System
A system that converts natural language requests into program code using AI, allowing non-experts to easily create and use programs, addresses the inefficiencies of traditional programming by reducing effort and cost.
Patent Information
- Application Number
- JP2024140272
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2026-03-06
AI Technical Summary
Traditional program creation requires specialized programming knowledge, is time-consuming, and costly, and manual coding is inefficient, making it difficult for non-experts to generate and use programs.
A system that receives user requests in natural language, uses natural language processing to analyze and convert them into technical specifications, generates program code with an AI module, and displays the code on a terminal for execution, allowing users to create and use programs without programming knowledge.
Significantly reduces the effort and cost associated with program creation by enabling non-experts to easily generate and use programs, while providing efficient and accurate conversion of natural language requests into executable code.
Smart Images

Figure 2026037247000001_ABST
Abstract
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] Traditionally, creating a program required specialized programming knowledge, which was a major barrier for users without programming knowledge. It also required the involvement of specialized engineers or the purchase of expensive software, resulting in time-consuming and costly problems. Furthermore, even simple programs required manual coding, which was inefficient. There is a need to solve these issues and provide a system that allows anyone to easily automatically generate and use the necessary programs. [Means for solving the problem]
[0005] In order to solve the above problems, the present invention provides the following means. The present invention is a system including: means for receiving a user request in natural language; means for transmitting the request to a server; a server including an AI module for generating program code based on the request; means for returning the generated program code to a terminal; and means for displaying the generated program code to the user and making it available. The system also includes means for analyzing the user request using natural language processing technology and generating program code based on the analyzed request. This allows users to easily create and use programs even if they have no programming knowledge.
[0006] "Means for receiving user requests in natural language" refers to an interface that allows program specifications and functions to be input in natural language.
[0007] The "means for transmitting the request to the server" refers to a network communication protocol and associated software for transmitting a request entered in natural language from a terminal to a server.
[0008] A "server including an AI module that generates program code based on the request" is a server equipped with artificial intelligence that analyzes a received request and automatically generates program code appropriate to that request.
[0009] The "means for returning the generated program code to the terminal" refers to a network communication protocol and associated software for transmitting the program code generated by the server to the terminal.
[0010] "Means for displaying and making the generated program code available to a user" refers to an interface and associated software for displaying the generated program code on a terminal and converting that code into a form that can be executed by the user.
[0011] "Means for analyzing user requirements using natural language processing technology" refers to a software module that uses natural language processing technology to analyze user requirements entered in natural language, understand their meaning, and convert them into appropriate technical requirements.
[0012] The "means for generating program code based on analyzed requirements" refers to an algorithm and associated software modules for automatically generating specific program code according to analyzed requirements. [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] The present invention relates to a system that enables a user to easily generate and use a program without having programming knowledge. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be specifically described below in detail with reference to the accompanying drawings.
[0035] First, the user uses a terminal to input their requirements for program specifications and functions in natural language. For example, they might request, "I want a program that multiplies two numbers." This request is analyzed using natural language processing technology and converted into an appropriate technical requirement. The terminal then sends the results of this analysis to the server.
[0036] The AI module located on the server automatically generates program code based on the received request. This program code satisfies the user's request, such as code containing a function to multiply two numbers.
[0037] The generated program code is sent back from the server to the terminal and displayed on the terminal to the user. The user can check the displayed program code and execute it by entering specific values. This system allows users to easily obtain and use programs that meet their requirements, even if they do not have specialized programming knowledge.
[0038] As a concrete example, consider the case where a user requests, "I want a program to multiply two numbers." First, the device sends this request to the server. The AI module on the server analyzes it and generates an appropriate multiplication program. The generated program is sent back to the device, where the user receives and runs it. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0039] The system of the present invention converts user requirements into program code quickly and accurately and provides the results to the user, thereby significantly reducing the effort and cost associated with conventional program creation. Furthermore, since it does not require specialized knowledge and can be operated efficiently, it lowers the barrier to program creation.
[0040] The processing flow will be explained below.
[0041] Step 1:
[0042] A user uses a terminal to input a request for program specifications and functions in natural language. For example, a user might input a request such as "I want a program that multiplies two numbers."
[0043] Step 2:
[0044] The terminal receives the user's request and sends it to the server, where it is formatted into an appropriate format.
[0045] Step 3:
[0046] The server analyzes the received request using natural language processing technology, which converts the user's request into technical specifications.
[0047] Step 4:
[0048] An AI module on the server generates appropriate program code based on the parsed request, for example, a program code containing a function to perform multiplication.
[0049] Step 5:
[0050] The generated program code is sent back to the terminal from the server, which sends the generated code in an appropriate format.
[0051] Step 6:
[0052] The terminal displays the received program code to the user, who can then confirm the generated program code.
[0053] Step 7:
[0054] The user executes the generated program code on the terminal. Specifically, by inputting two numbers and executing the program, the result is obtained.
[0055] Step 8:
[0056] The terminal will execute the program code based on the numbers you enter and display the result. For example, if you enter 6 and 7, the terminal will display 42 as the result.
[0057] Step 9:
[0058] The user can check the displayed results and perform further operations or inputs as necessary. Through this series of processes, the user can easily use the program based on their request.
[0059] Example 1
[0060] 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."
[0061] The traditional program creation process required specialized programming knowledge, making it difficult for many users to use, and was therefore only available to a select few experts. Furthermore, program creation was time-consuming and costly, placing a heavy burden on non-experts. Furthermore, even when requirements were entered in natural language, there were limited means to properly analyze them and convert them into actual program code.
[0062] 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.
[0063] In this invention, the server includes a means for receiving a user's request in natural language, a means for transmitting the request to the server, a server including an artificial intelligence module that generates program code based on the request, a means for returning the generated program code to a terminal, and a means for displaying the generated program code to the user and making it available. This allows users to easily obtain and use programs that meet their requirements, even without specialized programming knowledge. Furthermore, the time and cost required for program generation can be significantly reduced, making it easy for even non-experts to use. Furthermore, by providing a means for accurately analyzing natural language requests and converting them into appropriate program code, programs that meet user requirements can be efficiently generated.
[0064] "Means for receiving user requests in natural language" refers to a device or method that allows a user to input program-related requests written in a language that humans use on a daily basis and converts the input into a data format that the system can understand.
[0065] The "means for sending the request to the server" refers to a device or method for transferring data over the Internet or a network to a server for processing the user's request.
[0066] A "server including an artificial intelligence module that generates program code based on the request" is a server equipped with artificial intelligence that analyzes the user's request received and automatically creates appropriate program code.
[0067] The "means for returning the generated program code to the terminal" refers to a device or method for returning the generated program code to the user's terminal again.
[0068] "Means for displaying and making the generated program code available to the user" refers to a device or method that displays the generated program code in an easily viewable manner on the user's terminal and allows the user to execute or modify the code.
[0069] "Natural language processing technology" is a technology that enables computers to understand and process the language that humans use on a daily basis.
[0070] A "calculation program" is a program for performing numerical processing and calculations based on specific numbers and data.
[0071] MODE FOR CARRYING OUT THE INVENTION
[0072] Overall system overview
[0073] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. This system includes a process that receives user requests in natural language, converts them into appropriate program code, and provides the code to the user.
[0074] User request input
[0075] A user uses a terminal to input program specifications and functional requirements in natural language. This request is made simply using a keyboard or touch screen. For example, a request might be "I want a program that multiplies two numbers."
[0076] Natural language analysis and transmission
[0077] The device receives the user's request and analyzes it using natural language processing technology. NLP technology such as "Google (registered trademark) Cloud Natural Language API" is used for this analysis. The analyzed results are converted into technical requests and sent to the server using the HTTPS protocol. Security is ensured by encrypting the data during this process.
[0078] Program Generation
[0079] The server is configured to host a generative AI model (e.g., OpenAI® GPT-3®). The generative AI model automatically generates program code based on the received technical requirements. The generated program code satisfies the user's requirements and includes, for example, a function to multiply two numbers. The generative AI model is configured to generate code in an appropriate programming language, such as Python or JavaScript®.
[0080] Returning and Viewing Programs
[0081] The generated program code is sent back from the server to the terminal and displayed to the user. The user can check the code displayed on the terminal screen and execute it by entering specific numbers as needed. For example, if the user enters "6" and "7", the program will return the result "42".
[0082] Specific examples
[0083] Let us consider a specific example where a user requests "I want a program that multiplies two numbers." First, the user inputs this request in natural language using a device. Next, the device analyzes the request using natural language processing technology and sends the analysis results to the server. A generative AI model on the server generates appropriate program code based on the analysis results and sends that code back to the device. Finally, the user checks the generated program code on the device, enters numbers, and runs it. This allows users to easily use programs without specialized knowledge.
[0084] Prompt Sentence Examples
[0085] An example prompt for a generative AI model might be something like:
[0086] "Generate a Python program to multiply two numbers. Follow this format:
[0087] def multiply(x, y):
[0088] return [multiplication result]"
[0089] The above is a specific embodiment for carrying out the present invention. This system allows users to easily obtain and use programs, significantly reducing the effort and cost associated with conventional program creation.
[0090] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0091] Step 1:
[0092] Users input their requirements for program specifications and functions into a terminal in natural language, for example, "I want a program that multiplies two numbers." This input is done using a keyboard or touch screen.
[0093] Step 2:
[0094] The device analyzes the user's request using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to convert a request such as "I want a multiplication program" into a technical request (for example, "Create a program to multiply two numbers"). This analysis is completed within a few seconds, and the analysis result is generated.
[0095] Step 3:
[0096] The terminal sends the parsed technical request to the server. The transmission is carried out via the HTTPS protocol and security is ensured by data encryption. The input is the parsed technical request and the output is the data sent to the server.
[0097] Step 4:
[0098] The server uses a generative AI model (e.g., OpenAI GPT-3) to automatically generate program code based on the received technical requirements. The generative AI model understands the technical requirements and creates program code that includes, for example, a function to multiply two numbers in Python. For data processing, the input technical requirements are passed to the AI model, which then generates code. The output is the generated program code.
[0099] Step 5:
[0100] The server returns the generated program code to the terminal. This return is also done using the HTTPS protocol. The input is the generated program code, and the output is the data returned to the terminal.
[0101] Step 6:
[0102] The terminal displays the received program code to the user. The user checks this program code and executes the program by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. The input is the program code returned to the terminal and the numbers entered by the user, and the output is the execution result displayed.
[0103] The above is the specific processing flow of the program for this system.
[0104] (Application example 1)
[0105] 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."
[0106] In the past, users needed specialized knowledge to create programs, which required high learning costs. Furthermore, when searching for specific products or placing customized orders on online shopping sites, it was difficult to quickly generate appropriate programs, making them difficult for users to operate easily. This resulted in a lack of user-friendly search and customization functions.
[0107] 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.
[0108] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an artificial intelligence module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for automatically generating a program for product search and customized ordering, means for searching for products based on the generated program code, and means for displaying search results to the user and allowing them to purchase directly. This enables users to search for products and place customized orders in natural language without specialized programming knowledge.
[0109] The "means for receiving a user's request in natural language" is an interface for analyzing a request made by a user in natural language and inputting the analysis result into the system.
[0110] The "means for transmitting the request to the server" refers to a communication means for transferring the request data received from the user to the server.
[0111] A "server including an artificial intelligence module for generating program code" is a server equipped with artificial intelligence (AI) that automatically generates program code based on user requests.
[0112] The "means for returning the generated program code to the terminal" refers to a communication means for transmitting the program code generated by the server to the user's terminal.
[0113] "Means for displaying the generated program code to the user and making it available" refers to means for displaying the generated program code on the user's terminal and enabling the user to operate or execute the program code.
[0114] The "means for automatically generating a program for product search and customized ordering" is a means for generating a program for automatically performing a product search and customized ordering based on a request from a user in natural language.
[0115] The "means for searching for a product based on the generated program code" refers to a means for searching for a specific product from a database using the generated program code.
[0116] The "means for displaying search results to the user and enabling immediate purchase" refers to a means for displaying searched product information on the user's terminal and enabling the user to immediately purchase the product.
[0117] "Means for analyzing using natural language processing technology" refers to means for analyzing a user's request in natural language and using technology to understand the intent and content of that request.
[0118] The "program code" "search program for product search and customized ordering" is a program for searching for products based on user requests and customizing order details.
[0119] The present invention relates to a system that enables users to easily search for products and place customized orders, particularly on online shopping sites, without having to have programming knowledge. Specific embodiments for carrying out the present invention will be described below.
[0120] First, the user uses a smartphone application to input product specifications and requirements in natural language. For example, "I want a black T-shirt in size L." This request is analyzed using natural language processing (NLP) technology and converted into appropriate technical requirements.
[0121] For analysis, a request is sent from the terminal to the server, where it is analyzed by an NLP model (e.g., BERT) located on the server. The analyzed request is converted into a technical request (e.g., category "T-shirt", color "black", size "L").
[0122] Next, the analyzed data is passed to a generative AI model (e.g., GPT-4 (registered trademark)) on the server. Based on the analyzed data, the generative AI model automatically generates program code for product searches and customized orders. The generated program code is expressed in the form of, for example, an SQL query.
[0123] The generated program code is sent back from the server to the terminal. On the terminal, this code is displayed in a user interface and is provided in an immediately executable state. Based on the generated code, a product search is performed using database software (e.g., MySQL (registered trademark)), and the results are displayed to the user. The user can check the displayed product information and proceed with the purchase procedure if necessary.
[0124] Examples:
[0125] User Input:
[0126] "I want a black T-shirt, size L."
[0127] Generates the prompt statement:
[0128] "Write a program to search for and display black T-shirts in size L."
[0129] Example of generated code for database lookup:
[0130] SQL query format: SELECT FROM products WHERE category='T-shirt' AND color='black' AND size='L';
[0131] Output:
[0132] The search results will show a list of black T-shirts in size L, and the user can proceed to purchase them.
[0133] This system allows users to easily search for and purchase products that meet their needs without any specialized programming knowledge, thereby improving the user-friendliness and convenience of online shopping sites.
[0134] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0135] Step 1:
[0136] The user inputs product specifications and requests into the terminal in natural language. For example, "I want a black T-shirt in size L." This input data is prepared for the next step.
[0137] Step 2:
[0138] The terminal sends the user's request to the server. HTTP or WebSocket is typically used as the communication protocol. At this stage, the input data (user request) is transferred to the server.
[0139] Step 3:
[0140] The server analyzes the received request using natural language processing (NLP) technology. Specifically, it analyzes the input data using an NLP model (e.g., BERT) and converts it into technical requirements (e.g., category "T-shirt", color "black", size "L"). This converted data becomes the input data for the next step.
[0141] Step 4:
[0142] The server uses a generative AI model (e.g., GPT-4) to automatically generate program code based on technical requirements. The generated code is in the form of an SQL query for product search and customized ordering. This SQL query serves as input data for the next step.
[0143] Step 5:
[0144] The server returns the generated program code (e.g., an SQL query) to the terminal, again using HTTP or WebSocket as the communication protocol. The generated code is displayed on the terminal.
[0145] Step 6:
[0146] The terminal executes the received program code and searches the database for the corresponding product. The database software used is MySQL. Specifically, an SQL query is executed to extract the corresponding product data from the database. This extracted product data becomes the input data for the next step.
[0147] Step 7:
[0148] The terminal displays the search results to the user. The extracted product data is displayed in a formatted form so that the user can check the results. Specifically, the product details screen displays the product name, price, stock status, etc.
[0149] Step 8:
[0150] If a user decides to purchase after viewing the search results, they can proceed with the purchase process by pressing the purchase button on their device.
[0151] Through this series of processes, it is possible to provide a system that allows users to search for products and place customized orders through requests in natural language, without the need for specialized programming knowledge.
[0152] 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.
[0153] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system improves the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. The following describes in detail the embodiments of the present invention.
[0154] First, the user uses a terminal to input their requirements for the program's specifications and functions in natural language. At this time, an emotion engine is activated that analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user inputs "I want a program that multiplies two numbers," and the user is feeling relaxed, an explanation will be displayed in simple language; if the user is feeling impatient, the process will proceed quickly.
[0155] The device sends the user's request and emotional data to the server, where the request is formatted appropriately. The server then analyzes the received request using natural language processing technology and generates program code based on the analysis results. The content and difficulty of the generated program are adjusted according to the user's emotional state.
[0156] The generated program code is sent back from the server to the device and displayed to the user. The emotion engine continuously monitors the user's emotions and adjusts the program's explanation and usage instructions accordingly. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0157] As a concrete example, consider the case where a user requests a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program, along with detailed explanations and additional learning resources. On the other hand, if the user is anxious, a program in a format that can be quickly executed will be displayed. This system allows users to quickly and accurately obtain and use the necessary program while receiving assistance tailored to their emotional state.
[0158] The system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it lowers the barrier to program creation.
[0159] The processing flow will be explained below.
[0160] Step 1:
[0161] A user uses a terminal to input requests for program specifications and functions in natural language. For example, a user might request, "I want a program that multiplies two numbers."
[0162] Step 2:
[0163] The device's emotion engine recognizes the user's emotions from their facial expressions and voice, determining, for example, whether they are relaxed or anxious.
[0164] Step 3:
[0165] The device transmits the user's request and the emotion data it recognizes to the server, where the request is formatted appropriately.
[0166] Step 4:
[0167] An AI module on the server analyzes the received request using natural language processing technology and converts it into technical specifications. For example, it may be analyzed as a request to "create a multiplication program."
[0168] Step 5:
[0169] The server's AI module generates program code based on the analysis results, and adjusts the program's content and explanations according to the user's emotional state.
[0170] Step 6:
[0171] The generated program code is sent back to the terminal from the server, which sends the code in the appropriate format.
[0172] Step 7:
[0173] The terminal displays the received program code to the user, and the emotion engine continues to monitor the user's emotions and provide appropriate feedback.
[0174] Step 8:
[0175] The user checks the generated program code on the terminal and executes it by entering specific numbers, for example, 6 and 7.
[0176] Step 9:
[0177] The terminal runs a program based on the numbers you enter and displays the result, for example, 42.
[0178] Step 10:
[0179] The user can review the displayed results and take further action or input as needed, and the emotion engine provides additional feedback and assistance depending on the user's emotional state.
[0180] This series of processes allows the user to receive appropriate support tailored to their emotional state, while quickly and accurately generating and using the necessary programs.
[0181] Example 2
[0182] 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."
[0183] Conventional program generation systems are difficult to operate unless the user has programming knowledge, and they are unable to provide support tailored to the emotional state of each individual user. As a result, the increased effort and stress involved in creating programs has become a problem.
[0184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0185] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an AI module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for recognizing the user's emotional state, and means for adjusting processing in accordance with the recognized emotional state. This allows users to easily generate and use programs without specialized knowledge and receive support in accordance with their emotional state.
[0186] The "means for receiving a user's request in natural language" refers to a device or software that has the function of analyzing and acquiring a request in natural language input by a user.
[0187] The "means for sending a request to a server" refers to a device or software that has the function of sending a request entered by a user to a server via the Internet or other communication means.
[0188] A "server including an AI module for generating program code" is a server that has the function of automatically generating appropriate program code based on received requests using AI technology.
[0189] The "means for returning the generated program code to the terminal" refers to a device or software that has the function of transmitting the program code generated by the server to the user's terminal via the network.
[0190] "Means for displaying and making available the generated program code to the user" means a device or software that visually displays the received program code on a terminal and allows the user to operate and execute the program code.
[0191] "Means for recognizing the user's emotional state" refers to a device or software that has the function of analyzing and recognizing the user's emotional state from their facial expressions and voice.
[0192] The "means for adjusting processing in accordance with the recognized emotional state" refers to a device or software that has the function of dynamically adjusting the display content, processing speed, etc. based on the recognized emotional state of the user.
[0193] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system can improve the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. Specific embodiments of this system are described in detail below.
[0194] First, a user uses a device (e.g., a PC or smartphone) to input program specifications and function requirements in natural language. The device is equipped with a camera and microphone, which captures the user's facial expressions and voice. This data is then analyzed by an emotion engine (e.g., FaceAPI for facial expression recognition and Google Cloud Speech-to-Text for voice recognition) to recognize the user's emotional state in real time.
[0195] Next, the device sends the user's input request (e.g., "I want a program to multiply two numbers") and emotional data (relaxed, anxious, etc.) to the server. This data is formatted in JSON format and sent to the server via the Internet or other communication means.
[0196] The server analyzes the received JSON-formatted request and emotional data. It uses natural language processing (NLP) to analyze the request and automatically generate appropriate program code. This is done using a generative AI model (e.g., OpenAI's GPT-3). It also dynamically adjusts the content and difficulty of the generated program based on the recognized emotional state of the user. Specifically, it provides a program with detailed comments to a relaxed user, and concise, quickly executable code to a rushed user.
[0197] The generated program code is sent back from the server to the device. The device then displays the received program code to the user. Furthermore, the device's built-in emotion engine continuously monitors the user's emotions and can provide feedback or additional explanations according to the situation. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42.
[0198] As a concrete example, consider a user requesting a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program with detailed instructions and additional learning resources (e.g., links to documentation). On the other hand, if the user is impatient, the program will be displayed in a concise, quickly executable form.
[0199] Examples of prompts include:
[0200] "Generate a program that multiplies two numbers. The user is relaxed."
[0201] or
[0202] "Generate a program that multiplies two numbers. The user is in a hurry."
[0203] As described above, the system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it can lower the barrier to program creation.
[0204] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0205] Step 1:
[0206] The user uses the terminal to enter a request in natural language.
[0207] Input: User request (e.g., "I want a program to multiply two numbers")
[0208] Specific actions: The user enters a request in natural language into an input field on the terminal.
[0209] Output: Request data captured by the device
[0210] Step 2:
[0211] The device captures the user's facial expression and voice data and sends it to the emotion engine.
[0212] Input: User's facial expressions and voice
[0213] Specific operation: The device's camera captures facial expressions and microphone captures voice. The emotion engine receives and analyzes this data.
[0214] Output: User's emotional state (e.g., relaxed, anxious)
[0215] Step 3:
[0216] The terminal transmits the request data and the emotional state information to the server.
[0217] Input: Request data and emotional state information
[0218] Specific operation: The device formats the request data and emotional state information into JSON format and sends it to the server via the network.
[0219] Output: JSON data received by the server
[0220] Step 4:
[0221] The request data received by the server is analyzed using natural language processing technology.
[0222] Input: Request data in JSON format
[0223] Specific operation: The request data is analyzed by a natural language processing engine (e.g., a generative AI model) on the server, and program code specifications are extracted according to the demand.
[0224] Output: Program specification based on parsed requirements
[0225] Step 5:
[0226] The server generates program code based on the analysis results and emotional state.
[0227] Input: Program specifications and user emotional state
[0228] How it works: The server's AI module generates program code based on the user's emotional state and the user's specifications. For a relaxed user, detailed comments are generated, while for a panicked user, concise code is generated.
[0229] Output: Generated program code
[0230] Step 6:
[0231] The server formats the generated program code into JSON format and returns it to the terminal.
[0232] Input: Generated program code
[0233] Specific operation: The server converts the program code into JSON format and sends it to the terminal via the network.
[0234] Output: Program code in JSON format received by the terminal
[0235] Step 7:
[0236] The terminal displays the received program code to the user.
[0237] Input: Program code in JSON format
[0238] What it does: The terminal displays the program code in a user-friendly format.
[0239] Output: The program code displayed to the user
[0240] Step 8:
[0241] The user inputs numbers using program code and gets a result.
[0242] Input: The numbers you enter (e.g. 6 and 7)
[0243] Specific operation: The user inputs numbers into the program code on the terminal and executes the program.
[0244] Output: Program execution result (e.g. 42)
[0245] As described above, the specific operations performed at each step, as well as the input and output of data, can be explained in detail. This clarifies the processing flow of the entire system and makes it easier to understand how program code is generated in response to user requests.
[0246] (Application example 2)
[0247] 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."
[0248] Conventional program generation systems often make it difficult for users without programming knowledge to generate programs, and often fail to provide appropriate support that takes into account the user's emotional state. This results in a poor user experience, and it is difficult to provide appropriate interfaces and explanations, especially for users who are anxious or relaxed. Furthermore, in content distribution services, it is difficult to appropriately recommend content that users want to watch, making it difficult to improve user satisfaction.
[0249] 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.
[0250] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including a generative AI model for generating program code based on the request, means for recognizing emotions by analyzing the user's facial expressions and voice, means for adjusting the generated program code according to the user's emotional state, means for returning the generated program code to the terminal, and means for displaying the generated program code to the user and making it available for use, thereby enabling appropriate program generation and content recommendation according to the user's emotional state.
[0251] A "user" is an entity that uses the system to generate programs and receive content recommendations.
[0252] "Natural language" is a language that humans use on a daily basis, not program code.
[0253] A "server" is a central computer system that receives and processes requests from users.
[0254] A "generative AI model" refers to a collection of algorithms that analyze user requests and automatically generate program code.
[0255] "Facial expressions" are physical facial movements and placements used to determine the emotions expressed by a user.
[0256] "Audio" or "voice" refers to the spoken voice of the user and is used as part of sentiment analysis.
[0257] "Emotion recognition" means determining the user's emotional state at that time from their facial expression and voice.
[0258] "Program code" means a set of instructions in a format that a computer can understand and execute.
[0259] A "terminal" is a device (such as a smartphone or computer) that is directly operated by a user.
[0260] "Adjusting" refers to processing the generated program code and related information appropriately to suit the user's emotional state.
[0261] "Display" means visually outputting information on the screen of a terminal.
[0262] "Available" means that the user can actually operate or execute the generated program code.
[0263] The present invention is a system that allows a user to input a request in natural language, recognizes emotions from facial expressions and voice, and generates appropriate programs and recommends content according to the user's state. This system is realized by an application installed on a device such as a smartphone, smart glasses, a head-mounted display, or a robot. The system configuration and operation are described in detail below.
[0264] Components
[0265] 1. Terminal
[0266] Hardware: Devices such as smartphones, smart glasses, head-mounted displays, or robots.
[0267] Software: Installed OpenCV, transformers NLP models, and emotion recognition software.
[0268] 2. Server
[0269] Generative AI models: Algorithms that analyze user requests in natural language and generate program code (e.g., transformers).
[0270] Emotion recognition engine: Recognizes the user's emotional state by analyzing their facial expressions and voice.
[0271] Operation flow
[0272] 1. User request input
[0273] A user uses a terminal to input a request for content to be viewed or a program to be executed in natural language.
[0274] For example, a user may enter, "I want to watch a relaxing documentary."
[0275] 2. Emotional Recognition
[0276] The device's camera and microphone are used to capture the user's facial expressions and voice, which are then analyzed by an emotion recognition engine.
[0277] As a result of the analysis, the emotional state of the user, such as whether they are relaxed or anxious, is determined.
[0278] 3. Program Creation and Recommendation
[0279] The server uses a generative AI model to recommend appropriate program code and content based on the user's request and emotional state.
[0280] For example, in response to a request to "watch a documentary that will help me relax," documentary videos that are suitable for a relaxed state are recommended.
[0281] 4. Display and Use of Results
[0282] The generated program code and content recommendations are sent back to the terminal and displayed to the user.
[0283] The user checks the displayed information and starts viewing or playing as needed.
[0284] Specific examples
[0285] User Request: "I want to watch an uplifting music video."
[0286] Example prompt sentence:
[0287] User wants: Wants to watch an uplifting music video. User is feeling: Feeling anxious. Recommend an appropriate video.
[0288] System response: Recognizes when the user is in a state of agitation and immediately recommends energetic music videos.
[0289] A feature of the present invention is that appropriate content is recommended according to the user's emotional state, even if the user does not have any special programming knowledge, thereby improving the user experience and satisfying requests efficiently and quickly.
[0290] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0291] Step 1:
[0292] User request input
[0293] The user uses the terminal to input a request for the content they want to view or the program they want to run in natural language. In this case, the user enters text such as "I want to watch a relaxing documentary" into the input field. This text information is entered into the terminal, and the data is passed to the next processing step.
[0294] Step 2:
[0295] Emotion recognition
[0296] The device's camera and microphone are used to simultaneously capture the user's facial expressions and voice. The captured video and audio data are input into an emotion recognition engine. The emotion recognition engine (e.g., EmotionRecognizer) processes this data and determines the user's emotional state (relaxed, anxious, etc.). This emotional state information is sent to a server and input into a generative AI model.
[0297] Step 3:
[0298] Program Generation and Recommendations
[0299] The generative AI model installed on the server receives the user's request text (input in step 1) and emotional state (output in step 2) as input. The generative AI model analyzes this data using natural language processing (NLP) technology and recommends appropriate program code and content. For example, if the request text is "relaxing documentaries" and the emotional state is determined to be "relaxing," a list of documentary videos that can be enjoyed in a relaxed state will be generated. This list becomes the output of program generation and recommendations.
[0300] Step 4:
[0301] Displaying and Using the Results
[0302] The server returns the generated program code and a list of content recommendations to the device. The returned data is input into the device and visually displayed to the user. The user selects the documentary they want to watch from the displayed list and presses the play button to begin watching the video. All of this is done on the device, allowing users to easily consume content.
[0303] 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.
[0304] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0305] 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.
[0306] [Second embodiment]
[0307] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0308] 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.
[0309] 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).
[0310] 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.
[0311] 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.
[0312] 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).
[0313] 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. 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.
[0314] 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.
[0315] 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.
[0316] 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.
[0317] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0318] 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."
[0319] The present invention relates to a system that enables a user to easily generate and use a program without having programming knowledge. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be specifically described below in detail with reference to the accompanying drawings.
[0320] First, the user uses a terminal to input their requirements for program specifications and functions in natural language. For example, they might request, "I want a program that multiplies two numbers." This request is analyzed using natural language processing technology and converted into an appropriate technical requirement. The terminal then sends the results of this analysis to the server.
[0321] The AI module located on the server automatically generates program code based on the received request. This program code satisfies the user's request, such as code containing a function to multiply two numbers.
[0322] The generated program code is sent back from the server to the terminal and displayed on the terminal to the user. The user can check the displayed program code and execute it by entering specific values. This system allows users to easily obtain and use programs that meet their requirements, even if they do not have specialized programming knowledge.
[0323] As a concrete example, consider the case where a user requests, "I want a program to multiply two numbers." First, the device sends this request to the server. The AI module on the server analyzes it and generates an appropriate multiplication program. The generated program is sent back to the device, where the user receives and runs it. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0324] The system of the present invention converts user requirements into program code quickly and accurately and provides the results to the user, thereby significantly reducing the effort and cost associated with conventional program creation. Furthermore, since it does not require specialized knowledge and can be operated efficiently, it lowers the barrier to program creation.
[0325] The processing flow will be explained below.
[0326] Step 1:
[0327] A user uses a terminal to input a request for program specifications and functions in natural language. For example, a user might input a request such as "I want a program that multiplies two numbers."
[0328] Step 2:
[0329] The terminal receives the user's request and sends it to the server, where it is formatted into an appropriate format.
[0330] Step 3:
[0331] The server analyzes the received request using natural language processing technology, which converts the user's request into technical specifications.
[0332] Step 4:
[0333] An AI module on the server generates appropriate program code based on the parsed request, for example, a program code containing a function to perform multiplication.
[0334] Step 5:
[0335] The generated program code is sent back to the terminal from the server, which sends the generated code in an appropriate format.
[0336] Step 6:
[0337] The terminal displays the received program code to the user, who can then confirm the generated program code.
[0338] Step 7:
[0339] The user executes the generated program code on the terminal. Specifically, by inputting two numbers and executing the program, the result is obtained.
[0340] Step 8:
[0341] The terminal will execute the program code based on the numbers you enter and display the result. For example, if you enter 6 and 7, the terminal will display 42 as the result.
[0342] Step 9:
[0343] The user can check the displayed results and perform further operations or inputs as necessary. Through this series of processes, the user can easily use the program based on their request.
[0344] Example 1
[0345] 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."
[0346] The traditional program creation process required specialized programming knowledge, making it difficult for many users to use, and was therefore only available to a select few experts. Furthermore, program creation was time-consuming and costly, placing a heavy burden on non-experts. Furthermore, even when requirements were entered in natural language, there were limited means to properly analyze them and convert them into actual program code.
[0347] 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.
[0348] In this invention, the server includes a means for receiving a user's request in natural language, a means for transmitting the request to the server, a server including an artificial intelligence module that generates program code based on the request, a means for returning the generated program code to a terminal, and a means for displaying the generated program code to the user and making it available. This allows users to easily obtain and use programs that meet their requirements, even without specialized programming knowledge. Furthermore, the time and cost required for program generation can be significantly reduced, making it easy for even non-experts to use. Furthermore, by providing a means for accurately analyzing natural language requests and converting them into appropriate program code, programs that meet user requirements can be efficiently generated.
[0349] "Means for receiving user requests in natural language" refers to a device or method that allows a user to input program-related requests written in a language that humans use on a daily basis and converts the input into a data format that the system can understand.
[0350] The "means for sending the request to the server" refers to a device or method for transferring data over the Internet or a network to a server for processing the user's request.
[0351] A "server including an artificial intelligence module that generates program code based on the request" is a server equipped with artificial intelligence that analyzes the user's request received and automatically creates appropriate program code.
[0352] The "means for returning the generated program code to the terminal" refers to a device or method for returning the generated program code to the user's terminal again.
[0353] "Means for displaying and making the generated program code available to the user" refers to a device or method that displays the generated program code in an easily viewable manner on the user's terminal and allows the user to execute or modify the code.
[0354] "Natural language processing technology" is a technology that enables computers to understand and process the language that humans use on a daily basis.
[0355] A "calculation program" is a program for performing numerical processing and calculations based on specific numbers and data.
[0356] MODE FOR CARRYING OUT THE INVENTION
[0357] Overall system overview
[0358] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. This system includes a process that receives user requests in natural language, converts them into appropriate program code, and provides the code to the user.
[0359] User request input
[0360] A user uses a terminal to input program specifications and functional requirements in natural language. This request is made simply using a keyboard or touch screen. For example, a request might be "I want a program that multiplies two numbers."
[0361] Natural language analysis and transmission
[0362] The device receives the user's request and analyzes it using natural language processing technology. NLP technologies such as "Google Cloud Natural Language API" are used for this analysis. The analyzed results are converted into technical requests and sent to the server using the HTTPS protocol. Security is ensured by encrypting the data during this process.
[0363] Program Generation
[0364] The server hosts a generative AI model (e.g., "OpenAI GPT-3"). This generative AI model automatically generates program code based on the received technical requirements. The generated program code satisfies the user's requirements, and may include, for example, a function to multiply two numbers. The generative AI model is configured to generate code in an appropriate programming language, such as Python or JavaScript.
[0365] Returning and Viewing Programs
[0366] The generated program code is sent back from the server to the terminal and displayed to the user. The user can check the code displayed on the terminal screen and execute it by entering specific numbers as needed. For example, if the user enters "6" and "7", the program will return the result "42".
[0367] Specific examples
[0368] Let us consider a specific example where a user requests "I want a program that multiplies two numbers." First, the user inputs this request in natural language using a device. Next, the device analyzes the request using natural language processing technology and sends the analysis results to the server. A generative AI model on the server generates appropriate program code based on the analysis results and sends that code back to the device. Finally, the user checks the generated program code on the device, enters numbers, and runs it. This allows users to easily use programs without specialized knowledge.
[0369] Prompt Sentence Examples
[0370] An example prompt for a generative AI model might be something like:
[0371] "Generate a Python program to multiply two numbers. Follow this format:
[0372] def multiply(x, y):
[0373] return [multiplication result]"
[0374] The above is a specific embodiment for carrying out the present invention. This system allows users to easily obtain and use programs, significantly reducing the effort and cost associated with conventional program creation.
[0375] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0376] Step 1:
[0377] Users input their requirements for program specifications and functions into a terminal in natural language, for example, "I want a program that multiplies two numbers." This input is done using a keyboard or touch screen.
[0378] Step 2:
[0379] The device analyzes the user's request using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to convert a request such as "I want a multiplication program" into a technical request (for example, "Create a program to multiply two numbers"). This analysis is completed within a few seconds, and the analysis result is generated.
[0380] Step 3:
[0381] The terminal sends the parsed technical request to the server. The transmission is carried out via the HTTPS protocol and security is ensured by data encryption. The input is the parsed technical request and the output is the data sent to the server.
[0382] Step 4:
[0383] The server uses a generative AI model (e.g., OpenAI GPT-3) to automatically generate program code based on the received technical requirements. The generative AI model understands the technical requirements and creates program code that includes, for example, a function to multiply two numbers in Python. For data processing, the input technical requirements are passed to the AI model, which then generates code. The output is the generated program code.
[0384] Step 5:
[0385] The server returns the generated program code to the terminal. This return is also done using the HTTPS protocol. The input is the generated program code, and the output is the data returned to the terminal.
[0386] Step 6:
[0387] The terminal displays the received program code to the user. The user checks this program code and executes the program by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. The input is the program code returned to the terminal and the numbers entered by the user, and the output is the execution result displayed.
[0388] The above is the specific processing flow of the program for this system.
[0389] (Application example 1)
[0390] 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."
[0391] In the past, users needed specialized knowledge to create programs, which required high learning costs. Furthermore, when searching for specific products or placing customized orders on online shopping sites, it was difficult to quickly generate appropriate programs, making them difficult for users to operate easily. This resulted in a lack of user-friendly search and customization functions.
[0392] 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.
[0393] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an artificial intelligence module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for automatically generating a program for product search and customized ordering, means for searching for products based on the generated program code, and means for displaying search results to the user and allowing them to purchase directly. This enables users to search for products and place customized orders in natural language without specialized programming knowledge.
[0394] The "means for receiving a user's request in natural language" is an interface for analyzing a request made by a user in natural language and inputting the analysis result into the system.
[0395] The "means for transmitting the request to the server" refers to a communication means for transferring the request data received from the user to the server.
[0396] A "server including an artificial intelligence module for generating program code" is a server equipped with artificial intelligence (AI) that automatically generates program code based on user requests.
[0397] The "means for returning the generated program code to the terminal" refers to a communication means for transmitting the program code generated by the server to the user's terminal.
[0398] "Means for displaying the generated program code to the user and making it available" refers to means for displaying the generated program code on the user's terminal and enabling the user to operate or execute the program code.
[0399] The "means for automatically generating a program for product search and customized ordering" is a means for generating a program for automatically performing a product search and customized ordering based on a request from a user in natural language.
[0400] The "means for searching for a product based on the generated program code" refers to a means for searching for a specific product from a database using the generated program code.
[0401] The "means for displaying search results to the user and enabling immediate purchase" refers to a means for displaying searched product information on the user's terminal and enabling the user to immediately purchase the product.
[0402] "Means for analyzing using natural language processing technology" refers to means for analyzing a user's request in natural language and using technology to understand the intent and content of that request.
[0403] The "program code" "search program for product search and customized ordering" is a program for searching for products based on user requests and customizing order details.
[0404] The present invention relates to a system that enables users to easily search for products and place customized orders, particularly on online shopping sites, without having to have programming knowledge. Specific embodiments for carrying out the present invention will be described below.
[0405] First, the user uses a smartphone application to input product specifications and requirements in natural language. For example, "I want a black T-shirt in size L." This request is analyzed using natural language processing (NLP) technology and converted into appropriate technical requirements.
[0406] For analysis, a request is sent from the terminal to the server, where it is analyzed by an NLP model (e.g., BERT) located on the server. The analyzed request is converted into a technical request (e.g., category "T-shirt", color "black", size "L").
[0407] Next, the analyzed data is passed to a generative AI model (e.g., GPT-4) on the server. The generative AI model automatically generates program code for product searches and customized orders based on the analyzed data. The generated program code is expressed in the form of, for example, an SQL query.
[0408] The generated program code is sent back from the server to the terminal. On the terminal, this code is displayed in the user interface and is provided in an immediately executable state. Based on the generated code, a product search is performed using database software (e.g., MySQL), and the results are displayed to the user. The user can check the displayed product information and proceed with the purchase procedure if necessary.
[0409] Examples:
[0410] User Input:
[0411] "I want a black T-shirt, size L."
[0412] Generates the prompt statement:
[0413] "Write a program to search for and display black T-shirts in size L."
[0414] Example of generated code for database lookup:
[0415] SQL query format: SELECT FROM products WHERE category='T-shirt' AND color='black' AND size='L';
[0416] Output:
[0417] The search results will show a list of black T-shirts in size L, and the user can proceed to purchase them.
[0418] This system allows users to easily search for and purchase products that meet their needs without any specialized programming knowledge, thereby improving the user-friendliness and convenience of online shopping sites.
[0419] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0420] Step 1:
[0421] The user inputs product specifications and requests into the terminal in natural language. For example, "I want a black T-shirt in size L." This input data is prepared for the next step.
[0422] Step 2:
[0423] The terminal sends the user's request to the server. HTTP or WebSocket is typically used as the communication protocol. At this stage, the input data (user request) is transferred to the server.
[0424] Step 3:
[0425] The server analyzes the received request using natural language processing (NLP) technology. Specifically, it analyzes the input data using an NLP model (e.g., BERT) and converts it into technical requirements (e.g., category "T-shirt", color "black", size "L"). This converted data becomes the input data for the next step.
[0426] Step 4:
[0427] The server uses a generative AI model (e.g., GPT-4) to automatically generate program code based on technical requirements. The generated code is in the form of an SQL query for product search and customized ordering. This SQL query serves as input data for the next step.
[0428] Step 5:
[0429] The server returns the generated program code (e.g., an SQL query) to the terminal, again using HTTP or WebSocket as the communication protocol. The generated code is displayed on the terminal.
[0430] Step 6:
[0431] The terminal executes the received program code and searches the database for the corresponding product. The database software used is MySQL. Specifically, an SQL query is executed to extract the corresponding product data from the database. This extracted product data becomes the input data for the next step.
[0432] Step 7:
[0433] The terminal displays the search results to the user. The extracted product data is displayed in a formatted form so that the user can check the results. Specifically, the product details screen displays the product name, price, stock status, etc.
[0434] Step 8:
[0435] If a user decides to purchase after viewing the search results, they can proceed with the purchase process by pressing the purchase button on their device.
[0436] Through this series of processes, it is possible to provide a system that allows users to search for products and place customized orders through requests in natural language, without the need for specialized programming knowledge.
[0437] 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.
[0438] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system improves the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. The following describes in detail the embodiments of the present invention.
[0439] First, the user uses a terminal to input their requirements for the program's specifications and functions in natural language. At this time, an emotion engine is activated that analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user inputs "I want a program that multiplies two numbers," and the user is feeling relaxed, an explanation will be displayed in simple language; if the user is feeling impatient, the process will proceed quickly.
[0440] The device sends the user's request and emotional data to the server, where the request is formatted appropriately. The server then analyzes the received request using natural language processing technology and generates program code based on the analysis results. The content and difficulty of the generated program are adjusted according to the user's emotional state.
[0441] The generated program code is sent back from the server to the device and displayed to the user. The emotion engine continuously monitors the user's emotions and adjusts the program's explanation and usage instructions accordingly. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0442] As a concrete example, consider the case where a user requests a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program, along with detailed explanations and additional learning resources. On the other hand, if the user is anxious, a program in a format that can be quickly executed will be displayed. This system allows users to quickly and accurately obtain and use the necessary program while receiving assistance tailored to their emotional state.
[0443] The system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it lowers the barrier to program creation.
[0444] The processing flow will be explained below.
[0445] Step 1:
[0446] A user uses a terminal to input requests for program specifications and functions in natural language. For example, a user might request, "I want a program that multiplies two numbers."
[0447] Step 2:
[0448] The device's emotion engine recognizes the user's emotions from their facial expressions and voice, determining, for example, whether they are relaxed or anxious.
[0449] Step 3:
[0450] The device transmits the user's request and the emotion data it recognizes to the server, where the request is formatted appropriately.
[0451] Step 4:
[0452] An AI module on the server analyzes the received request using natural language processing technology and converts it into technical specifications. For example, it may be analyzed as a request to "create a multiplication program."
[0453] Step 5:
[0454] The server's AI module generates program code based on the analysis results, and adjusts the program's content and explanations according to the user's emotional state.
[0455] Step 6:
[0456] The generated program code is sent back to the terminal from the server, which sends the code in the appropriate format.
[0457] Step 7:
[0458] The terminal displays the received program code to the user, and the emotion engine continues to monitor the user's emotions and provide appropriate feedback.
[0459] Step 8:
[0460] The user checks the generated program code on the terminal and executes it by entering specific numbers, for example, 6 and 7.
[0461] Step 9:
[0462] The terminal runs a program based on the numbers you enter and displays the result, for example, 42.
[0463] Step 10:
[0464] The user can review the displayed results and take further action or input as needed, and the emotion engine provides additional feedback and assistance depending on the user's emotional state.
[0465] This series of processes allows the user to receive appropriate support tailored to their emotional state, while quickly and accurately generating and using the necessary programs.
[0466] Example 2
[0467] 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."
[0468] Conventional program generation systems are difficult to operate unless the user has programming knowledge, and they are unable to provide support tailored to the emotional state of each individual user. As a result, the increased effort and stress involved in creating programs has become a problem.
[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0470] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an AI module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for recognizing the user's emotional state, and means for adjusting processing in accordance with the recognized emotional state. This allows users to easily generate and use programs without specialized knowledge and receive support in accordance with their emotional state.
[0471] The "means for receiving a user's request in natural language" refers to a device or software that has the function of analyzing and acquiring a request in natural language input by a user.
[0472] The "means for sending a request to a server" refers to a device or software that has the function of sending a request entered by a user to a server via the Internet or other communication means.
[0473] A "server including an AI module for generating program code" is a server that has the function of automatically generating appropriate program code based on received requests using AI technology.
[0474] The "means for returning the generated program code to the terminal" refers to a device or software that has the function of transmitting the program code generated by the server to the user's terminal via the network.
[0475] "Means for displaying and making available the generated program code to the user" means a device or software that visually displays the received program code on a terminal and allows the user to operate and execute the program code.
[0476] "Means for recognizing the user's emotional state" refers to a device or software that has the function of analyzing and recognizing the user's emotional state from their facial expressions and voice.
[0477] The "means for adjusting processing in accordance with the recognized emotional state" refers to a device or software that has the function of dynamically adjusting the display content, processing speed, etc. based on the recognized emotional state of the user.
[0478] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system can improve the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. Specific embodiments of this system are described in detail below.
[0479] First, a user uses a device (e.g., a PC or smartphone) to input program specifications and function requirements in natural language. The device is equipped with a camera and microphone, which captures the user's facial expressions and voice. This data is then analyzed by an emotion engine (e.g., FaceAPI for facial expression recognition and Google Cloud Speech-to-Text for voice recognition) to recognize the user's emotional state in real time.
[0480] Next, the device sends the user's input request (e.g., "I want a program to multiply two numbers") and emotional data (relaxed, anxious, etc.) to the server. This data is formatted in JSON format and sent to the server via the Internet or other communication means.
[0481] The server analyzes the received JSON-formatted request and emotional data. It uses natural language processing (NLP) to analyze the request and automatically generate appropriate program code. This is done using a generative AI model (e.g., OpenAI's GPT-3). It also dynamically adjusts the content and difficulty of the generated program based on the recognized emotional state of the user. Specifically, it provides a program with detailed comments to a relaxed user, and concise, quickly executable code to a rushed user.
[0482] The generated program code is sent back from the server to the device. The device then displays the received program code to the user. Furthermore, the device's built-in emotion engine continuously monitors the user's emotions and can provide feedback or additional explanations according to the situation. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42.
[0483] As a concrete example, consider a user requesting a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program with detailed instructions and additional learning resources (e.g., links to documentation). On the other hand, if the user is impatient, the program will be displayed in a concise, quickly executable form.
[0484] Examples of prompts include:
[0485] "Generate a program that multiplies two numbers. The user is relaxed."
[0486] or
[0487] "Generate a program that multiplies two numbers. The user is in a hurry."
[0488] As described above, the system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it can lower the barrier to program creation.
[0489] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0490] Step 1:
[0491] The user uses the terminal to enter a request in natural language.
[0492] Input: User request (e.g., "I want a program to multiply two numbers")
[0493] Specific actions: The user enters a request in natural language into an input field on the terminal.
[0494] Output: Request data captured by the device
[0495] Step 2:
[0496] The device captures the user's facial expression and voice data and sends it to the emotion engine.
[0497] Input: User's facial expressions and voice
[0498] Specific operation: The device's camera captures facial expressions and microphone captures voice. The emotion engine receives and analyzes this data.
[0499] Output: User's emotional state (e.g., relaxed, anxious)
[0500] Step 3:
[0501] The terminal transmits the request data and the emotional state information to the server.
[0502] Input: Request data and emotional state information
[0503] Specific operation: The device formats the request data and emotional state information into JSON format and sends it to the server via the network.
[0504] Output: JSON data received by the server
[0505] Step 4:
[0506] The request data received by the server is analyzed using natural language processing technology.
[0507] Input: Request data in JSON format
[0508] Specific operation: The request data is analyzed by a natural language processing engine (e.g., a generative AI model) on the server, and program code specifications are extracted according to the demand.
[0509] Output: Program specification based on parsed requirements
[0510] Step 5:
[0511] The server generates program code based on the analysis results and emotional state.
[0512] Input: Program specifications and user emotional state
[0513] How it works: The server's AI module generates program code based on the user's emotional state and the user's specifications. For a relaxed user, detailed comments are generated, while for a panicked user, concise code is generated.
[0514] Output: Generated program code
[0515] Step 6:
[0516] The server formats the generated program code into JSON format and returns it to the terminal.
[0517] Input: Generated program code
[0518] Specific operation: The server converts the program code into JSON format and sends it to the terminal via the network.
[0519] Output: Program code in JSON format received by the terminal
[0520] Step 7:
[0521] The terminal displays the received program code to the user.
[0522] Input: Program code in JSON format
[0523] What it does: The terminal displays the program code in a user-friendly format.
[0524] Output: The program code displayed to the user
[0525] Step 8:
[0526] The user inputs numbers using program code and gets a result.
[0527] Input: The numbers you enter (e.g. 6 and 7)
[0528] Specific operation: The user inputs numbers into the program code on the terminal and executes the program.
[0529] Output: Program execution result (e.g. 42)
[0530] As described above, the specific operations performed at each step, as well as the input and output of data, can be explained in detail. This clarifies the processing flow of the entire system and makes it easier to understand how program code is generated in response to user requests.
[0531] (Application example 2)
[0532] 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."
[0533] Conventional program generation systems often make it difficult for users without programming knowledge to generate programs, and often fail to provide appropriate support that takes into account the user's emotional state. This results in a poor user experience, and it is difficult to provide appropriate interfaces and explanations, especially for users who are anxious or relaxed. Furthermore, in content distribution services, it is difficult to appropriately recommend content that users want to watch, making it difficult to improve user satisfaction.
[0534] 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.
[0535] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including a generative AI model for generating program code based on the request, means for recognizing emotions by analyzing the user's facial expressions and voice, means for adjusting the generated program code according to the user's emotional state, means for returning the generated program code to the terminal, and means for displaying the generated program code to the user and making it available for use, thereby enabling appropriate program generation and content recommendation according to the user's emotional state.
[0536] A "user" is an entity that uses the system to generate programs and receive content recommendations.
[0537] "Natural language" is a language that humans use on a daily basis, not program code.
[0538] A "server" is a central computer system that receives and processes requests from users.
[0539] A "generative AI model" refers to a collection of algorithms that analyze user requests and automatically generate program code.
[0540] "Facial expressions" are physical facial movements and placements used to determine the emotions expressed by a user.
[0541] "Audio" or "voice" refers to the spoken voice of the user and is used as part of sentiment analysis.
[0542] "Emotion recognition" means determining the user's emotional state at that time from their facial expression and voice.
[0543] "Program code" means a set of instructions in a format that a computer can understand and execute.
[0544] A "terminal" is a device (such as a smartphone or computer) that is directly operated by a user.
[0545] "Adjusting" refers to processing the generated program code and related information appropriately to suit the user's emotional state.
[0546] "Display" means visually outputting information on the screen of a terminal.
[0547] "Available" means that the user can actually operate or execute the generated program code.
[0548] The present invention is a system that allows a user to input a request in natural language, recognizes emotions from facial expressions and voice, and generates appropriate programs and recommends content according to the user's state. This system is realized by an application installed on a device such as a smartphone, smart glasses, a head-mounted display, or a robot. The system configuration and operation are described in detail below.
[0549] Components
[0550] 1. Terminal
[0551] Hardware: Devices such as smartphones, smart glasses, head-mounted displays, or robots.
[0552] Software: Installed OpenCV, transformers NLP models, and emotion recognition software.
[0553] 2. Server
[0554] Generative AI models: Algorithms that analyze user requests in natural language and generate program code (e.g., transformers).
[0555] Emotion recognition engine: Recognizes the user's emotional state by analyzing their facial expressions and voice.
[0556] Operation flow
[0557] 1. User request input
[0558] A user uses a terminal to input a request for content to be viewed or a program to be executed in natural language.
[0559] For example, a user may enter, "I want to watch a relaxing documentary."
[0560] 2. Emotional Recognition
[0561] The device's camera and microphone are used to capture the user's facial expressions and voice, which are then analyzed by an emotion recognition engine.
[0562] As a result of the analysis, the emotional state of the user, such as whether they are relaxed or anxious, is determined.
[0563] 3. Program Creation and Recommendation
[0564] The server uses a generative AI model to recommend appropriate program code and content based on the user's request and emotional state.
[0565] For example, in response to a request to "watch a documentary that will help me relax," documentary videos that are suitable for a relaxed state are recommended.
[0566] 4. Display and Use of Results
[0567] The generated program code and content recommendations are sent back to the terminal and displayed to the user.
[0568] The user checks the displayed information and starts viewing or playing as needed.
[0569] Specific examples
[0570] User Request: "I want to watch an uplifting music video."
[0571] Example prompt sentence:
[0572] User wants: Wants to watch an uplifting music video. User is feeling: Feeling anxious. Recommend an appropriate video.
[0573] System response: Recognizes when the user is in a state of agitation and immediately recommends energetic music videos.
[0574] A feature of the present invention is that appropriate content is recommended according to the user's emotional state, even if the user does not have any special programming knowledge, thereby improving the user experience and satisfying requests efficiently and quickly.
[0575] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0576] Step 1:
[0577] User request input
[0578] The user uses the terminal to input a request for the content they want to view or the program they want to run in natural language. In this case, the user enters text such as "I want to watch a relaxing documentary" into the input field. This text information is entered into the terminal, and the data is passed to the next processing step.
[0579] Step 2:
[0580] Emotion recognition
[0581] The device's camera and microphone are used to simultaneously capture the user's facial expressions and voice. The captured video and audio data are input into an emotion recognition engine. The emotion recognition engine (e.g., EmotionRecognizer) processes this data and determines the user's emotional state (relaxed, anxious, etc.). This emotional state information is sent to a server and input into a generative AI model.
[0582] Step 3:
[0583] Program Generation and Recommendations
[0584] The generative AI model installed on the server receives the user's request text (input in step 1) and emotional state (output in step 2) as input. The generative AI model analyzes this data using natural language processing (NLP) technology and recommends appropriate program code and content. For example, if the request text is "relaxing documentaries" and the emotional state is determined to be "relaxing," a list of documentary videos that can be enjoyed in a relaxed state will be generated. This list becomes the output of program generation and recommendations.
[0585] Step 4:
[0586] Displaying and Using the Results
[0587] The server returns the generated program code and a list of content recommendations to the device. The returned data is input into the device and visually displayed to the user. The user selects the documentary they want to watch from the displayed list and presses the play button to begin watching the video. All of this is done on the device, allowing users to easily consume content.
[0588] 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.
[0589] 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.
[0590] 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.
[0591] [Third embodiment]
[0592] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0593] 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.
[0594] 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).
[0595] 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.
[0596] 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.
[0597] 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).
[0598] 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. 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.
[0599] 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.
[0600] 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.
[0601] 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.
[0602] 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.
[0603] 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."
[0604] The present invention relates to a system that enables a user to easily generate and use a program without having programming knowledge. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be specifically described below in detail with reference to the accompanying drawings.
[0605] First, the user uses a terminal to input their requirements for program specifications and functions in natural language. For example, they might request, "I want a program that multiplies two numbers." This request is analyzed using natural language processing technology and converted into an appropriate technical requirement. The terminal then sends the results of this analysis to the server.
[0606] The AI module located on the server automatically generates program code based on the received request. This program code satisfies the user's request, such as code containing a function to multiply two numbers.
[0607] The generated program code is sent back from the server to the terminal and displayed on the terminal to the user. The user can check the displayed program code and execute it by entering specific values. This system allows users to easily obtain and use programs that meet their requirements, even if they do not have specialized programming knowledge.
[0608] As a concrete example, consider the case where a user requests, "I want a program to multiply two numbers." First, the device sends this request to the server. The AI module on the server analyzes it and generates an appropriate multiplication program. The generated program is sent back to the device, where the user receives and runs it. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0609] The system of the present invention converts user requirements into program code quickly and accurately and provides the results to the user, thereby significantly reducing the effort and cost associated with conventional program creation. Furthermore, since it does not require specialized knowledge and can be operated efficiently, it lowers the barrier to program creation.
[0610] The processing flow will be explained below.
[0611] Step 1:
[0612] A user uses a terminal to input a request for program specifications and functions in natural language. For example, a user might input a request such as "I want a program that multiplies two numbers."
[0613] Step 2:
[0614] The terminal receives the user's request and sends it to the server, where it is formatted into an appropriate format.
[0615] Step 3:
[0616] The server analyzes the received request using natural language processing technology, which converts the user's request into technical specifications.
[0617] Step 4:
[0618] An AI module on the server generates appropriate program code based on the parsed request, for example, a program code containing a function to perform multiplication.
[0619] Step 5:
[0620] The generated program code is sent back to the terminal from the server, which sends the generated code in an appropriate format.
[0621] Step 6:
[0622] The terminal displays the received program code to the user, who can then confirm the generated program code.
[0623] Step 7:
[0624] The user executes the generated program code on the terminal. Specifically, by inputting two numbers and executing the program, the result is obtained.
[0625] Step 8:
[0626] The terminal will execute the program code based on the numbers you enter and display the result. For example, if you enter 6 and 7, the terminal will display 42 as the result.
[0627] Step 9:
[0628] The user can check the displayed results and perform further operations or inputs as necessary. Through this series of processes, the user can easily use the program based on their request.
[0629] Example 1
[0630] 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."
[0631] The traditional program creation process required specialized programming knowledge, making it difficult for many users to use, and was therefore only available to a select few experts. Furthermore, program creation was time-consuming and costly, placing a heavy burden on non-experts. Furthermore, even when requirements were entered in natural language, there were limited means to properly analyze them and convert them into actual program code.
[0632] 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.
[0633] In this invention, the server includes a means for receiving a user's request in natural language, a means for transmitting the request to the server, a server including an artificial intelligence module that generates program code based on the request, a means for returning the generated program code to a terminal, and a means for displaying the generated program code to the user and making it available. This allows users to easily obtain and use programs that meet their requirements, even without specialized programming knowledge. Furthermore, the time and cost required for program generation can be significantly reduced, making it easy for even non-experts to use. Furthermore, by providing a means for accurately analyzing natural language requests and converting them into appropriate program code, programs that meet user requirements can be efficiently generated.
[0634] "Means for receiving user requests in natural language" refers to a device or method that allows a user to input program-related requests written in a language that humans use on a daily basis and converts the input into a data format that the system can understand.
[0635] The "means for sending the request to the server" refers to a device or method for transferring data over the Internet or a network to a server for processing the user's request.
[0636] A "server including an artificial intelligence module that generates program code based on the request" is a server equipped with artificial intelligence that analyzes the user's request received and automatically creates appropriate program code.
[0637] The "means for returning the generated program code to the terminal" refers to a device or method for returning the generated program code to the user's terminal again.
[0638] "Means for displaying and making the generated program code available to the user" refers to a device or method that displays the generated program code in an easily viewable manner on the user's terminal and allows the user to execute or modify the code.
[0639] "Natural language processing technology" is a technology that enables computers to understand and process the language that humans use on a daily basis.
[0640] A "calculation program" is a program for performing numerical processing and calculations based on specific numbers and data.
[0641] MODE FOR CARRYING OUT THE INVENTION
[0642] Overall system overview
[0643] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. This system includes a process that receives user requests in natural language, converts them into appropriate program code, and provides the code to the user.
[0644] User request input
[0645] A user uses a terminal to input program specifications and functional requirements in natural language. This request is made simply using a keyboard or touch screen. For example, a request might be "I want a program that multiplies two numbers."
[0646] Natural language analysis and transmission
[0647] The device receives the user's request and analyzes it using natural language processing technology. NLP technologies such as "Google Cloud Natural Language API" are used for this analysis. The analyzed results are converted into technical requests and sent to the server using the HTTPS protocol. Security is ensured by encrypting the data during this process.
[0648] Program Generation
[0649] The server hosts a generative AI model (e.g., "OpenAI GPT-3"). This generative AI model automatically generates program code based on the received technical requirements. The generated program code satisfies the user's requirements, and may include, for example, a function to multiply two numbers. The generative AI model is configured to generate code in an appropriate programming language, such as Python or JavaScript.
[0650] Returning and Viewing Programs
[0651] The generated program code is sent back from the server to the terminal and displayed to the user. The user can check the code displayed on the terminal screen and execute it by entering specific numbers as needed. For example, if the user enters "6" and "7", the program will return the result "42".
[0652] Specific examples
[0653] Let us consider a specific example where a user requests "I want a program that multiplies two numbers." First, the user inputs this request in natural language using a device. Next, the device analyzes the request using natural language processing technology and sends the analysis results to the server. A generative AI model on the server generates appropriate program code based on the analysis results and sends that code back to the device. Finally, the user checks the generated program code on the device, enters numbers, and runs it. This allows users to easily use programs without specialized knowledge.
[0654] Prompt Sentence Examples
[0655] An example prompt for a generative AI model might be something like:
[0656] "Generate a Python program to multiply two numbers. Follow this format:
[0657] def multiply(x, y):
[0658] return [multiplication result]"
[0659] The above is a specific embodiment for carrying out the present invention. This system allows users to easily obtain and use programs, significantly reducing the effort and cost associated with conventional program creation.
[0660] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0661] Step 1:
[0662] Users input their requirements for program specifications and functions into a terminal in natural language, for example, "I want a program that multiplies two numbers." This input is done using a keyboard or touch screen.
[0663] Step 2:
[0664] The device analyzes the user's request using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to convert a request such as "I want a multiplication program" into a technical request (for example, "Create a program to multiply two numbers"). This analysis is completed within a few seconds, and the analysis result is generated.
[0665] Step 3:
[0666] The terminal sends the parsed technical request to the server. The transmission is carried out via the HTTPS protocol and security is ensured by data encryption. The input is the parsed technical request and the output is the data sent to the server.
[0667] Step 4:
[0668] The server uses a generative AI model (e.g., OpenAI GPT-3) to automatically generate program code based on the received technical requirements. The generative AI model understands the technical requirements and creates program code that includes, for example, a function to multiply two numbers in Python. For data processing, the input technical requirements are passed to the AI model, which then generates code. The output is the generated program code.
[0669] Step 5:
[0670] The server returns the generated program code to the terminal. This return is also done using the HTTPS protocol. The input is the generated program code, and the output is the data returned to the terminal.
[0671] Step 6:
[0672] The terminal displays the received program code to the user. The user checks this program code and executes the program by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. The input is the program code returned to the terminal and the numbers entered by the user, and the output is the execution result displayed.
[0673] The above is the specific processing flow of the program for this system.
[0674] (Application example 1)
[0675] 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."
[0676] In the past, users needed specialized knowledge to create programs, which required high learning costs. Furthermore, when searching for specific products or placing customized orders on online shopping sites, it was difficult to quickly generate appropriate programs, making them difficult for users to operate easily. This resulted in a lack of user-friendly search and customization functions.
[0677] 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.
[0678] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an artificial intelligence module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for automatically generating a program for product search and customized ordering, means for searching for products based on the generated program code, and means for displaying search results to the user and allowing them to purchase directly. This enables users to search for products and place customized orders in natural language without specialized programming knowledge.
[0679] The "means for receiving a user's request in natural language" is an interface for analyzing a request made by a user in natural language and inputting the analysis result into the system.
[0680] The "means for transmitting the request to the server" refers to a communication means for transferring the request data received from the user to the server.
[0681] A "server including an artificial intelligence module for generating program code" is a server equipped with artificial intelligence (AI) that automatically generates program code based on user requests.
[0682] The "means for returning the generated program code to the terminal" refers to a communication means for transmitting the program code generated by the server to the user's terminal.
[0683] "Means for displaying the generated program code to the user and making it available" refers to means for displaying the generated program code on the user's terminal and enabling the user to operate or execute the program code.
[0684] The "means for automatically generating a program for product search and customized ordering" is a means for generating a program for automatically performing a product search and customized ordering based on a request from a user in natural language.
[0685] The "means for searching for a product based on the generated program code" refers to a means for searching for a specific product from a database using the generated program code.
[0686] The "means for displaying search results to the user and enabling immediate purchase" refers to a means for displaying searched product information on the user's terminal and enabling the user to immediately purchase the product.
[0687] "Means for analyzing using natural language processing technology" refers to means for analyzing a user's request in natural language and using technology to understand the intent and content of that request.
[0688] The "program code" "search program for product search and customized ordering" is a program for searching for products based on user requests and customizing order details.
[0689] The present invention relates to a system that enables users to easily search for products and place customized orders, particularly on online shopping sites, without having to have programming knowledge. Specific embodiments for carrying out the present invention will be described below.
[0690] First, the user uses a smartphone application to input product specifications and requirements in natural language. For example, "I want a black T-shirt in size L." This request is analyzed using natural language processing (NLP) technology and converted into appropriate technical requirements.
[0691] For analysis, a request is sent from the terminal to the server, where it is analyzed by an NLP model (e.g., BERT) located on the server. The analyzed request is converted into a technical request (e.g., category "T-shirt", color "black", size "L").
[0692] Next, the analyzed data is passed to a generative AI model (e.g., GPT-4) on the server. The generative AI model automatically generates program code for product searches and customized orders based on the analyzed data. The generated program code is expressed in the form of, for example, an SQL query.
[0693] The generated program code is sent back from the server to the terminal. On the terminal, this code is displayed in the user interface and is provided in an immediately executable state. Based on the generated code, a product search is performed using database software (e.g., MySQL), and the results are displayed to the user. The user can check the displayed product information and proceed with the purchase procedure if necessary.
[0694] Examples:
[0695] User Input:
[0696] "I want a black T-shirt, size L."
[0697] Generates the prompt statement:
[0698] "Write a program to search for and display black T-shirts in size L."
[0699] Example of generated code for database lookup:
[0700] SQL query format: SELECT FROM products WHERE category='T-shirt' AND color='black' AND size='L';
[0701] Output:
[0702] The search results will show a list of black T-shirts in size L, and the user can proceed to purchase them.
[0703] This system allows users to easily search for and purchase products that meet their needs without any specialized programming knowledge, thereby improving the user-friendliness and convenience of online shopping sites.
[0704] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0705] Step 1:
[0706] The user inputs product specifications and requests into the terminal in natural language. For example, "I want a black T-shirt in size L." This input data is prepared for the next step.
[0707] Step 2:
[0708] The terminal sends the user's request to the server. HTTP or WebSocket is typically used as the communication protocol. At this stage, the input data (user request) is transferred to the server.
[0709] Step 3:
[0710] The server analyzes the received request using natural language processing (NLP) technology. Specifically, it analyzes the input data using an NLP model (e.g., BERT) and converts it into technical requirements (e.g., category "T-shirt", color "black", size "L"). This converted data becomes the input data for the next step.
[0711] Step 4:
[0712] The server uses a generative AI model (e.g., GPT-4) to automatically generate program code based on technical requirements. The generated code is in the form of an SQL query for product search and customized ordering. This SQL query serves as input data for the next step.
[0713] Step 5:
[0714] The server returns the generated program code (e.g., an SQL query) to the terminal, again using HTTP or WebSocket as the communication protocol. The generated code is displayed on the terminal.
[0715] Step 6:
[0716] The terminal executes the received program code and searches the database for the corresponding product. The database software used is MySQL. Specifically, an SQL query is executed to extract the corresponding product data from the database. This extracted product data becomes the input data for the next step.
[0717] Step 7:
[0718] The terminal displays the search results to the user. The extracted product data is displayed in a formatted form so that the user can check the results. Specifically, the product details screen displays the product name, price, stock status, etc.
[0719] Step 8:
[0720] If a user decides to purchase after viewing the search results, they can proceed with the purchase process by pressing the purchase button on their device.
[0721] Through this series of processes, it is possible to provide a system that allows users to search for products and place customized orders through requests in natural language, without the need for specialized programming knowledge.
[0722] 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.
[0723] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system improves the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. The following describes in detail the embodiments of the present invention.
[0724] First, the user uses a terminal to input their requirements for the program's specifications and functions in natural language. At this time, an emotion engine is activated that analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user inputs "I want a program that multiplies two numbers," and the user is feeling relaxed, an explanation will be displayed in simple language; if the user is feeling impatient, the process will proceed quickly.
[0725] The device sends the user's request and emotional data to the server, where the request is formatted appropriately. The server then analyzes the received request using natural language processing technology and generates program code based on the analysis results. The content and difficulty of the generated program are adjusted according to the user's emotional state.
[0726] The generated program code is sent back from the server to the device and displayed to the user. The emotion engine continuously monitors the user's emotions and adjusts the program's explanation and usage instructions accordingly. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0727] As a concrete example, consider the case where a user requests a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program, along with detailed explanations and additional learning resources. On the other hand, if the user is anxious, a program in a format that can be quickly executed will be displayed. This system allows users to quickly and accurately obtain and use the necessary program while receiving assistance tailored to their emotional state.
[0728] The system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it lowers the barrier to program creation.
[0729] The processing flow will be explained below.
[0730] Step 1:
[0731] A user uses a terminal to input requests for program specifications and functions in natural language. For example, a user might request, "I want a program that multiplies two numbers."
[0732] Step 2:
[0733] The device's emotion engine recognizes the user's emotions from their facial expressions and voice, determining, for example, whether they are relaxed or anxious.
[0734] Step 3:
[0735] The device transmits the user's request and the emotion data it recognizes to the server, where the request is formatted appropriately.
[0736] Step 4:
[0737] An AI module on the server analyzes the received request using natural language processing technology and converts it into technical specifications. For example, it may be analyzed as a request to "create a multiplication program."
[0738] Step 5:
[0739] The server's AI module generates program code based on the analysis results, and adjusts the program's content and explanations according to the user's emotional state.
[0740] Step 6:
[0741] The generated program code is sent back to the terminal from the server, which sends the code in the appropriate format.
[0742] Step 7:
[0743] The terminal displays the received program code to the user, and the emotion engine continues to monitor the user's emotions and provide appropriate feedback.
[0744] Step 8:
[0745] The user checks the generated program code on the terminal and executes it by entering specific numbers, for example, 6 and 7.
[0746] Step 9:
[0747] The terminal runs a program based on the numbers you enter and displays the result, for example, 42.
[0748] Step 10:
[0749] The user can review the displayed results and take further action or input as needed, and the emotion engine provides additional feedback and assistance depending on the user's emotional state.
[0750] This series of processes allows the user to receive appropriate support tailored to their emotional state, while quickly and accurately generating and using the necessary programs.
[0751] Example 2
[0752] 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."
[0753] Conventional program generation systems are difficult to operate unless the user has programming knowledge, and they are unable to provide support tailored to the emotional state of each individual user. As a result, the increased effort and stress involved in creating programs has become a problem.
[0754] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0755] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an AI module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for recognizing the user's emotional state, and means for adjusting processing in accordance with the recognized emotional state. This allows users to easily generate and use programs without specialized knowledge and receive support in accordance with their emotional state.
[0756] The "means for receiving a user's request in natural language" refers to a device or software that has the function of analyzing and acquiring a request in natural language input by a user.
[0757] The "means for sending a request to a server" refers to a device or software that has the function of sending a request entered by a user to a server via the Internet or other communication means.
[0758] A "server including an AI module for generating program code" is a server that has the function of automatically generating appropriate program code based on received requests using AI technology.
[0759] The "means for returning the generated program code to the terminal" refers to a device or software that has the function of transmitting the program code generated by the server to the user's terminal via the network.
[0760] "Means for displaying and making available the generated program code to the user" means a device or software that visually displays the received program code on a terminal and allows the user to operate and execute the program code.
[0761] "Means for recognizing the user's emotional state" refers to a device or software that has the function of analyzing and recognizing the user's emotional state from their facial expressions and voice.
[0762] The "means for adjusting processing in accordance with the recognized emotional state" refers to a device or software that has the function of dynamically adjusting the display content, processing speed, etc. based on the recognized emotional state of the user.
[0763] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system can improve the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. Specific embodiments of this system are described in detail below.
[0764] First, a user uses a device (e.g., a PC or smartphone) to input program specifications and function requirements in natural language. The device is equipped with a camera and microphone, which captures the user's facial expressions and voice. This data is then analyzed by an emotion engine (e.g., FaceAPI for facial expression recognition and Google Cloud Speech-to-Text for voice recognition) to recognize the user's emotional state in real time.
[0765] Next, the device sends the user's input request (e.g., "I want a program to multiply two numbers") and emotional data (relaxed, anxious, etc.) to the server. This data is formatted in JSON format and sent to the server via the Internet or other communication means.
[0766] The server analyzes the received JSON-formatted request and emotional data. It uses natural language processing (NLP) to analyze the request and automatically generate appropriate program code. This is done using a generative AI model (e.g., OpenAI's GPT-3). It also dynamically adjusts the content and difficulty of the generated program based on the recognized emotional state of the user. Specifically, it provides a program with detailed comments to a relaxed user, and concise, quickly executable code to a rushed user.
[0767] The generated program code is sent back from the server to the device. The device then displays the received program code to the user. Furthermore, the device's built-in emotion engine continuously monitors the user's emotions and can provide feedback or additional explanations according to the situation. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42.
[0768] As a concrete example, consider a user requesting a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program with detailed instructions and additional learning resources (e.g., links to documentation). On the other hand, if the user is impatient, the program will be displayed in a concise, quickly executable form.
[0769] Examples of prompts include:
[0770] "Generate a program that multiplies two numbers. The user is relaxed."
[0771] or
[0772] "Generate a program that multiplies two numbers. The user is in a hurry."
[0773] As described above, the system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it can lower the barrier to program creation.
[0774] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0775] Step 1:
[0776] The user uses the terminal to enter a request in natural language.
[0777] Input: User request (e.g., "I want a program to multiply two numbers")
[0778] Specific actions: The user enters a request in natural language into an input field on the terminal.
[0779] Output: Request data captured by the device
[0780] Step 2:
[0781] The device captures the user's facial expression and voice data and sends it to the emotion engine.
[0782] Input: User's facial expressions and voice
[0783] Specific operation: The device's camera captures facial expressions and microphone captures voice. The emotion engine receives and analyzes this data.
[0784] Output: User's emotional state (e.g., relaxed, anxious)
[0785] Step 3:
[0786] The terminal transmits the request data and the emotional state information to the server.
[0787] Input: Request data and emotional state information
[0788] Specific operation: The device formats the request data and emotional state information into JSON format and sends it to the server via the network.
[0789] Output: JSON data received by the server
[0790] Step 4:
[0791] The request data received by the server is analyzed using natural language processing technology.
[0792] Input: Request data in JSON format
[0793] Specific operation: The request data is analyzed by a natural language processing engine (e.g., a generative AI model) on the server, and program code specifications are extracted according to the demand.
[0794] Output: Program specification based on parsed requirements
[0795] Step 5:
[0796] The server generates program code based on the analysis results and emotional state.
[0797] Input: Program specifications and user emotional state
[0798] How it works: The server's AI module generates program code based on the user's emotional state and the user's specifications. For a relaxed user, detailed comments are generated, while for a panicked user, concise code is generated.
[0799] Output: Generated program code
[0800] Step 6:
[0801] The server formats the generated program code into JSON format and returns it to the terminal.
[0802] Input: Generated program code
[0803] Specific operation: The server converts the program code into JSON format and sends it to the terminal via the network.
[0804] Output: Program code in JSON format received by the terminal
[0805] Step 7:
[0806] The terminal displays the received program code to the user.
[0807] Input: Program code in JSON format
[0808] What it does: The terminal displays the program code in a user-friendly format.
[0809] Output: The program code displayed to the user
[0810] Step 8:
[0811] The user inputs numbers using program code and gets a result.
[0812] Input: The numbers you enter (e.g. 6 and 7)
[0813] Specific operation: The user inputs numbers into the program code on the terminal and executes the program.
[0814] Output: Program execution result (e.g. 42)
[0815] As described above, the specific operations performed at each step, as well as the input and output of data, can be explained in detail. This clarifies the processing flow of the entire system and makes it easier to understand how program code is generated in response to user requests.
[0816] (Application example 2)
[0817] 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."
[0818] Conventional program generation systems often make it difficult for users without programming knowledge to generate programs, and often fail to provide appropriate support that takes into account the user's emotional state. This results in a poor user experience, and it is difficult to provide appropriate interfaces and explanations, especially for users who are anxious or relaxed. Furthermore, in content distribution services, it is difficult to appropriately recommend content that users want to watch, making it difficult to improve user satisfaction.
[0819] 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.
[0820] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including a generative AI model for generating program code based on the request, means for recognizing emotions by analyzing the user's facial expressions and voice, means for adjusting the generated program code according to the user's emotional state, means for returning the generated program code to the terminal, and means for displaying the generated program code to the user and making it available for use, thereby enabling appropriate program generation and content recommendation according to the user's emotional state.
[0821] A "user" is an entity that uses the system to generate programs and receive content recommendations.
[0822] "Natural language" is a language that humans use on a daily basis, not program code.
[0823] A "server" is a central computer system that receives and processes requests from users.
[0824] A "generative AI model" refers to a collection of algorithms that analyze user requests and automatically generate program code.
[0825] "Facial expressions" are physical facial movements and placements used to determine the emotions expressed by a user.
[0826] "Audio" or "voice" refers to the spoken voice of the user and is used as part of sentiment analysis.
[0827] "Emotion recognition" means determining the user's emotional state at that time from their facial expression and voice.
[0828] "Program code" means a set of instructions in a format that a computer can understand and execute.
[0829] A "terminal" is a device (such as a smartphone or computer) that is directly operated by a user.
[0830] "Adjusting" refers to processing the generated program code and related information appropriately to suit the user's emotional state.
[0831] "Display" means visually outputting information on the screen of a terminal.
[0832] "Available" means that the user can actually operate or execute the generated program code.
[0833] The present invention is a system that allows a user to input a request in natural language, recognizes emotions from facial expressions and voice, and generates appropriate programs and recommends content according to the user's state. This system is realized by an application installed on a device such as a smartphone, smart glasses, a head-mounted display, or a robot. The system configuration and operation are described in detail below.
[0834] Components
[0835] 1. Terminal
[0836] Hardware: Devices such as smartphones, smart glasses, head-mounted displays, or robots.
[0837] Software: Installed OpenCV, transformers NLP models, and emotion recognition software.
[0838] 2. Server
[0839] Generative AI models: Algorithms that analyze user requests in natural language and generate program code (e.g., transformers).
[0840] Emotion recognition engine: Recognizes the user's emotional state by analyzing their facial expressions and voice.
[0841] Operation flow
[0842] 1. User request input
[0843] A user uses a terminal to input a request for content to be viewed or a program to be executed in natural language.
[0844] For example, a user may enter, "I want to watch a relaxing documentary."
[0845] 2. Emotional Recognition
[0846] The device's camera and microphone are used to capture the user's facial expressions and voice, which are then analyzed by an emotion recognition engine.
[0847] As a result of the analysis, the emotional state of the user, such as whether they are relaxed or anxious, is determined.
[0848] 3. Program Creation and Recommendation
[0849] The server uses a generative AI model to recommend appropriate program code and content based on the user's request and emotional state.
[0850] For example, in response to a request to "watch a documentary that will help me relax," documentary videos that are suitable for a relaxed state are recommended.
[0851] 4. Display and Use of Results
[0852] The generated program code and content recommendations are sent back to the terminal and displayed to the user.
[0853] The user checks the displayed information and starts viewing or playing as needed.
[0854] Specific examples
[0855] User Request: "I want to watch an uplifting music video."
[0856] Example prompt sentence:
[0857] User wants: Wants to watch an uplifting music video. User is feeling: Feeling anxious. Recommend an appropriate video.
[0858] System response: Recognizes when the user is in a state of agitation and immediately recommends energetic music videos.
[0859] A feature of the present invention is that appropriate content is recommended according to the user's emotional state, even if the user does not have any special programming knowledge, thereby improving the user experience and satisfying requests efficiently and quickly.
[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0861] Step 1:
[0862] User request input
[0863] The user uses the terminal to input a request for the content they want to view or the program they want to run in natural language. In this case, the user enters text such as "I want to watch a relaxing documentary" into the input field. This text information is entered into the terminal, and the data is passed to the next processing step.
[0864] Step 2:
[0865] Emotion recognition
[0866] The device's camera and microphone are used to simultaneously capture the user's facial expressions and voice. The captured video and audio data are input into an emotion recognition engine. The emotion recognition engine (e.g., EmotionRecognizer) processes this data and determines the user's emotional state (relaxed, anxious, etc.). This emotional state information is sent to a server and input into a generative AI model.
[0867] Step 3:
[0868] Program Generation and Recommendations
[0869] The generative AI model installed on the server receives the user's request text (input in step 1) and emotional state (output in step 2) as input. The generative AI model analyzes this data using natural language processing (NLP) technology and recommends appropriate program code and content. For example, if the request text is "relaxing documentaries" and the emotional state is determined to be "relaxing," a list of documentary videos that can be enjoyed in a relaxed state will be generated. This list becomes the output of program generation and recommendations.
[0870] Step 4:
[0871] Displaying and Using the Results
[0872] The server returns the generated program code and a list of content recommendations to the device. The returned data is input into the device and visually displayed to the user. The user selects the documentary they want to watch from the displayed list and presses the play button to begin watching the video. All of this is done on the device, allowing users to easily consume content.
[0873] 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.
[0874] 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.
[0875] 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.
[0876] [Fourth embodiment]
[0877] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[0878] 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.
[0879] 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).
[0880] 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.
[0881] 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.
[0882] 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).
[0883] 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. 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.
[0884] 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.
[0885] 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.
[0886] 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.
[0887] 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.
[0888] 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.
[0889] 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."
[0890] The present invention relates to a system that enables a user to easily generate and use a program without having programming knowledge. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS ... will be specifically described below in detail with reference to the accompanying drawings.
[0891] First, the user uses a terminal to input their requirements for program specifications and functions in natural language. For example, they might request, "I want a program that multiplies two numbers." This request is analyzed using natural language processing technology and converted into an appropriate technical requirement. The terminal then sends the results of this analysis to the server.
[0892] The AI module located on the server automatically generates program code based on the received request. This program code satisfies the user's request, such as code containing a function to multiply two numbers.
[0893] The generated program code is sent back from the server to the terminal and displayed on the terminal to the user. The user can check the displayed program code and execute it by entering specific values. This system allows users to easily obtain and use programs that meet their requirements, even if they do not have specialized programming knowledge.
[0894] As a concrete example, consider the case where a user requests, "I want a program to multiply two numbers." First, the device sends this request to the server. The AI module on the server analyzes it and generates an appropriate multiplication program. The generated program is sent back to the device, where the user receives and runs it. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[0895] The system of the present invention converts user requirements into program code quickly and accurately and provides the results to the user, thereby significantly reducing the effort and cost associated with conventional program creation. Furthermore, since it does not require specialized knowledge and can be operated efficiently, it lowers the barrier to program creation.
[0896] The processing flow will be explained below.
[0897] Step 1:
[0898] A user uses a terminal to input a request for program specifications and functions in natural language. For example, a user might input a request such as "I want a program that multiplies two numbers."
[0899] Step 2:
[0900] The terminal receives the user's request and sends it to the server, where it is formatted into an appropriate format.
[0901] Step 3:
[0902] The server analyzes the received request using natural language processing technology, which converts the user's request into technical specifications.
[0903] Step 4:
[0904] An AI module on the server generates appropriate program code based on the parsed request, for example, a program code containing a function to perform multiplication.
[0905] Step 5:
[0906] The generated program code is sent back to the terminal from the server, which sends the generated code in an appropriate format.
[0907] Step 6:
[0908] The terminal displays the received program code to the user, who can then confirm the generated program code.
[0909] Step 7:
[0910] The user executes the generated program code on the terminal. Specifically, by inputting two numbers and executing the program, the result is obtained.
[0911] Step 8:
[0912] The terminal will execute the program code based on the numbers you enter and display the result. For example, if you enter 6 and 7, the terminal will display 42 as the result.
[0913] Step 9:
[0914] The user can check the displayed results and perform further operations or inputs as necessary. Through this series of processes, the user can easily use the program based on their request.
[0915] Example 1
[0916] 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."
[0917] The traditional program creation process required specialized programming knowledge, making it difficult for many users to use, and was therefore only available to a select few experts. Furthermore, program creation was time-consuming and costly, placing a heavy burden on non-experts. Furthermore, even when requirements were entered in natural language, there were limited means to properly analyze them and convert them into actual program code.
[0918] 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.
[0919] In this invention, the server includes a means for receiving a user's request in natural language, a means for transmitting the request to the server, a server including an artificial intelligence module that generates program code based on the request, a means for returning the generated program code to a terminal, and a means for displaying the generated program code to the user and making it available. This allows users to easily obtain and use programs that meet their requirements, even without specialized programming knowledge. Furthermore, the time and cost required for program generation can be significantly reduced, making it easy for even non-experts to use. Furthermore, by providing a means for accurately analyzing natural language requests and converting them into appropriate program code, programs that meet user requirements can be efficiently generated.
[0920] "Means for receiving user requests in natural language" refers to a device or method that allows a user to input program-related requests written in a language that humans use on a daily basis and converts the input into a data format that the system can understand.
[0921] The "means for sending the request to the server" refers to a device or method for transferring data over the Internet or a network to a server for processing the user's request.
[0922] A "server including an artificial intelligence module that generates program code based on the request" is a server equipped with artificial intelligence that analyzes the user's request received and automatically creates appropriate program code.
[0923] The "means for returning the generated program code to the terminal" refers to a device or method for returning the generated program code to the user's terminal again.
[0924] "Means for displaying and making the generated program code available to the user" refers to a device or method that displays the generated program code in an easily viewable manner on the user's terminal and allows the user to execute or modify the code.
[0925] "Natural language processing technology" is a technology that enables computers to understand and process the language that humans use on a daily basis.
[0926] A "calculation program" is a program for performing numerical processing and calculations based on specific numbers and data.
[0927] MODE FOR CARRYING OUT THE INVENTION
[0928] Overall system overview
[0929] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. This system includes a process that receives user requests in natural language, converts them into appropriate program code, and provides the code to the user.
[0930] User request input
[0931] A user uses a terminal to input program specifications and functional requirements in natural language. This request is made simply using a keyboard or touch screen. For example, a request might be "I want a program that multiplies two numbers."
[0932] Natural language analysis and transmission
[0933] The device receives the user's request and analyzes it using natural language processing technology. NLP technologies such as "Google Cloud Natural Language API" are used for this analysis. The analyzed results are converted into technical requests and sent to the server using the HTTPS protocol. Security is ensured by encrypting the data during this process.
[0934] Program Generation
[0935] The server hosts a generative AI model (e.g., "OpenAI GPT-3"). This generative AI model automatically generates program code based on the received technical requirements. The generated program code satisfies the user's requirements, and may include, for example, a function to multiply two numbers. The generative AI model is configured to generate code in an appropriate programming language, such as Python or JavaScript.
[0936] Returning and Viewing Programs
[0937] The generated program code is sent back from the server to the terminal and displayed to the user. The user can check the code displayed on the terminal screen and execute it by entering specific numbers as needed. For example, if the user enters "6" and "7", the program will return the result "42".
[0938] Specific examples
[0939] Let us consider a specific example where a user requests "I want a program that multiplies two numbers." First, the user inputs this request in natural language using a device. Next, the device analyzes the request using natural language processing technology and sends the analysis results to the server. A generative AI model on the server generates appropriate program code based on the analysis results and sends that code back to the device. Finally, the user checks the generated program code on the device, enters numbers, and runs it. This allows users to easily use programs without specialized knowledge.
[0940] Prompt Sentence Examples
[0941] An example prompt for a generative AI model might be something like:
[0942] "Generate a Python program to multiply two numbers. Follow this format:
[0943] def multiply(x, y):
[0944] return [multiplication result]"
[0945] The above is a specific embodiment for carrying out the present invention. This system allows users to easily obtain and use programs, significantly reducing the effort and cost associated with conventional program creation.
[0946] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0947] Step 1:
[0948] Users input their requirements for program specifications and functions into a terminal in natural language, for example, "I want a program that multiplies two numbers." This input is done using a keyboard or touch screen.
[0949] Step 2:
[0950] The device analyzes the user's request using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to convert a request such as "I want a multiplication program" into a technical request (for example, "Create a program to multiply two numbers"). This analysis is completed within a few seconds, and the analysis result is generated.
[0951] Step 3:
[0952] The terminal sends the parsed technical request to the server. The transmission is carried out via the HTTPS protocol and security is ensured by data encryption. The input is the parsed technical request and the output is the data sent to the server.
[0953] Step 4:
[0954] The server uses a generative AI model (e.g., OpenAI GPT-3) to automatically generate program code based on the received technical requirements. The generative AI model understands the technical requirements and creates program code that includes, for example, a function to multiply two numbers in Python. For data processing, the input technical requirements are passed to the AI model, which then generates code. The output is the generated program code.
[0955] Step 5:
[0956] The server returns the generated program code to the terminal. This return is also done using the HTTPS protocol. The input is the generated program code, and the output is the data returned to the terminal.
[0957] Step 6:
[0958] The terminal displays the received program code to the user. The user checks this program code and executes the program by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. The input is the program code returned to the terminal and the numbers entered by the user, and the output is the execution result displayed.
[0959] The above is the specific processing flow of the program for this system.
[0960] (Application example 1)
[0961] 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."
[0962] In the past, users needed specialized knowledge to create programs, which required high learning costs. Furthermore, when searching for specific products or placing customized orders on online shopping sites, it was difficult to quickly generate appropriate programs, making them difficult for users to operate easily. This resulted in a lack of user-friendly search and customization functions.
[0963] 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.
[0964] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an artificial intelligence module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for automatically generating a program for product search and customized ordering, means for searching for products based on the generated program code, and means for displaying search results to the user and allowing them to purchase directly. This enables users to search for products and place customized orders in natural language without specialized programming knowledge.
[0965] The "means for receiving a user's request in natural language" is an interface for analyzing a request made by a user in natural language and inputting the analysis result into the system.
[0966] The "means for transmitting the request to the server" refers to a communication means for transferring the request data received from the user to the server.
[0967] A "server including an artificial intelligence module for generating program code" is a server equipped with artificial intelligence (AI) that automatically generates program code based on user requests.
[0968] The "means for returning the generated program code to the terminal" refers to a communication means for transmitting the program code generated by the server to the user's terminal.
[0969] "Means for displaying the generated program code to the user and making it available" refers to means for displaying the generated program code on the user's terminal and enabling the user to operate or execute the program code.
[0970] The "means for automatically generating a program for product search and customized ordering" is a means for generating a program for automatically performing a product search and customized ordering based on a request from a user in natural language.
[0971] The "means for searching for a product based on the generated program code" refers to a means for searching for a specific product from a database using the generated program code.
[0972] The "means for displaying search results to the user and enabling immediate purchase" refers to a means for displaying searched product information on the user's terminal and enabling the user to immediately purchase the product.
[0973] "Means for analyzing using natural language processing technology" refers to means for analyzing a user's request in natural language and using technology to understand the intent and content of that request.
[0974] The "program code" "search program for product search and customized ordering" is a program for searching for products based on user requests and customizing order details.
[0975] The present invention relates to a system that enables users to easily search for products and place customized orders, particularly on online shopping sites, without having to have programming knowledge. Specific embodiments for carrying out the present invention will be described below.
[0976] First, the user uses a smartphone application to input product specifications and requirements in natural language. For example, "I want a black T-shirt in size L." This request is analyzed using natural language processing (NLP) technology and converted into appropriate technical requirements.
[0977] For analysis, a request is sent from the terminal to the server, where it is analyzed by an NLP model (e.g., BERT) located on the server. The analyzed request is converted into a technical request (e.g., category "T-shirt", color "black", size "L").
[0978] Next, the analyzed data is passed to a generative AI model (e.g., GPT-4) on the server. The generative AI model automatically generates program code for product searches and customized orders based on the analyzed data. The generated program code is expressed in the form of, for example, an SQL query.
[0979] The generated program code is sent back from the server to the terminal. On the terminal, this code is displayed in the user interface and is provided in an immediately executable state. Based on the generated code, a product search is performed using database software (e.g., MySQL), and the results are displayed to the user. The user can check the displayed product information and proceed with the purchase procedure if necessary.
[0980] Examples:
[0981] User Input:
[0982] "I want a black T-shirt, size L."
[0983] Generates the prompt statement:
[0984] "Write a program to search for and display black T-shirts in size L."
[0985] Example of generated code for database lookup:
[0986] SQL query format: SELECT FROM products WHERE category='T-shirt' AND color='black' AND size='L';
[0987] Output:
[0988] The search results will show a list of black T-shirts in size L, and the user can proceed to purchase them.
[0989] This system allows users to easily search for and purchase products that meet their needs without any specialized programming knowledge, thereby improving the user-friendliness and convenience of online shopping sites.
[0990] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0991] Step 1:
[0992] The user inputs product specifications and requests into the terminal in natural language. For example, "I want a black T-shirt in size L." This input data is prepared for the next step.
[0993] Step 2:
[0994] The terminal sends the user's request to the server. HTTP or WebSocket is typically used as the communication protocol. At this stage, the input data (user request) is transferred to the server.
[0995] Step 3:
[0996] The server analyzes the received request using natural language processing (NLP) technology. Specifically, it analyzes the input data using an NLP model (e.g., BERT) and converts it into technical requirements (e.g., category "T-shirt", color "black", size "L"). This converted data becomes the input data for the next step.
[0997] Step 4:
[0998] The server uses a generative AI model (e.g., GPT-4) to automatically generate program code based on technical requirements. The generated code is in the form of an SQL query for product search and customized ordering. This SQL query serves as input data for the next step.
[0999] Step 5:
[1000] The server returns the generated program code (e.g., an SQL query) to the terminal, again using HTTP or WebSocket as the communication protocol. The generated code is displayed on the terminal.
[1001] Step 6:
[1002] The terminal executes the received program code and searches the database for the corresponding product. The database software used is MySQL. Specifically, an SQL query is executed to extract the corresponding product data from the database. This extracted product data becomes the input data for the next step.
[1003] Step 7:
[1004] The terminal displays the search results to the user. The extracted product data is displayed in a formatted form so that the user can check the results. Specifically, the product details screen displays the product name, price, stock status, etc.
[1005] Step 8:
[1006] If a user decides to purchase after viewing the search results, they can proceed with the purchase process by pressing the purchase button on their device.
[1007] Through this series of processes, it is possible to provide a system that allows users to search for products and place customized orders through requests in natural language, without the need for specialized programming knowledge.
[1008] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[1009] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system improves the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. The following describes in detail the embodiments of the present invention.
[1010] First, the user uses a terminal to input their requirements for the program's specifications and functions in natural language. At this time, an emotion engine is activated that analyzes the user's facial expressions and voice to recognize their emotional state. For example, if the user inputs "I want a program that multiplies two numbers," and the user is feeling relaxed, an explanation will be displayed in simple language; if the user is feeling impatient, the process will proceed quickly.
[1011] The device sends the user's request and emotional data to the server, where the request is formatted appropriately. The server then analyzes the received request using natural language processing technology and generates program code based on the analysis results. The content and difficulty of the generated program are adjusted according to the user's emotional state.
[1012] The generated program code is sent back from the server to the device and displayed to the user. The emotion engine continuously monitors the user's emotions and adjusts the program's explanation and usage instructions accordingly. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42. This allows users to easily perform calculations without having to code the program themselves.
[1013] As a concrete example, consider the case where a user requests a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program, along with detailed explanations and additional learning resources. On the other hand, if the user is anxious, a program in a format that can be quickly executed will be displayed. This system allows users to quickly and accurately obtain and use the necessary program while receiving assistance tailored to their emotional state.
[1014] The system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it lowers the barrier to program creation.
[1015] The processing flow will be explained below.
[1016] Step 1:
[1017] A user uses a terminal to input requests for program specifications and functions in natural language. For example, a user might request, "I want a program that multiplies two numbers."
[1018] Step 2:
[1019] The device's emotion engine recognizes the user's emotions from their facial expressions and voice, determining, for example, whether they are relaxed or anxious.
[1020] Step 3:
[1021] The device transmits the user's request and the emotion data it recognizes to the server, where the request is formatted appropriately.
[1022] Step 4:
[1023] An AI module on the server analyzes the received request using natural language processing technology and converts it into technical specifications. For example, it may be analyzed as a request to "create a multiplication program."
[1024] Step 5:
[1025] The server's AI module generates program code based on the analysis results, and adjusts the program's content and explanations according to the user's emotional state.
[1026] Step 6:
[1027] The generated program code is sent back to the terminal from the server, which sends the code in the appropriate format.
[1028] Step 7:
[1029] The terminal displays the received program code to the user, and the emotion engine continues to monitor the user's emotions and provide appropriate feedback.
[1030] Step 8:
[1031] The user checks the generated program code on the terminal and executes it by entering specific numbers, for example, 6 and 7.
[1032] Step 9:
[1033] The terminal runs a program based on the numbers you enter and displays the result, for example, 42.
[1034] Step 10:
[1035] The user can review the displayed results and take further action or input as needed, and the emotion engine provides additional feedback and assistance depending on the user's emotional state.
[1036] This series of processes allows the user to receive appropriate support tailored to their emotional state, while quickly and accurately generating and using the necessary programs.
[1037] Example 2
[1038] 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."
[1039] Conventional program generation systems are difficult to operate unless the user has programming knowledge, and they are unable to provide support tailored to the emotional state of each individual user. As a result, the increased effort and stress involved in creating programs has become a problem.
[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1041] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including an AI module for generating program code based on the request, means for returning the generated program code to the terminal, means for displaying the generated program code to the user and making it available for use, means for recognizing the user's emotional state, and means for adjusting processing in accordance with the recognized emotional state. This allows users to easily generate and use programs without specialized knowledge and receive support in accordance with their emotional state.
[1042] The "means for receiving a user's request in natural language" refers to a device or software that has the function of analyzing and acquiring a request in natural language input by a user.
[1043] The "means for sending a request to a server" refers to a device or software that has the function of sending a request entered by a user to a server via the Internet or other communication means.
[1044] A "server including an AI module for generating program code" is a server that has the function of automatically generating appropriate program code based on received requests using AI technology.
[1045] The "means for returning the generated program code to the terminal" refers to a device or software that has the function of transmitting the program code generated by the server to the user's terminal via the network.
[1046] "Means for displaying and making available the generated program code to the user" means a device or software that visually displays the received program code on a terminal and allows the user to operate and execute the program code.
[1047] "Means for recognizing the user's emotional state" refers to a device or software that has the function of analyzing and recognizing the user's emotional state from their facial expressions and voice.
[1048] The "means for adjusting processing in accordance with the recognized emotional state" refers to a device or software that has the function of dynamically adjusting the display content, processing speed, etc. based on the recognized emotional state of the user.
[1049] The present invention relates to a system that allows users to easily create and use programs without having programming knowledge. Furthermore, the system can improve the user experience by recognizing the user's emotions and providing programs and interfaces that correspond to that state. Specific embodiments of this system are described in detail below.
[1050] First, a user uses a device (e.g., a PC or smartphone) to input program specifications and function requirements in natural language. The device is equipped with a camera and microphone, which captures the user's facial expressions and voice. This data is then analyzed by an emotion engine (e.g., FaceAPI for facial expression recognition and Google Cloud Speech-to-Text for voice recognition) to recognize the user's emotional state in real time.
[1051] Next, the device sends the user's input request (e.g., "I want a program to multiply two numbers") and emotional data (relaxed, anxious, etc.) to the server. This data is formatted in JSON format and sent to the server via the Internet or other communication means.
[1052] The server analyzes the received JSON-formatted request and emotional data. It uses natural language processing (NLP) to analyze the request and automatically generate appropriate program code. This is done using a generative AI model (e.g., OpenAI's GPT-3). It also dynamically adjusts the content and difficulty of the generated program based on the recognized emotional state of the user. Specifically, it provides a program with detailed comments to a relaxed user, and concise, quickly executable code to a rushed user.
[1053] The generated program code is sent back from the server to the device. The device then displays the received program code to the user. Furthermore, the device's built-in emotion engine continuously monitors the user's emotions and can provide feedback or additional explanations according to the situation. The user can check the displayed program code and execute it by entering specific numbers. For example, if the user enters the numbers 6 and 7, the program will return the result 42.
[1054] As a concrete example, consider a user requesting a program to multiply two numbers. If the user is relaxed, the server's AI module will generate a multiplication program with detailed instructions and additional learning resources (e.g., links to documentation). On the other hand, if the user is impatient, the program will be displayed in a concise, quickly executable form.
[1055] Examples of prompts include:
[1056] "Generate a program that multiplies two numbers. The user is relaxed."
[1057] or
[1058] "Generate a program that multiplies two numbers. The user is in a hurry."
[1059] As described above, the system of the present invention not only converts user requests into program code quickly and accurately and provides the results to the user, but also recognizes emotions to improve the user experience, significantly reducing the effort and stress associated with conventional program creation. Furthermore, since it can be operated efficiently without requiring specialized knowledge, it can lower the barrier to program creation.
[1060] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1061] Step 1:
[1062] The user uses the terminal to enter a request in natural language.
[1063] Input: User request (e.g., "I want a program to multiply two numbers")
[1064] Specific actions: The user enters a request in natural language into an input field on the terminal.
[1065] Output: Request data captured by the device
[1066] Step 2:
[1067] The device captures the user's facial expression and voice data and sends it to the emotion engine.
[1068] Input: User's facial expressions and voice
[1069] Specific operation: The device's camera captures facial expressions and microphone captures voice. The emotion engine receives and analyzes this data.
[1070] Output: User's emotional state (e.g., relaxed, anxious)
[1071] Step 3:
[1072] The terminal transmits the request data and the emotional state information to the server.
[1073] Input: Request data and emotional state information
[1074] Specific operation: The device formats the request data and emotional state information into JSON format and sends it to the server via the network.
[1075] Output: JSON data received by the server
[1076] Step 4:
[1077] The request data received by the server is analyzed using natural language processing technology.
[1078] Input: Request data in JSON format
[1079] Specific operation: The request data is analyzed by a natural language processing engine (e.g., a generative AI model) on the server, and program code specifications are extracted according to the demand.
[1080] Output: Program specification based on parsed requirements
[1081] Step 5:
[1082] The server generates program code based on the analysis results and emotional state.
[1083] Input: Program specifications and user emotional state
[1084] How it works: The server's AI module generates program code based on the user's emotional state and the user's specifications. For a relaxed user, detailed comments are generated, while for a panicked user, concise code is generated.
[1085] Output: Generated program code
[1086] Step 6:
[1087] The server formats the generated program code into JSON format and returns it to the terminal.
[1088] Input: Generated program code
[1089] Specific operation: The server converts the program code into JSON format and sends it to the terminal via the network.
[1090] Output: Program code in JSON format received by the terminal
[1091] Step 7:
[1092] The terminal displays the received program code to the user.
[1093] Input: Program code in JSON format
[1094] What it does: The terminal displays the program code in a user-friendly format.
[1095] Output: The program code displayed to the user
[1096] Step 8:
[1097] The user inputs numbers using program code and gets a result.
[1098] Input: The numbers you enter (e.g. 6 and 7)
[1099] Specific operation: The user inputs numbers into the program code on the terminal and executes the program.
[1100] Output: Program execution result (e.g. 42)
[1101] As described above, the specific operations performed at each step, as well as the input and output of data, can be explained in detail. This clarifies the processing flow of the entire system and makes it easier to understand how program code is generated in response to user requests.
[1102] (Application example 2)
[1103] 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."
[1104] Conventional program generation systems often make it difficult for users without programming knowledge to generate programs, and often fail to provide appropriate support that takes into account the user's emotional state. This results in a poor user experience, and it is difficult to provide appropriate interfaces and explanations, especially for users who are anxious or relaxed. Furthermore, in content distribution services, it is difficult to appropriately recommend content that users want to watch, making it difficult to improve user satisfaction.
[1105] 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.
[1106] In this invention, the server includes means for receiving a user request in natural language, means for transmitting the request to the server, means including a generative AI model for generating program code based on the request, means for recognizing emotions by analyzing the user's facial expressions and voice, means for adjusting the generated program code according to the user's emotional state, means for returning the generated program code to the terminal, and means for displaying the generated program code to the user and making it available for use, thereby enabling appropriate program generation and content recommendation according to the user's emotional state.
[1107] A "user" is an entity that uses the system to generate programs and receive content recommendations.
[1108] "Natural language" is a language that humans use on a daily basis, not program code.
[1109] A "server" is a central computer system that receives and processes requests from users.
[1110] A "generative AI model" refers to a collection of algorithms that analyze user requests and automatically generate program code.
[1111] "Facial expressions" are physical facial movements and placements used to determine the emotions expressed by a user.
[1112] "Audio" or "voice" refers to the spoken voice of the user and is used as part of sentiment analysis.
[1113] "Emotion recognition" means determining the user's emotional state at that time from their facial expression and voice.
[1114] "Program code" means a set of instructions in a format that a computer can understand and execute.
[1115] A "terminal" is a device (such as a smartphone or computer) that is directly operated by a user.
[1116] "Adjusting" refers to processing the generated program code and related information appropriately to suit the user's emotional state.
[1117] "Display" means visually outputting information on the screen of a terminal.
[1118] "Available" means that the user can actually operate or execute the generated program code.
[1119] The present invention is a system that allows a user to input a request in natural language, recognizes emotions from facial expressions and voice, and generates appropriate programs and recommends content according to the user's state. This system is realized by an application installed on a device such as a smartphone, smart glasses, a head-mounted display, or a robot. The system configuration and operation are described in detail below.
[1120] Components
[1121] 1. Terminal
[1122] Hardware: Devices such as smartphones, smart glasses, head-mounted displays, or robots.
[1123] Software: Installed OpenCV, transformers NLP models, and emotion recognition software.
[1124] 2. Server
[1125] Generative AI models: Algorithms that analyze user requests in natural language and generate program code (e.g., transformers).
[1126] Emotion recognition engine: Recognizes the user's emotional state by analyzing their facial expressions and voice.
[1127] Operation flow
[1128] 1. User request input
[1129] A user uses a terminal to input a request for content to be viewed or a program to be executed in natural language.
[1130] For example, a user may enter, "I want to watch a relaxing documentary."
[1131] 2. Emotional Recognition
[1132] The device's camera and microphone are used to capture the user's facial expressions and voice, which are then analyzed by an emotion recognition engine.
[1133] As a result of the analysis, the emotional state of the user, such as whether they are relaxed or anxious, is determined.
[1134] 3. Program Creation and Recommendation
[1135] The server uses a generative AI model to recommend appropriate program code and content based on the user's request and emotional state.
[1136] For example, in response to a request to "watch a documentary that will help me relax," documentary videos that are suitable for a relaxed state are recommended.
[1137] 4. Display and Use of Results
[1138] The generated program code and content recommendations are sent back to the terminal and displayed to the user.
[1139] The user checks the displayed information and starts viewing or playing as needed.
[1140] Specific examples
[1141] User Request: "I want to watch an uplifting music video."
[1142] Example prompt sentence:
[1143] User wants: Wants to watch an uplifting music video. User is feeling: Feeling anxious. Recommend an appropriate video.
[1144] System response: Recognizes when the user is in a state of agitation and immediately recommends energetic music videos.
[1145] A feature of the present invention is that appropriate content is recommended according to the user's emotional state, even if the user does not have any special programming knowledge, thereby improving the user experience and satisfying requests efficiently and quickly.
[1146] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1147] Step 1:
[1148] User request input
[1149] The user uses the terminal to input a request for the content they want to view or the program they want to run in natural language. In this case, the user enters text such as "I want to watch a relaxing documentary" into the input field. This text information is entered into the terminal, and the data is passed to the next processing step.
[1150] Step 2:
[1151] Emotion recognition
[1152] The device's camera and microphone are used to simultaneously capture the user's facial expressions and voice. The captured video and audio data are input into an emotion recognition engine. The emotion recognition engine (e.g., EmotionRecognizer) processes this data and determines the user's emotional state (relaxed, anxious, etc.). This emotional state information is sent to a server and input into a generative AI model.
[1153] Step 3:
[1154] Program Generation and Recommendations
[1155] The generative AI model installed on the server receives the user's request text (input in step 1) and emotional state (output in step 2) as input. The generative AI model analyzes this data using natural language processing (NLP) technology and recommends appropriate program code and content. For example, if the request text is "relaxing documentaries" and the emotional state is determined to be "relaxing," a list of documentary videos that can be enjoyed in a relaxed state will be generated. This list becomes the output of program generation and recommendations.
[1156] Step 4:
[1157] Displaying and Using the Results
[1158] The server returns the generated program code and a list of content recommendations to the device. The returned data is input into the device and visually displayed to the user. The user selects the documentary they want to watch from the displayed list and presses the play button to begin watching the video. All of this is done on the device, allowing users to easily consume content.
[1159] 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.
[1160] 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.
[1161] 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.
[1162] 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.
[1163] 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.
[1164] 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.
[1165] 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).
[1166] 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.
[1167] 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."
[1168] 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.
[1169] 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).
[1170] 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.
[1171] 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.
[1172] 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.
[1173] 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.
[1174] 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.
[1175] 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.
[1176] 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.
[1177] 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.
[1178] 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.
[1179] 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.
[1180] The following is further disclosed regarding the above embodiment.
[1181] (Claim 1)
[1182] a means for receiving a user request in natural language;
[1183] means for sending the request to a server;
[1184] a server including an AI module that generates program code based on the request;
[1185] means for returning the generated program code to a terminal;
[1186] means for displaying and making available the generated program code to a user;
[1187] A system including:
[1188] (Claim 2)
[1189] means for analyzing the user's request using natural language processing technology;
[1190] means for generating program code based on the parsed requirements;
[1191] The system of claim 1 further comprising:
[1192] (Claim 3)
[1193] 10. The system of claim 1, wherein the generated program code includes a calculation program that operates based on a numerical value entered by a user.
[1194] "Example 1"
[1195] (Claim 1)
[1196] a means for receiving a user request in natural language;
[1197] means for sending the request to a server;
[1198] a server including an artificial intelligence module that generates program code based on the request;
[1199] means for returning the generated program code to a terminal;
[1200] means for displaying and making available the generated program code to a user;
[1201] A system including:
[1202] (Claim 2)
[1203] means for analyzing the user's request using natural language processing technology;
[1204] means for generating program code based on the parsed requirements;
[1205] The generated program code is generated in a programming language appropriate for the application;
[1206] 10. The system of claim 1, comprising:
[1207] (Claim 3)
[1208] 10. The system of claim 1, wherein the generated program code includes a calculation program that operates based on a numerical value entered by a user.
[1209] "Application Example 1"
[1210] (Claim 1)
[1211] a means for receiving a user request in natural language;
[1212] means for sending the request to a server;
[1213] a server including an artificial intelligence module that generates program code based on the request;
[1214] means for returning the generated program code to a terminal;
[1215] means for displaying and making available the generated program code to a user;
[1216] A means to automatically generate programs for product searches and customized orders,
[1217] A means for searching for a product based on the generated program code;
[1218] A way to display search results to users and make them available for immediate purchase;
[1219] A system including:
[1220] (Claim 2)
[1221] means for analyzing the user's request using natural language processing technology;
[1222] means for generating program code based on the parsed requirements;
[1223] a means for searching for products from a database based on the generated program code;
[1224] The system of claim 1 further comprising:
[1225] (Claim 3)
[1226] 2. The system of claim 1, wherein the generated program code includes a search program for product searches and customized ordering.
[1227] "Example 2: Combining Emotion Engines"
[1228] (Claim 1)
[1229] a means for receiving a user request in natural language;
[1230] means for sending the request to a server;
[1231] a server including an AI module that generates program code based on the request;
[1232] means for returning the generated program code to a terminal;
[1233] means for displaying and making available the generated program code to a user;
[1234] means for recognizing the emotional state of a user;
[1235] a means for adjusting processing in response to the perceived emotional state;
[1236] A system including:
[1237] (Claim 2)
[1238] means for analyzing the user's request using natural language processing technology;
[1239] means for generating program code based on the parsed requirements;
[1240] The program code may further include a means for adjusting the content and difficulty of the program code based on the emotional state of the user.
[1241] 10. The system of claim 1.
[1242] (Claim 3)
[1243] The generated program code includes a calculation program that operates based on a numerical value input by a user.
[1244] 10. The system of claim 1.
[1245] "Application example 2 when combining emotion engines"
[1246] (Claim 1)
[1247] a means for receiving a user request in natural language;
[1248] means for sending the request to a server;
[1249] a server including a generative AI model that generates program code based on the request;
[1250] A means for recognizing emotions by analyzing the user's facial expressions and voice;
[1251] means for adjusting the generated program code in response to the emotional state of a user;
[1252] means for returning the generated program code to a terminal;
[1253] means for displaying and making available the generated program code to a user;
[1254] A system including:
[1255] (Claim 2)
[1256] means for analyzing the user's request using natural language processing technology;
[1257] means for generating program code based on the parsed requirements;
[1258] means for adjusting the content and difficulty of the program code based on the emotional state of the user;
[1259] The system of claim 1 further comprising:
[1260] (Claim 3)
[1261] 10. The system of claim 1, wherein the generated program code includes a calculation program that operates based on a numerical value entered by a user. [Explanation of symbols]
[1262] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>
Claims
1. a means for receiving a user request in natural language; means for sending the request to a server; a server including an AI module that generates program code based on the request; means for returning the generated program code to a terminal; means for displaying and making available the generated program code to a user; A system including:
2. means for analyzing the user's request using natural language processing technology; means for generating program code based on the parsed requirements; The system of claim 1 further comprising:
3. 2. The system of claim 1, wherein the generated program code includes a calculation program that operates based on a numerical value entered by a user.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A