script that generates filtering rules in the format "if sender == 'no-reply@amazon.com' and 'Orders' in subject" based on the conditions.

[1469] Output: The generated filtering rules.

[1470] Step 4:

[1471] Input: The generated filtering rules.

[1472] Server: The generated filtering rules are applied to the mail server.

[1473] What happens: The server runs a script to add the generated filtering rules to the mail server's configuration file. After adding the rules, the mail server will sort emails according to the new filtering rules.

[1474] Output: The applied filtering rules.

[1475] Step 5:

[1476] Input: The user's prompt and any filtering rules that have been applied.

[1477] Terminal: Receives notification that the filtering rules have been applied.

[1478] Specific operation: The server notifies the device that the application of the filtering rules has been completed. This notification is sent from the server to the device in JSON format, and the device notifies the user via a pop-up message or notification bar.

[1479] Output: A message informing you that the configuration is complete.

[1480] Step 6:

[1481] Input: Email with filtering applied.

[1482] User: Check the filtering results in your email application.

[1483] Specific behavior: The user launches an email application and checks the inbox or a specific folder. The user verifies that emails are properly sorted according to the configured filtering rules. For example, the user checks to see if the Amazon order history email has been properly moved to a specific folder.

[1484] Output: Check the filtering results.

[1485] (Application example 1)

[1486] 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."

[1487] Autonomous vehicles receive massive amounts of data from numerous sensors in real time. Managing this data efficiently and extracting only the necessary information is important for improving vehicle performance and ensuring safety. However, manually filtering each sensor's data is extremely time-consuming and the accuracy is unstable. To solve this issue, there is a need for a system that automates data filtering within autonomous vehicles and allows users to easily configure it.

[1488] 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.

[1489] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model to extract filtering conditions, and means for automatically generating filtering rules to be applied to an in-vehicle data processing system based on the filtering conditions, thereby enabling efficient data management within an autonomous vehicle and enabling only required data to be extracted quickly and accurately.

[1490] A "user" is a person who rides in an autonomous vehicle and configures data filtering.

[1491] "Natural language" refers to the language used by humans on a daily basis, and refers to human language, not a specific programming language or code.

[1492] A "prompt" is an instruction or request entered in natural language by a user to specify data filtering criteria.

[1493] A "means for receiving" is an interface or device for receiving a prompt from a user.

[1494] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze a user's natural language and extract specific data conditions.

[1495] "Analyzing means" refers to a processing device that uses a generative AI model to derive data filtering conditions from the prompts.

[1496] "Filtering conditions" are the conditions that the user specifies as the criteria for extracting or excluding data.

[1497] An "in-vehicle data processing system" is a system for processing sensor data and various information in real time within an autonomous vehicle.

[1498] The "filtering rules" are set rules for selecting and discarding data based on the extracted filtering conditions.

[1499] "Means for automatic generation" refers to programs or algorithms that use generative AI models to create specific filtering rules from filtering conditions.

[1500] The present invention provides a system for automatically generating filtering rules to be applied to a data processing system in an autonomous vehicle by analyzing a prompt input in natural language by a user. Specific embodiments of the system are described below.

[1501] Hardware and Software Configuration

[1502] The system consists of a server that receives user input and analyzes the data using a generative AI model, and a terminal where users can enter prompts. The terminal is a smartphone or tablet with a dedicated application installed. The server is installed on the cloud and has high-performance data processing capabilities.

[1503] Program processing explanation

[1504] Terminal side processing

[1505] 1. Enter the prompt:

[1506] Users launch the smartphone application and input data filtering criteria in natural language, such as "don't record license plate information of cars ahead" or "save only data related to multiple lane changes."

[1507] 2. Send prompt:

[1508] The device sends the input prompt to the cloud server as JSON format data using an HTTP POST request.

[1509] Server-side processing

[1510] 1. Receiving prompts:

[1511] The server receives the prompt received from the terminal.

[1512] 2. Prompt analysis:

[1513] The server uses a generative AI model to analyze the received prompt. The generative AI model includes natural language understanding technology and can accurately analyze the user's intent. For example, from the prompt "Do not record the license plate information of the car ahead," it can extract the condition to exclude data about the car ahead.

[1514] 3. Create filtering rules:

[1515] Based on the analysis results, filtering rules are automatically generated, such as "if 'vehicle ahead' in data and 'license plate information' in data then exclude."

[1516] 4. Rules apply:

[1517] The generated filtering rules are applied to the vehicle's data processing system, which then filters out sensor data that meets specific conditions.

[1518] User processing

[1519] 1. Preparation for use:

[1520] The user confirms through the application that the filtering conditions have been applied.

[1521] 2. Check the settings:

[1522] Verify that your filter settings were applied correctly and receive notifications to let you know that your settings have been applied.

[1523] 3. Continued Use:

[1524] The data processing system of the autonomous vehicle processes data according to filtering rules, allowing users to efficiently manage only the data they need.

[1525] Examples and prompts

[1526] Example 1: Do not record the license plate information of the car ahead

[1527] Example 2: Save only data related to multiple lane changes

[1528] Based on the above prompts, the system can perform real-time conditional filtering and provide data management according to the user's preferences.

[1529] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1530] Step 1:

[1531] The user starts the smartphone application and inputs data filtering conditions in natural language, such as prompts like "Don't record license plate information of cars ahead" or "Save only data related to multiple lane changes." These prompts are then input into the application as text data.

[1532] Input: A natural language prompt

[1533] Output: Input text data

[1534] Step 2:

[1535] The device sends the input prompt to the cloud server using an HTTP POST request, sending the input prompt text as JSON format data.

[1536] Input: Prompt sentence entered as text data

[1537] Output: JSON format data

[1538] Step 3:

[1539] The server receives the prompt (JSON format data) from the device. An API is implemented to receive this data.

[1540] Input: Prompt data in JSON format

[1541] Output: Received JSON data

[1542] Step 4:

[1543] The server uses a generative AI model to analyze the received prompt and extract filtering conditions. At this time, the generative AI model (including natural language understanding technology) analyzes the user's intent and extracts specific filtering conditions (e.g., "Ignore the license plate information of the car ahead") as text data.

[1544] Input: Received JSON data

[1545] Data processing: Analyzing prompts using generative AI models

[1546] Output: Text data as filtering criteria

[1547] Step 5:

[1548] The server automatically generates filtering rules based on the extracted filtering conditions. For example, it generates filtering rules in the format "if 'vehicle ahead' in data and 'license plate information' in data then exclude" and stores them as rule data.

[1549] Input: Text data as filtering criteria

[1550] Data Calculation: Generate rules from filtering conditions

[1551] Output: Rule data as filtering rules

[1552] Step 6:

[1553] The server applies the generated filtering rules to the data processing system in the vehicle by transmitting the rule data to the data filtering system installed in the vehicle, and the filtering rules are applied immediately.

[1554] Input: Rule data as filtering rules

[1555] Output: Filtering rules applied to the data processing system in the vehicle

[1556] Step 7:

[1557] The user confirms through the application that the filtering conditions have been applied. The device receives a notification from the server and displays a message confirming that the filtering settings have been applied correctly.

[1558] Input: Notification of completion of setup from the server

[1559] Output: Display confirming the configuration

[1560] Step 8:

[1561] Users can verify that the data processing system of the autonomous vehicle processes data according to the filtering rules and efficiently manage only the necessary data. This step allows users to confirm that the filtering settings are working as expected.

[1562] Input: Filtered data in the vehicle

[1563] Output: Check results filtered to only the required data

[1564] Through these steps, the system achieves efficient data filtering within an autonomous vehicle based on the user's natural language instructions.

[1565] 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.

[1566] This invention is a system that analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules that meet specific needs. This system is mainly composed of three elements: a server, a terminal, and a user.

[1567] Server-side processing

[1568] Receiving prompts

[1569] The server receives a natural language prompt entered by the user at the device, which includes a specific filtering request, such as "Filter my Amazon order history."

[1570] Prompt and Sentiment Analysis

[1571] The server uses a generative AI model and an emotion engine to analyze the received prompt. The generative AI model includes natural language understanding technology, allowing it to accurately grasp the user's intent. At the same time, the emotion engine analyzes emotions from the user's prompt and recognizes emotional states such as anger, sadness, and joy. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[1572] Adjusting filtering conditions and generating rules

[1573] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[1574] Applying rules

[1575] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[1576] Terminal side processing

[1577] Entering Prompts

[1578] The terminal provides an interface where users can enter filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[1579] Sending a prompt

[1580] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1581] Checking the Configuration

[1582] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[1583] User processing

[1584] Preparation for use

[1585] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1586] Prompt Input

[1587] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[1588] Checking the settings and using

[1589] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[1590] Specific examples

[1591] Example 1: Filtering Amazon order history

[1592] User prompt input: "Filter my Amazon order history"

[1593] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[1594] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus additional conditions if stress is detected

[1595] Apply rules: Apply rules to the mail server and start filtering

[1596] Example 2: Excluding Amazon promotional emails

[1597] User prompt input: "Exclude Amazon promotional emails"

[1598] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[1599] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", with rules not adjusted based on sentiment

[1600] Apply rules: Apply rules to the mail server and start filtering

[1601] This system automatically generates and applies flexible and accurate filtering rules based on natural language input, taking into account the user's emotional state, thereby meeting diverse email filtering needs while significantly reducing the burden on users.

[1602] The processing flow will be explained below.

[1603] Step 1: Enter the prompt and submit

[1604] User: Enters filtering criteria in natural language through the device interface, providing specific requests such as "Filter my Amazon order history."

[1605] Terminal: Construct the user-supplied prompt as an HTTP POST or API request.

[1606] Terminal: Sends the constructed request to the server.

[1607] Step 2: Receiving the prompt

[1608] Server: Receives prompts from the terminal at an HTTP endpoint and stores them as logs in a database (optional).

[1609] Step 3: Prompt analysis and emotion recognition

[1610] Server: Inputs the received prompt into a generative AI model and begins analysis, for example using an AI model such as GPT-4.

[1611] Generative AI model: Uses natural language understanding techniques to analyze prompts and extract user intent. For example, from the prompt "Filter my Amazon order history," it extracts "From: no-reply@amazon.com" and "Subject contains 'order'."

[1612] Emotion Engine: Analyzes the user's emotions from prompts and recognizes their emotional state (happiness, sadness, anger, stress, etc.). This information is used to adjust filtering rules.

[1613] Step 4: Adjust filtering conditions and generate rules

[1614] Server: Generates specific filtering rules based on the extracted filtering conditions and the results of the emotion engine. For example, if the prompt "Filter Amazon order history" is stressful, the server sets a stricter filtering rule such as "if sender == 'no-reply@amazon.com' and 'Orders' in subject."

[1615] Server: Stores the generated filtering rules in a database and converts them into an executable format.

[1616] Step 5: Applying rules

[1617] Server: Distributes the generated filtering rules to the mail server and instructs it to apply them.

[1618] Mail Server: Receives new filtering rules and adds or modifies existing filter settings.

[1619] Step 6: Check your filtering settings

[1620] Mail server: After applying the rules, check that the filtering settings are working properly.

[1621] Server: Collects the confirmation results and notifies the device.

[1622] Step 7: Setup Complete Notification

[1623] Server: Sends a prompt processing and filtering rule setting completion notification to the user terminal.

[1624] Terminal: Receives notification from the server and displays to the user that the filtering rule has been applied successfully.

[1625] Step 8: User review and use

[1626] User: Receives a notification on the device confirming that the filtering rules have been applied and confirms it.

[1627] Users: Use their email application to check that filtering is working properly in their inbox and reset it if necessary.

[1628] Example 2

[1629] 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."

[1630] Conventional email filtering systems required users to manually set detailed conditions, which often made the process complicated. Furthermore, they lacked the flexibility to filter according to the user's emotional state or stress level, making it difficult to accurately filter according to the user's intentions and emotions. This required users to go through the trouble of checking unwanted emails and risked filtering out necessary emails.

[1631] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for analyzing the user's emotions from the prompt using an emotion engine and recognizing the user's emotional state, means for automatically generating filtering rules to be applied to the mail server based on the filtering conditions and the emotional state, means for applying the filtering rules to the mail server, and means for notifying the user that application of the filtering rules has been completed. This enables flexible and accurate email filtering according to the user's natural language input and emotional state.

[1632] A "user" is a person who uses the system to configure email filtering.

[1633] "Natural language" refers to the language used by humans on a daily basis, not a specific program code or machine language.

[1634] A "prompt" refers to an instruction or request that a user enters in natural language.

[1635] A "generative AI model" is a system or program that uses artificial intelligence techniques to analyze input natural language prompts and extract specific conditions or information.

[1636] An "emotion engine" is a system or program that analyzes a user's emotional state from the user's prompts and recognizes emotions such as anger, sadness, and joy.

[1637] "Filtering conditions" are conditions or rules used to classify or filter out email based on specific criteria.

[1638] "Filtering rules" are settings for automatically receiving and classifying emails based on filtering conditions.

[1639] A "mail server" is a server that manages incoming and outgoing emails.

[1640] A "notification" is a message or alert from the server that tells the user that a particular operation or event has been completed.

[1641] This system analyzes prompts entered by users in natural language and combines them with an emotion engine that recognizes the user's emotions to automatically generate email filtering rules tailored to specific needs. This system is primarily composed of three elements: a server, a terminal, and a user.

[1642] Server-side implementation

[1643] The server receives a natural language prompt sent by the user, which includes a specific filtering request, such as "Filter my Amazon order history."

[1644] Parsing prompts

[1645] The server analyzes the received prompt using a generative AI model, which includes natural language understanding technology to accurately understand the user's intent.

[1646] Emotion Analysis

[1647] The server uses an emotion engine to analyze the user's emotions from the prompt and recognize their emotional state, such as anger, sadness, joy, etc. For example, in response to the prompt "Filter my Amazon order history," the emotion engine can sense the user's stress.

[1648] Adjusting filtering conditions and generating rules

[1649] Based on the prompt and emotion analysis results, the server extracts filtering conditions and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, it generates rules to filter the target email more strictly.

[1650] Applying rules

[1651] The generated filtering rules are applied to the mail server by the server, and mail is automatically sorted upon receipt, allowing users to efficiently manage their mail.

[1652] Terminal side embodiment

[1653] Entering Prompts

[1654] The terminal provides an interface where users can input filtering criteria in natural language. Users can simply enter the prompts and click the submit button. For example, they can enter specific criteria such as "Exclude Amazon promotional emails."

[1655] Sending a prompt

[1656] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1657] Checking the Configuration

[1658] Once the server has created and applied the filtering rules, a notification is sent to the device, allowing the user to confirm that the filtering settings have been applied successfully.

[1659] User-Side Embodiment

[1660] Preparation for use

[1661] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1662] Prompt Input

[1663] Users enter filtering criteria in natural language, such as "save all important Amazon notifications," into the interface and click submit.

[1664] Checking the settings and using

[1665] The user receives a notification from the server that the settings have been completed, and confirms that the filtering rules have been applied properly. After that, the user can check whether the filtering is working properly in their inbox and adjust it if necessary.

[1666] Specific examples

[1667] Example 1: Filtering Amazon order history

[1668] User prompt input: "Filter my Amazon order history"

[1669] Server analysis: Extract the sender (no-reply@amazon.com) and subject (order) from the prompt, and use the emotion engine to recognize that the user is stressed.

[1670] Generate filtering rules: "if sender == 'no-reply@amazon.com' and 'Orders' in subject" plus apply additional conditions if stress is detected.

[1671] Apply rules: Apply rules to the mail server and start filtering.

[1672] Example 2: Excluding Amazon promotional emails

[1673] User prompt input: "Exclude Amazon promotional emails"

[1674] Server analysis: Extract emails from the prompt that contain the sender (promotions@amazon.com) or the word 'sale' in the body, and use the emotion engine to recognize that the user is feeling happy.

[1675] Generate filtering rules: "if sender == 'promotions@amazon.com' or 'sale' in body", to prevent rule adjustment based on sentiment.

[1676] Apply rules: Apply rules to the mail server and start filtering.

[1677] By applying this invention, flexible and accurate filtering rules can be automatically generated and applied based on natural language input, while also taking into account the user's emotional state. This makes it possible to meet a variety of email filtering needs and significantly reduce the burden on users.

[1678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1679] Step 1: Enter the prompt (terminal)

[1680] The terminal provides the user with an interface for entering natural language prompts. The user enters a prompt such as "Filter my Amazon order history" into the interface and clicks a submit button, which inputs the user's request into the terminal in natural language format.

[1681] Input: A natural language prompt entered by the user

[1682] Output: The natural language prompt received on the terminal

[1683] Step 2: Sending a prompt (terminal)

[1684] The terminal sends the input prompt to the server, which receives the user's request.

[1685] Input: Natural language prompts received on the device

[1686] Output: The natural language prompt sent to the server

[1687] Step 3: Parsing prompts and emotions (server)

[1688] The server receives the natural language prompt sent from the device and begins analysis using the generative AI model and emotion engine. The generative AI model analyzes the prompt, converts it into structured data, and accurately grasps the user's intention. The emotion engine also analyzes the user's emotion from the prompt and recognizes emotional states such as anger, sadness, and joy.

[1689] Input: Natural language prompt sent from the terminal

[1690] Output: Parsed filtering conditions and the user's emotional state

[1691] Step 4: Adjusting filtering conditions and generating rules (server)

[1692] The server extracts filtering conditions based on the prompt and emotion analysis results, and generates filtering rules based on them. It is also possible to adjust the filtering conditions based on the results of the emotion engine. For example, if the user is feeling stressed, a rule can be added to filter the target email more strictly.

[1693] Input: Parsed filtering conditions and the user's emotional state

[1694] Output: Generated filtering rules

[1695] Step 5: Applying filtering rules (server)

[1696] The server applies the generated filtering rules to the mail server, which allows mail to be automatically sorted upon receipt.

[1697] Input: Generated filtering rules

[1698] Output: Filtering rules applied to the mail server

[1699] Step 6: Notification of settings (server)

[1700] The server sends a message to the device notifying it that the filtering rules have been applied, allowing the user to confirm that the settings have been applied successfully.

[1701] Input: Filtering rules applied to the mail server

[1702] Output: Notification message to terminal

[1703] Step 7: Check the settings (device)

[1704] The terminal receives a notification from the server and displays to the user that the filtering settings have been completed. This process allows the user to confirm the settings.

[1705] Input: Notification message from the server

[1706] Output: A message on the terminal saying the setup is complete

[1707] Step 8: Preparation for use (user)

[1708] The user starts the email application and checks that the filter setting function is enabled, thereby making the filtering function available.

[1709] Input: Display of completed setup on terminal

[1710] Output: Mail application with filter settings enabled

[1711] Step 9: Check filtering application and use (user)

[1712] The user checks their inbox to ensure that the filtering rules were applied properly. They verify that their emails are being filtered properly and adjust as necessary.

[1713] Input: Email application with filter settings enabled

[1714] Output: Inbox with filtering rules applied

[1715] This allows users to filter emails according to their needs and feelings with minimal burden.

[1716] (Application example 2)

[1717] 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."

[1718] In conventional autonomous vehicles, passengers need to adjust the in-car environment and driving conditions through detailed settings and operations, which often reduces passenger comfort and convenience. Furthermore, there is a lack of technology to accurately recognize passenger emotions and intentions and reflect them in vehicle operation, making it difficult to provide services that meet individual needs. This has made it difficult to improve passenger satisfaction.

[1719] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1720] In this invention, the server includes means for receiving a prompt input by a user in natural language, means for analyzing the prompt using a generative AI model and extracting filtering conditions, means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions, means for applying the filtering rules to an in-vehicle adjustment system or a driving control system of an autonomous vehicle, means for analyzing user emotions using the generative AI model and an emotion analysis engine and adjusting the in-vehicle environment, and means for adjusting the in-vehicle environment of the autonomous vehicle, thereby enabling the in-vehicle environment and driving conditions to be automatically adjusted based on the specific needs and emotions of passengers.

[1721] "User" refers to a passenger who utilizes the system to adjust the vehicle's environmental settings and driving controls.

[1722] "Natural language" refers to a linguistic form that is directly input using words that humans use on a daily basis.

[1723] A "prompt" refers to a natural language input sentence that a user uses to give instructions or requests to a system.

[1724] A "generative AI model" refers to an artificial intelligence model that analyzes natural language and accurately understands the user's intentions and requests.

[1725] "Filtering conditions" refer to specific conditions extracted from user prompts for operating or adjusting the system.

[1726] A "mail server" refers to a server that manages and stores email.

[1727] The "filtering rule" refers to a rule for automatically performing a specific process based on the extracted filtering condition.

[1728] "Autonomous vehicle" refers to a vehicle that is capable of driving autonomously.

[1729] "In-vehicle conditioning system" refers to a system for adjusting the interior environment of an autonomous vehicle.

[1730] "Driving control system" refers to a system that controls the driving situation, speed, direction, etc. of an autonomous vehicle.

[1731] "Sentiment analysis engine" refers to an engine for analyzing and recognizing emotions from user prompts.

[1732] "In-vehicle environment" refers to the physical environment inside an autonomous vehicle, including temperature, music, and lighting.

[1733] This invention is a system for an autonomous vehicle that analyzes prompts entered in natural language by passengers, recognizes their emotions, and automatically adjusts the in-vehicle environment and driving situation. This system consists of three elements: a server, a terminal, and a user.

[1734] Server-side processing

[1735] Receiving prompts

[1736] The server receives natural language prompts entered by the passenger at the terminal, including requests related to specific environmental and driving conditions, such as "Turn down the music while driving."

[1737] Prompt and Sentiment Analysis

[1738] The server analyzes the received prompts using a generative AI model and a sentiment analysis engine. The generative AI model incorporates natural language understanding technology to accurately grasp the passenger's intent. At the same time, the sentiment analysis engine analyzes emotions from the prompts and recognizes emotional states such as anger, anxiety, and joy.

[1739] Generating adjustment conditions

[1740] Based on the prompt and emotion analysis results, the server extracts the environmental and driving conditions and generates adjustments to the in-car environment and driving controls based on them. For example, if a passenger requests "quieter music while driving" and the emotion analysis engine detects stress, the server will adjust the music volume down.

[1741] Application of conditions

[1742] The server then applies the generated adjustment conditions to the in-car adjustment system or driving control system, and this process automatically adjusts the passenger environment and driving conditions.

[1743] Terminal side processing

[1744] Entering Prompts

[1745] The device provides an interface that allows passengers to input environmental and driving conditions in natural language, such as specific requests like "Make the music quieter while driving."

[1746] Sending a prompt

[1747] The terminal sends the entered prompt to the server, which receives the prompt and begins parsing it.

[1748] Checking the Configuration

[1749] Once the server has generated and applied the conditions, a notification is sent to the terminal, allowing passengers to confirm that the settings have been applied successfully.

[1750] User processing

[1751] Preparation for use

[1752] The passenger simply turns on the device and confirms that the settings are enabled, and the adjustment function becomes available.

[1753] Prompt Input

[1754] Passengers input their environment and driving conditions using natural language, such as "Hurry to the next rest area," and click send.

[1755] Checking the settings and using

[1756] Passengers receive a notification from the server that the settings have been completed, confirm that the adjustments have been made properly, and then check whether the in-car environment and driving conditions have been adjusted properly, and make further adjustments if necessary.

[1757] Specific examples

[1758] Example 1: Quieting the music while driving

[1759] Passenger prompt input: "Quiet music while driving."

[1760] Server analysis: Extract the volume adjustment intent from the prompt and detect stress using an emotion analysis engine

[1761] Generate adjustment conditions: Generate conditions to lower the volume

[1762] Conditions apply: Apply to the in-car adjustment system to reduce the music volume

[1763] Example 2: When rushing to the next rest area

[1764] Passenger prompt input: "Hurry to the next rest area."

[1765] Server analysis: Extracting speed throttling intent from prompts

[1766] Generate tuning conditions: Generate conditions that increase speed within a limited range

[1767] Condition application: Apply to the driving control system and adjust the speed

[1768] The system can automatically adjust the in-car environment and driving conditions based on passengers' specific needs and emotions, providing a comfortable and personalized autonomous driving experience.

[1769] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1770] Step 1:

[1771] Entering and submitting prompts

[1772] The user uses the terminal to input a natural language prompt about the environment or driving conditions, for example, "Turn down the music while driving," and clicks the send button. The terminal then sends this input to the server. The input is the natural language prompt, and the output is the transmission of the prompt data to the server.

[1773] Step 2:

[1774] Receiving prompts

[1775] The server receives natural language prompts sent from the terminal, where the input is the prompt data sent from the terminal and the output is the storage of the prompt data in the server.

[1776] Step 3:

[1777] Analysis using generative AI models

[1778] The server uses a generative AI model to analyze the received prompt. In this process, it understands the meaning of the prompt and extracts filtering conditions. The input is the received prompt data, and the output is the extracted filtering conditions.

[1779] Step 4:

[1780] Emotion recognition using an emotion analysis engine

[1781] The server uses an emotion analysis engine to recognize the user's emotion from the prompt, thereby understanding what emotional state the user is in (e.g., anger, stress, joy). The input is the prompt data, and the output is the analyzed emotion data.

[1782] Step 5:

[1783] Generating adjustment conditions

[1784] The server generates specific adjustment conditions based on the results of the generative AI model and the emotion analysis engine. For example, it creates specific operation conditions such as "lower the music volume" or "increase driving speed." The input is the filtering conditions and emotion data, and the output is the generated adjustment conditions.

[1785] Step 6:

[1786] Application of adjustment conditions

[1787] The server applies the generated adjustment conditions to the in-vehicle adjustment system or driving control system. This process reflects specific operations in the autonomous vehicle. The input is the adjustment conditions, and the output is the adjustment of the in-vehicle environment or driving situation.

[1788] Step 7:

[1789] Sending a notification of completion of setup

[1790] The server notifies the terminal that the adjustment has been completed. The user confirms through the terminal whether the adjustment was successful. The input is the information that the adjustment has been completed, and the output is a notification to the terminal.

[1791] Step 8:

[1792] Checking the settings and using

[1793] The user checks the notification on the device to see if the in-car environment and driving conditions have been adjusted as expected. If necessary, they can enter the prompt again to make adjustments. The input is the setting completion notification and the actual conditions in the car, and the output is the user's confirmation and re-entry if necessary.

[1794] Through these steps, users can easily adjust the environment and driving conditions of their autonomous vehicle using natural language prompts.

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] 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.

[1800] 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.

[1801] 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).

[1802] 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.

[1803] 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."

[1804] 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.

[1805] 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).

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] The following is further disclosed regarding the above embodiment.

[1817] (Claim 1)

[1818] means for receiving a prompt input by the user in natural language;

[1819] means for analyzing the prompt and extracting filtering conditions using a generative AI model;

[1820] means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions;

[1821] The system includes means for applying the filtering rules to the mail server.

[1822] (Claim 2)

[1823] 10. The system of claim 1, wherein the generative AI model includes natural language understanding techniques.

[1824] (Claim 3)

[1825] 2. The system according to claim 1, wherein a filtering rule is generated based on a user's prompt, the filtering rule being based on any one of keywords in the sender, subject, or body of the email.

[1826] "Example 1"

[1827] (Claim 1)

[1828] means for receiving instructions input by a user in a natural language;

[1829] A means for analyzing the instruction sentence and extracting a filtering condition using a generative AI model;

[1830] means for automatically generating filtering rules to be applied to the communication server based on the filtering conditions;

[1831] A system including means for applying said filtering rules to said communication server.

[1832] (Claim 2)

[1833] 10. The system of claim 1, wherein the generative AI model includes natural language understanding techniques.

[1834] (Claim 3)

[1835] 2. The system according to claim 1, wherein a filtering rule is generated based on a user instruction, the filtering rule being based on any one of keywords in the sender, subject, or body of the email.

[1836] "Application Example 1"

[1837] (Claim 1)

[1838] means for receiving a prompt input by the user in natural language;

[1839] means for analyzing the prompt and extracting filtering conditions using a generative AI model;

[1840] means for automatically generating filtering rules to be applied to a data processing system in a vehicle based on the filtering conditions;

[1841] A system including means for applying said filtering rules to a data processing system within said vehicle.

[1842] (Claim 2)

[1843] 10. The system of claim 1, wherein the generative AI model includes natural language understanding techniques.

[1844] (Claim 3)

[1845] 10. The system of claim 1, wherein the system generates rules to filter specific conditions (e.g., keywords in sender, subject, or body) of the sensor data based on a user prompt.

[1846] "Example 2: Combining Emotion Engines"

[1847] (Claim 1)

[1848] means for receiving a prompt input by the user in natural language;

[1849] means for analyzing the prompt using a generative AI model to extract filtering conditions;

[1850] means for analyzing a user's emotion from the prompt using an emotion engine to recognize an emotional state;

[1851] means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions and emotional state;

[1852] means for applying the filtering rules to the mail server;

[1853] The system further includes a means for notifying a user that application of the filtering rules has been completed.

[1854] (Claim 2)

[1855] 10. The system of claim 1, wherein the generative AI model includes natural language understanding techniques.

[1856] (Claim 3)

[1857] The system of claim 1, wherein the system generates filtering rules based on a user prompt, the filtering rules being based on keywords in the sender, subject, or body of the email, and adjusts the filtering conditions based on the emotional state of the emotion engine.

[1858] "Application example 2 when combining emotion engines"

[1859] (Claim 1)

[1860] means for receiving a prompt input by the user in natural language;

[1861] means for analyzing the prompt and extracting filtering conditions using a generative AI model;

[1862] means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions;

[1863] means for applying the filtering rules to an in-vehicle coordination system or driving control system of an autonomous vehicle;

[1864] A means for analyzing a user's emotions and adjusting the in-car environment using the generative AI model and an emotion analysis engine;

[1865] A system including means for adjusting an interior environment of the autonomous vehicle.

[1866] (Claim 2)

[1867] 10. The system of claim 1, wherein the generative AI model includes natural language understanding techniques.

[1868] (Claim 3)

[1869] 10. The system of claim 1, wherein the system generates in-vehicle environment settings or driving control conditions based on a user prompt. [Explanation of symbols]

[1870] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a prompt input by the user in natural language; means for analyzing the prompt and extracting filtering conditions using a generative AI model; means for automatically generating filtering rules to be applied to a mail server based on the filtering conditions; The system includes means for applying the filtering rules to the mail server.

2. The system of claim 1 , wherein the generative AI model includes natural language understanding techniques.

3. 2. The system according to claim 1, wherein a filtering rule is generated based on a user's prompt, the filtering rule being based on any one of sender, subject, and body keywords.

Images