system

Abstract

The system according to this embodiment aims to quickly reflect user requests and efficiently modify applications and add new functions. [Solution] A system according to an embodiment includes a request receiving unit, an approval unit, a generation unit, and a utilization unit. The request receiving unit receives a user's request. The approval unit approves the request received by the request receiving unit. The generation unit analyzes the request approved by the approval unit and generates program code. The utilization unit provides the user with the program code generated by the generation unit.

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] Conventional technologies have made it difficult to quickly modify applications or add new features to reflect user requests, placing a heavy burden on developers.

[0005] The system according to this embodiment aims to quickly reflect user requests and efficiently modify applications and add new functions. [Means for solving the problem]

[0006] The system according to this embodiment comprises a request receiving unit, an approval unit, a generation unit, and a utilization unit. The request receiving unit receives requests from users. The approval unit approves the requests received by the request receiving unit. The generation unit analyzes the requests approved by the approval unit and generates program code. The utilization unit provides the program code generated by the generation unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can quickly reflect user requests and efficiently modify applications and add functions. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The matching system according to an embodiment of the present invention is a system that matches users who want to improve an application with application developers. In this matching system, when a user submits a request for an application and the content of the request is approved, a generating AI analyzes the request and generates program code, allowing the user to modify or add functions to the service themselves. This makes it easy for even beginners to add functions. Developers can have functions developed that meet the user's needs, reducing development time. For example, a user submits a request to add a specific function or improve an existing function. This request is entered into the request reception unit. Next, the approval unit approves the user's request. The approved request is sent to the generating AI, which analyzes the request and generates program code. The generating AI automatically generates the necessary program code based on the user's request. For example, it generates code to add a specific function or code to improve an existing function. The generated program code is provided to the user through the utilization unit. The user uses the code generated by the generating AI to modify the application or add functions. This makes it easy for even beginners to add functions. Developers can have functions developed that meet the user's needs, reducing development time. For example, if a user requests the addition of a specific feature, the generation AI can generate the code to add that feature, and the user can then use that code to add the feature, saving the developer the effort of developing it themselves. This mechanism allows users to improve the application based on their requests, and developers can efficiently develop features that meet user needs. For example, if a user requests the addition of a new feature, the generation AI can generate the code to add that feature, and the user can then use that code to add the feature, saving the developer the effort of developing it themselves. This enables the matching system to efficiently receive, approve, analyze, generate, and provide user requests.

[0029] A matching system according to an embodiment includes a request receiving unit, an approval unit, a generation unit, and a utilization unit. The request receiving unit provides an interface through which a user submits a request for an app. Examples of interfaces through which a user submits a request for an app include, but are not limited to, a web interface and a mobile app interface. For example, the request receiving unit allows a user to input a request through the web interface. The request receiving unit can also allow a user to submit a request through the mobile app interface. Furthermore, the request receiving unit provides a voice input interface, allowing a user to submit a request by voice. For example, the request receiving unit converts a user's voice into text using voice recognition technology and accepts the text as a request. The approval unit sets criteria for approving a user's request and approves the request based on the criteria. The approval unit evaluates and approves the request based on criteria such as the importance, urgency, and technical feasibility of the request. The approval unit can also evaluate the request using AI. For example, the approval unit evaluates the importance and urgency of the request using an AI model and determines whether to approve the request. The generation unit generates program code based on the user's request using a generation AI. The generation unit generates program code using, for example, machine learning models or natural language processing technology. The generation AI analyzes user requests and automatically generates the necessary program code. For example, the generation AI generates code for adding specific functions or code for improving existing functions. Some or all of the above-mentioned processes in the generation unit are performed using the generation AI. The utilization unit provides the generated program code to the user and provides support for the user to use the code to modify or add functions to an application. The utilization unit provides the generated program code to the user, for example, through a web interface or a mobile app interface. The utilization unit can also send the generated program code to the user by email. Furthermore, the utilization unit provides technical support when the user uses the generated program code to modify or add functions to an application.For example, the utilization unit provides a user guide and FAQs to support the user in using the generated program code, which enables the matching system according to the embodiment to efficiently accept, approve, analyze, generate, and provide user requests.

[0030] The request receiving unit may provide an interface through which a user submits a request for the app. The request receiving unit may provide, for example, a web interface, allowing the user to input the request. For example, the request receiving unit may provide a form through which the user inputs the request via a web browser. The request receiving unit may also provide a mobile app interface, allowing the user to submit the request using a smartphone or tablet. For example, the request receiving unit may provide a screen through which the user inputs the request via the mobile app. The request receiving unit may also provide a voice input interface, allowing the user to submit the request by voice. For example, the request receiving unit may convert the user's voice into text using voice recognition technology and accept the text as a request. This allows the user to easily submit a request. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without AI. For example, the request receiving unit may perform voice recognition using an AI model when converting the user's voice into text using voice recognition technology.

[0031] The approval unit can set criteria for approving user requests and approve the requests based on those criteria. The approval unit evaluates and approves the requests based on criteria such as the importance, urgency, and technical feasibility of the request. For example, the approval unit evaluates the impact of the request on the functionality of the application to evaluate the importance of the request. Furthermore, the approval unit evaluates how important the request is to the user to evaluate the urgency of the request. Furthermore, the approval unit evaluates whether the request is technically feasible to evaluate technical feasibility. The approval unit can also use AI to evaluate the requests. For example, the approval unit uses an AI model to evaluate the importance and urgency of the request and decides whether to approve it. This streamlines the request approval process. Some or all of the above-mentioned processing in the approval unit may be performed using AI, or may be performed without using AI. For example, when evaluating the requests using an AI model, the approval unit can use a machine learning algorithm to evaluate the importance and urgency of the request.

[0032] The generation unit can generate program code based on a user's request using a generation AI. The generation unit generates the program code using, for example, a machine learning model or natural language processing technology. The generation AI analyzes the user's request and automatically generates the necessary program code. For example, the generation AI generates code for adding a specific function or code for improving an existing function. Some or all of the above-described processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's request into the generation AI, and the generation AI generates program code based on the request. The generation AI analyzes the user's request using, for example, natural language processing technology and generates program code. The generation AI can also generate program code based on the user's request using a machine learning model. This automatically generates program code based on the user's request. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, when generating program code using a generation AI, the generation unit can generate the program code using a machine learning algorithm.

[0033] The User Unit can provide the user with the generated program code and support the user in modifying or adding features to the application using that code. For example, the User Unit can provide the generated program code to the user through a web interface or a mobile app interface. For instance, the User Unit can provide a link to download the generated program code via a web browser. Alternatively, the User Unit can provide a screen through a mobile app where the user can obtain the generated program code. Furthermore, the User Unit can send the generated program code to the user via email. For example, the User Unit can send the generated program code as an attachment to the user's email address. The User Unit also provides technical support when the user modifies or adds features to the application using the generated program code. For example, the User Unit can provide a user guide and FAQs to support the user in using the generated program code. This enables the user to modify or add features to the application using the generated program code. Some or all of the above-described processes in the User Unit may be performed using AI or not. For example, the User Unit can use AI to generate answers to user questions and provide technical support.

[0034] The request reception department can analyze a user's past request submission history and select the optimal submission method. For example, the request reception department can prioritize suggesting submission methods (such as voice or text) that the user has frequently used in the past. For example, the request reception department can analyze a user's past request submission history, identify the submission method the user has used most often in the past, and prioritize suggesting that method. The request reception department can also suggest the optimal submission method for a specific time period based on the user's past request submission history. For example, the request reception department can analyze a user's history of submitting requests at a specific time period and suggest the optimal submission method for that time period. Furthermore, the request reception department can analyze the content of requests the user has submitted in the past and make it easy for the user to submit similar requests. For example, the request reception department can analyze the content of requests the user has submitted in the past, provide similar requests as templates, and make it easy for the user to submit requests. This allows the optimal submission method to be selected based on the user's past history. Some or all of the above processes in the request reception department may be performed using AI or not. For example, the request reception department can use AI to analyze a user's past request submission history and select the optimal submission method based on the results.

[0035] The request receiving department can filter requests based on the user's current projects and areas of interest when they are submitted. For example, the request receiving department can prioritize requests related to the user's current projects. For example, the request receiving department can analyze the content of the user's current projects and prioritize requests related to those projects. The request receiving department can also filter relevant requests based on the user's areas of interest and encourage their submission. For example, the request receiving department can analyze the user's areas of interest and prioritize requests related to those areas. Furthermore, the request receiving department can also prioritize highly relevant requests by referring to the user's past project history. For example, the request receiving department can analyze the user's past project history and prioritize requests related to projects they have worked on in the past. This allows for filtering requests based on the user's current projects and areas of interest. Some or all of the above processing in the request receiving department may be performed using AI or not. For example, the request receiving department can use AI to analyze the user's projects and areas of interest and filter requests based on the results.

[0036] When a request is submitted, the request receiving unit can prioritize accepting highly relevant requests by taking into account the user's geographical location information. For example, if the user is in a specific area, the request receiving unit prioritizes accepting requests related to that area. For example, if the request receiving unit determines that the user is in a specific area, it prioritizes accepting requests related to that area. The request receiving unit can also prioritize processing requests related to locations close to the user's current location. For example, the request receiving unit prioritizes processing requests related to locations close to the user's current location. Furthermore, the request receiving unit can also prioritize accepting requests specific to a specific area based on the user's geographical location information. For example, the request receiving unit prioritizes accepting requests specific to a specific area based on the user's geographical location information. This allows requests to be prioritized based on the user's geographical location information. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without using AI. For example, the request receiving unit can analyze the user's geographical location information using AI and prioritize accepting requests based on the results.

[0037] The request receiving unit can analyze the user's social media activity when the request is submitted and receive related requests. The request receiving unit, for example, prioritizes receiving related requests based on content mentioned by the user on social media. For example, the request receiving unit analyzes content mentioned by the user on social media and prioritizes receiving requests related to the content. The request receiving unit can also prioritize processing requests related to topics of high interest from the user's social media activity. For example, the request receiving unit analyzes the user's social media activity and prioritizes processing requests related to topics of high interest. Furthermore, the request receiving unit can analyze the user's feedback on social media and receive related requests. For example, the request receiving unit analyzes the user's feedback on social media and receives requests related to the feedback. This makes it possible to receive related requests based on the user's social media activity. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without using AI. For example, the request receiving unit can analyze the user's social media activity using AI and receive related requests based on the results.

[0038] The approval department can adjust the level of detail in the approval process based on the importance of the request. For example, the approval department can conduct a detailed review of high-priority requests to improve the accuracy of the approval. For example, the approval department can evaluate the importance of requests and conduct a detailed review of high-priority requests. Alternatively, the approval department can conduct a simpler review of low-priority requests and approve them quickly. For example, the approval department can evaluate the importance of requests and conduct a simpler review of low-priority requests. Furthermore, the approval department can adjust the number of steps in the approval process according to the importance of the request. For example, the approval department can conduct a detailed review through multiple steps for high-priority requests and approve low-priority requests quickly with fewer steps. This allows the level of detail in the approval process to be adjusted based on the importance of the request. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to evaluate the importance of requests and adjust the level of detail in the approval process based on the results.

[0039] The approval department can apply different approval algorithms depending on the category of the request during the approval process. For example, for requests to add new features, the approval department can apply an algorithm that conducts a detailed technical review. For example, for requests to add new features, the approval department can apply an algorithm that evaluates the technical feasibility and scope of impact in detail. The approval department can also apply an algorithm that emphasizes user feedback for requests to improve existing features. For example, for requests to improve existing features, the approval department can apply an algorithm that evaluates them with an emphasis on user feedback and usage. Furthermore, the approval department can apply an algorithm that ensures a rapid response for requests to fix bugs. For example, for requests to fix bugs, the approval department can apply an algorithm that quickly identifies the problem and determines whether it can be fixed. This allows for the application of different approval algorithms depending on the category of the request. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to classify the categories of requests and apply an appropriate approval algorithm based on the results.

[0040] At the time of approval, the approval unit can determine the priority of approval based on the time of submission of the request. The approval unit can determine the priority based on, for example, the time of day when the request is submitted. For example, the approval unit can analyze the time of day when the request is submitted and prioritize approval of requests submitted during that time of day. The approval unit can also determine the priority based on the day of the week when the request is submitted. For example, the approval unit can analyze the day of the week when the request is submitted and prioritize approval of requests submitted on that day. The approval unit can also determine the priority based on the season when the request is submitted. For example, the approval unit can analyze the season when the request is submitted and prioritize approval of requests submitted during that season. In this way, the priority of approval can be determined based on the time of submission of the request. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without using AI. For example, the approval unit can analyze the time of submission of the request using AI and determine the priority of approval based on the results.

[0041] The approval unit can adjust the approval order based on the relevance of requests during approval. For example, the approval unit prioritizes approval of requests that are highly relevant to other requests. For example, if the approval unit determines that a request is highly relevant to other requests, it prioritizes approval of the request. Furthermore, if a request is related to a specific project, the approval unit can approve it based on the progress of the project. For example, if the approval unit determines that a request is related to a specific project, it approves it based on the progress of the project. Furthermore, if a request is related to a specific function, the approval unit can approve it based on the importance of the function. For example, if the approval unit determines that a request is related to a specific function, it approves it based on the importance of the function. This allows the approval order to be adjusted based on the relevance of requests. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without using AI. For example, the approval unit can analyze the relevance of requests using AI and adjust the approval order based on the results.

[0042] When generating program code, the generation unit can adjust the level of detail of the generated program code based on the importance of the request. For example, the generation unit generates detailed program code for requests with high importance. For example, the generation unit evaluates the importance of the request and generates detailed program code for requests with high importance. The generation unit can also generate concise program code for requests with low importance. For example, the generation unit evaluates the importance of the request and generates concise program code for requests with low importance. Furthermore, the generation unit can adjust comments and explanations in the program code based on the importance of the request. For example, the generation unit evaluates the importance of the request and generates program code including detailed comments and explanations for requests with high importance, and generates program code including concise comments and explanations for requests with low importance. This allows the level of detail of the generated program code to be adjusted based on the importance of the request. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can evaluate the importance of the request using a generation AI and adjust the level of detail of the generated program code based on the evaluation result.

[0043] When generating program code, the generation unit can apply different generation algorithms depending on the category of the request. For example, for a request to add a new function, the generation unit applies an algorithm that performs a detailed technical review. For example, for a request to add a new function, the generation unit applies an algorithm that performs a detailed evaluation of the technical feasibility and the scope of impact. The generation unit can also apply an algorithm that emphasizes user feedback to a request to improve an existing function. For example, for a request to improve an existing function, the generation unit applies an algorithm that emphasizes user feedback and usage status in evaluation. Furthermore, the generation unit can also apply an algorithm that provides a rapid response to a request to fix a bug. For example, for a request to fix a bug, the generation unit applies an algorithm that quickly identifies the problem and determines whether the fix is ​​possible. This allows the optimal generation algorithm to be applied depending on the category of the request. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can classify the category of the request using a generation AI and apply an appropriate generation algorithm based on the results.

[0044] The generation unit can determine the generation priority based on the timing of requests when generating program code. For example, the generation unit can determine the generation priority based on the time of day the requests were submitted. For example, the generation unit can analyze the time of day the requests were submitted and prioritize the generation of requests submitted during that time. The generation unit can also determine the generation priority based on the day of the week the requests were submitted. For example, the generation unit can analyze the day of the week the requests were submitted and prioritize the generation of requests submitted on that day. Furthermore, the generation unit can also determine the generation priority based on the season in which the requests were submitted. For example, the generation unit can analyze the season in which the requests were submitted and prioritize the generation of requests submitted during that season. This allows the generation priority to be determined based on the timing of the requests. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can use a generation AI to analyze the timing of requests and determine the generation priority based on the results.

[0045] The generation unit can adjust the generation order based on the relevance of requests when generating program code. For example, if a request is highly relevant to other requests, the generation unit will prioritize its generation. For example, if the generation unit determines that a request is highly relevant to other requests, it will prioritize the generation of that request. The generation unit can also generate requests according to the progress of a specific project if the request is related to that project. For example, if the generation unit determines that a request is related to a specific project, it will generate the request according to the progress of that project. Furthermore, if a request is related to a specific function, the generation unit can generate the request according to the importance of that function. For example, if the generation unit determines that a request is related to a specific function, it will generate the request according to the importance of that function. This allows the generation order to be adjusted based on the relevance of requests. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can use a generation AI to analyze the relevance of requests and adjust the generation order based on the results.

[0046] When providing program code, the utilization unit can select the optimal delivery method by referring to the user's past usage history. For example, the utilization unit prioritizes proposing delivery methods (email, download link, etc.) that the user has used in the past. For example, the utilization unit analyzes the user's past usage history, identifies the delivery method that the user has used most frequently, and prioritizes proposing that method. The utilization unit can also propose the optimal delivery method for a specific time period based on the user's past usage history. For example, the utilization unit analyzes the user's past usage history and proposes the optimal delivery method for a specific time period. Furthermore, the utilization unit can select the optimal delivery method based on the format of the program code that the user has used in the past (source code, binary, etc.). For example, the utilization unit analyzes the user's past usage history, identifies the format of the program code that the user has used in the past, and selects the optimal delivery method based on that format. This allows the optimal delivery method to be selected based on the user's past usage history. Some or all of the above-described processing in the utilization unit may be performed using AI, or may be performed without AI. For example, the utilization unit can analyze the user's past usage history using AI and select the optimal delivery method based on the results.

[0047] When providing program code, the utilization unit can customize the provided content based on the user's current project or area of ​​interest. For example, the utilization unit can prioritize providing program code related to the project the user is currently working on. For example, the utilization unit can analyze the content of the project the user is currently working on and prioritize providing program code related to that project. The utilization unit can also customize and provide related program code based on the user's area of ​​interest. For example, the utilization unit can analyze the user's area of ​​interest and customize and provide program code related to that area. Furthermore, the utilization unit can provide highly relevant program code by referring to the user's past project history. For example, the utilization unit can analyze the user's past project history and prioritize providing program code related to projects the user worked on in the past. This allows the provided content to be customized based on the user's current project or area of ​​interest. Some or all of the above-mentioned processing in the utilization unit may be performed using AI or without AI. For example, the utilization unit can analyze the user's project or area of ​​interest using AI and customize the provided content based on the results.

[0048] When providing program code, the utilization unit can select the optimal delivery method by taking into account the user's geographical location information. For example, if the user is in a specific region, the utilization unit prioritizes providing program code related to that region. For example, if the utilization unit determines that the user is in a specific region, the utilization unit prioritizes providing program code related to that region. The utilization unit can also prioritize providing program code related to locations close to the user's current location. For example, the utilization unit prioritizes providing program code related to locations close to the user's current location. Furthermore, the utilization unit can also prioritize providing region-specific program code based on the user's geographical location information. For example, the utilization unit prioritizes providing region-specific program code based on the user's geographical location information. This allows the optimal delivery method to be selected based on the user's geographical location information. Some or all of the above-described processing in the utilization unit may be performed using AI, or may be performed without AI. For example, the utilization unit can analyze the user's geographical location information using AI and select the optimal delivery method based on the results.

[0049] The user unit can analyze the user's social media activity and customize the content provided when delivering program code. For example, the user unit can prioritize providing relevant program code based on what the user has mentioned on social media. For example, the user unit can analyze what the user has mentioned on social media and prioritize providing program code related to that content. The user unit can also customize and provide program code related to topics of high interest based on the user's social media activity. For example, the user unit can analyze the user's social media activity and customize and provide program code related to topics of high interest. Furthermore, the user unit can analyze the user's feedback on social media and provide relevant program code. For example, the user unit can analyze the user's feedback on social media and provide program code related to that feedback. This allows the content provided to be customized based on the user's social media activity. Some or all of the above processing in the user unit may be performed using AI or not. For example, the user unit can use AI to analyze the user's social media activity and customize the content provided based on the results.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The request reception department can analyze a user's past request submission history and select the most suitable submission method. For example, it can prioritize suggesting submission methods that the user has frequently used in the past (such as voice or text). The request reception department can also suggest the most suitable submission method for a specific time period based on the user's past request submission history. Furthermore, the request reception department can analyze the content of requests previously submitted by the user and make it easier to submit similar requests. This allows for the selection of the most suitable submission method based on the user's past history.

[0052] The request reception system can filter requests based on the user's current projects and areas of interest. For example, it can prioritize requests related to projects the user is currently working on. The request reception system can also filter relevant requests based on the user's areas of interest and encourage their submission. Furthermore, the request reception system can prioritize highly relevant requests by referring to the user's past project history. This allows for filtering requests based on the user's current projects and areas of interest.

[0053] The request reception department can prioritize requests based on the user's geographical location when they are submitted. For example, if a user is in a specific region, requests related to that region will be prioritized. The request reception department can also prioritize requests related to locations close to the user's current location. Furthermore, the request reception department can prioritize requests specific to a region based on the user's geographical location. This allows for priority processing of requests based on the user's geographical location.

[0054] The approval department can adjust the level of detail in the approval process based on the importance of the request. For example, high-priority requests will undergo a more detailed review to improve the accuracy of the approval. Conversely, low-priority requests can undergo a simpler review and be approved more quickly. Furthermore, the approval department can adjust the number of steps in the approval process according to the importance of the request. This allows for adjustment of the level of detail in the approval process based on the importance of the request.

[0055] When generating program code, the generation unit can apply different generation algorithms depending on the category of request. For example, for a request to add a new function, the generation unit can apply an algorithm that performs detailed technical review. For a request to improve an existing function, the generation unit can also apply an algorithm that emphasizes user feedback. Furthermore, for a request to fix a bug, the generation unit can also apply an algorithm that provides a quick response. This makes it possible to apply the optimal generation algorithm depending on the category of request.

[0056] When providing program code, the utilization unit can select the optimal delivery method by referring to the user's past usage history. For example, it can preferentially suggest delivery methods (email, download link, etc.) that the user has used in the past. The utilization unit can also suggest the optimal delivery method for a specific time period based on the user's past usage history. Furthermore, the utilization unit can select the optimal delivery method based on the format of the program code that the user has used in the past (source code, binary, etc.). This allows the optimal delivery method to be selected based on the user's past usage history.

[0057] When providing the program code, the utilization unit can analyze the user's social media activity and customize the provided content. For example, the utilization unit can prioritize providing related program code based on what the user has mentioned on social media. The utilization unit can also customize and provide program code related to topics of high interest to the user based on the user's social media activity. Furthermore, the utilization unit can analyze the user's feedback on social media and provide related program code. This allows the provided content to be customized based on the user's social media activity.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The request submission department provides an interface for users to submit requests for the app. Users can submit requests through a web interface, a mobile app interface, or a voice input interface. For example, speech recognition technology can be used to convert the user's voice into text and accept it as a request. Step 2: The approval department sets criteria for approving user requests and approves them based on those criteria. For example, requests are evaluated and approved based on criteria such as the importance and urgency of the request, and technical feasibility. Requests can also be evaluated using AI. Step 3: The generator uses a generation AI to generate program code based on the user's requests. For example, it generates program code using machine learning models or natural language processing techniques, generating code to add specific functions or improve existing functions. Step 4: The user unit provides the generated program code to the user and offers support for the user to modify the application or add features using that code. For example, the generated program code can be provided through a web interface or mobile app interface, or sent via email. The user unit also provides user guides and FAQs, and offers technical support.

[0060] (Example 2) The matching system according to an embodiment of the present invention is a system that matches users who want to improve an application with application developers. In this matching system, when a user submits a request for an application and the content of the request is approved, a generating AI analyzes the request and generates program code, allowing the user to modify or add functions to the service themselves. This makes it easy for even beginners to add functions. Developers can have functions developed that meet the user's needs, reducing development time. For example, a user submits a request to add a specific function or improve an existing function. This request is entered into the request reception unit. Next, the approval unit approves the user's request. The approved request is sent to the generating AI, which analyzes the request and generates program code. The generating AI automatically generates the necessary program code based on the user's request. For example, it generates code to add a specific function or code to improve an existing function. The generated program code is provided to the user through the utilization unit. The user uses the code generated by the generating AI to modify the application or add functions. This makes it easy for even beginners to add functions. Developers can have functions developed that meet the user's needs, reducing development time. For example, if a user requests the addition of a specific feature, the generation AI can generate the code to add that feature, and the user can then use that code to add the feature, saving the developer the effort of developing it themselves. This mechanism allows users to improve the application based on their requests, and developers can efficiently develop features that meet user needs. For example, if a user requests the addition of a new feature, the generation AI can generate the code to add that feature, and the user can then use that code to add the feature, saving the developer the effort of developing it themselves. This enables the matching system to efficiently receive, approve, analyze, generate, and provide user requests.

[0061] A matching system according to an embodiment includes a request receiving unit, an approval unit, a generation unit, and a utilization unit. The request receiving unit provides an interface through which a user submits a request for an app. Examples of interfaces through which a user submits a request for an app include, but are not limited to, a web interface and a mobile app interface. For example, the request receiving unit allows a user to input a request through the web interface. The request receiving unit can also allow a user to submit a request through the mobile app interface. Furthermore, the request receiving unit provides a voice input interface, allowing a user to submit a request by voice. For example, the request receiving unit converts a user's voice into text using voice recognition technology and accepts the text as a request. The approval unit sets criteria for approving a user's request and approves the request based on the criteria. The approval unit evaluates and approves the request based on criteria such as the importance, urgency, and technical feasibility of the request. The approval unit can also evaluate the request using AI. For example, the approval unit evaluates the importance and urgency of the request using an AI model and determines whether to approve the request. The generation unit generates program code based on the user's request using a generation AI. The generation unit generates program code using, for example, machine learning models or natural language processing technology. The generation AI analyzes user requests and automatically generates the necessary program code. For example, the generation AI generates code for adding specific functions or code for improving existing functions. Some or all of the above-mentioned processes in the generation unit are performed using the generation AI. The utilization unit provides the generated program code to the user and provides support for the user to use the code to modify or add functions to an application. The utilization unit provides the generated program code to the user, for example, through a web interface or a mobile app interface. The utilization unit can also send the generated program code to the user by email. Furthermore, the utilization unit provides technical support when the user uses the generated program code to modify or add functions to an application.For example, the utilization unit provides a user guide and FAQs to support the user in using the generated program code, which enables the matching system according to the embodiment to efficiently accept, approve, analyze, generate, and provide user requests.

[0062] The request receiving unit may provide an interface through which a user submits a request for the app. The request receiving unit may provide, for example, a web interface, allowing the user to input the request. For example, the request receiving unit may provide a form through which the user inputs the request via a web browser. The request receiving unit may also provide a mobile app interface, allowing the user to submit the request using a smartphone or tablet. For example, the request receiving unit may provide a screen through which the user inputs the request via the mobile app. The request receiving unit may also provide a voice input interface, allowing the user to submit the request by voice. For example, the request receiving unit may convert the user's voice into text using voice recognition technology and accept the text as a request. This allows the user to easily submit a request. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without AI. For example, the request receiving unit may perform voice recognition using an AI model when converting the user's voice into text using voice recognition technology.

[0063] The approval unit can set criteria for approving user requests and approve the requests based on those criteria. The approval unit evaluates and approves the requests based on criteria such as the importance, urgency, and technical feasibility of the request. For example, the approval unit evaluates the impact of the request on the functionality of the application to evaluate the importance of the request. Furthermore, the approval unit evaluates how important the request is to the user to evaluate the urgency of the request. Furthermore, the approval unit evaluates whether the request is technically feasible to evaluate technical feasibility. The approval unit can also use AI to evaluate the requests. For example, the approval unit uses an AI model to evaluate the importance and urgency of the request and decides whether to approve it. This streamlines the request approval process. Some or all of the above-mentioned processing in the approval unit may be performed using AI, or may be performed without using AI. For example, when evaluating the requests using an AI model, the approval unit can use a machine learning algorithm to evaluate the importance and urgency of the request.

[0064] The generation unit can generate program code based on a user's request using a generation AI. The generation unit generates the program code using, for example, a machine learning model or natural language processing technology. The generation AI analyzes the user's request and automatically generates the necessary program code. For example, the generation AI generates code for adding a specific function or code for improving an existing function. Some or all of the above-described processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's request into the generation AI, and the generation AI generates program code based on the request. The generation AI analyzes the user's request using, for example, natural language processing technology and generates program code. The generation AI can also generate program code based on the user's request using a machine learning model. This automatically generates program code based on the user's request. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, when generating program code using a generation AI, the generation unit can generate the program code using a machine learning algorithm.

[0065] The User Unit can provide the user with the generated program code and support the user in modifying or adding features to the application using that code. For example, the User Unit can provide the generated program code to the user through a web interface or a mobile app interface. For instance, the User Unit can provide a link to download the generated program code via a web browser. Alternatively, the User Unit can provide a screen through a mobile app where the user can obtain the generated program code. Furthermore, the User Unit can send the generated program code to the user via email. For example, the User Unit can send the generated program code as an attachment to the user's email address. The User Unit also provides technical support when the user modifies or adds features to the application using the generated program code. For example, the User Unit can provide a user guide and FAQs to support the user in using the generated program code. This enables the user to modify or add features to the application using the generated program code. Some or all of the above-described processes in the User Unit may be performed using AI or not. For example, the User Unit can use AI to generate answers to user questions and provide technical support.

[0066] The request receiving unit can estimate a user's emotions and adjust the timing of request submission based on the estimated user emotions. For example, if the user is feeling stressed, the request receiving unit can simplify the request submission interface to allow the user to submit the request quickly. For example, if the request receiving unit estimates that the user is feeling stressed, it can reduce the number of input items in the request submission form to allow the user to submit the request with simple input. Furthermore, if the user is relaxed, the request receiving unit can provide more detailed input options to increase the specificity of the request. For example, if the request receiving unit estimates that the user is relaxed, it can add more detailed input items to the request submission form to allow the user to submit a specific request. Furthermore, if the user is in a hurry, the request receiving unit can prioritize voice input to allow the user to submit the request quickly. For example, if the request receiving unit estimates that the user is in a hurry, it can convert the user's voice into text using voice recognition technology and accept it as a request. This allows the timing of request submission to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without using AI. For example, the request receiving unit may use AI to estimate the user's emotions and adjust the request submission interface based on the results.

[0067] The request reception department can analyze a user's past request submission history and select the optimal submission method. For example, the request reception department can prioritize suggesting submission methods (such as voice or text) that the user has frequently used in the past. For example, the request reception department can analyze a user's past request submission history, identify the submission method the user has used most often in the past, and prioritize suggesting that method. The request reception department can also suggest the optimal submission method for a specific time period based on the user's past request submission history. For example, the request reception department can analyze a user's history of submitting requests at a specific time period and suggest the optimal submission method for that time period. Furthermore, the request reception department can analyze the content of requests the user has submitted in the past and make it easy for the user to submit similar requests. For example, the request reception department can analyze the content of requests the user has submitted in the past, provide similar requests as templates, and make it easy for the user to submit requests. This allows the optimal submission method to be selected based on the user's past history. Some or all of the above processes in the request reception department may be performed using AI or not. For example, the request reception department can use AI to analyze a user's past request submission history and select the optimal submission method based on the results.

[0068] The request receiving department can filter requests based on the user's current projects and areas of interest when they are submitted. For example, the request receiving department can prioritize requests related to the user's current projects. For example, the request receiving department can analyze the content of the user's current projects and prioritize requests related to those projects. The request receiving department can also filter relevant requests based on the user's areas of interest and encourage their submission. For example, the request receiving department can analyze the user's areas of interest and prioritize requests related to those areas. Furthermore, the request receiving department can also prioritize highly relevant requests by referring to the user's past project history. For example, the request receiving department can analyze the user's past project history and prioritize requests related to projects they have worked on in the past. This allows for filtering requests based on the user's current projects and areas of interest. Some or all of the above processing in the request receiving department may be performed using AI or not. For example, the request receiving department can use AI to analyze the user's projects and areas of interest and filter requests based on the results.

[0069] The request receiving unit can estimate the user's emotions and determine the priority of submitted requests based on the estimated user emotions. For example, if the user feels an urgent need, the request receiving unit prioritizes processing the request. For example, if the request receiving unit estimates that the user feels an urgent need, the request receiving unit prioritizes processing the request. Furthermore, if the user is relaxed, the request receiving unit can also prioritize detailed requests. For example, if the request receiving unit estimates that the user is relaxed, the request receiving unit prioritizes detailed requests. Furthermore, if the user is stressed, the request receiving unit can also prioritize simple requests. For example, if the request receiving unit estimates that the user is stressed, the request receiving unit prioritizes simple requests. This allows the priority of requests to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the request receiving unit may be performed using AI or without AI. For example, the request reception department can use AI to estimate the user's emotions and determine the priority of requests based on the results.

[0070] When a request is submitted, the request receiving unit can prioritize accepting highly relevant requests by taking into account the user's geographical location information. For example, if the user is in a specific area, the request receiving unit prioritizes accepting requests related to that area. For example, if the request receiving unit determines that the user is in a specific area, it prioritizes accepting requests related to that area. The request receiving unit can also prioritize processing requests related to locations close to the user's current location. For example, the request receiving unit prioritizes processing requests related to locations close to the user's current location. Furthermore, the request receiving unit can also prioritize accepting requests specific to a specific area based on the user's geographical location information. For example, the request receiving unit prioritizes accepting requests specific to a specific area based on the user's geographical location information. This allows requests to be prioritized based on the user's geographical location information. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without using AI. For example, the request receiving unit can analyze the user's geographical location information using AI and prioritize accepting requests based on the results.

[0071] The request receiving unit can analyze the user's social media activity when the request is submitted and receive related requests. The request receiving unit, for example, prioritizes receiving related requests based on content mentioned by the user on social media. For example, the request receiving unit analyzes content mentioned by the user on social media and prioritizes receiving requests related to the content. The request receiving unit can also prioritize processing requests related to topics of high interest from the user's social media activity. For example, the request receiving unit analyzes the user's social media activity and prioritizes processing requests related to topics of high interest. Furthermore, the request receiving unit can analyze the user's feedback on social media and receive related requests. For example, the request receiving unit analyzes the user's feedback on social media and receives requests related to the feedback. This makes it possible to receive related requests based on the user's social media activity. Some or all of the above-described processing in the request receiving unit may be performed using AI, or may be performed without using AI. For example, the request receiving unit can analyze the user's social media activity using AI and receive related requests based on the results.

[0072] The approval unit can estimate the user's emotions and adjust the approval criteria based on the estimated user's emotions. For example, if the user feels urgency, the approval unit relaxes the approval criteria and quickly approves the request. For example, if the approval unit estimates that the user feels urgency, the approval unit relaxes the approval criteria and quickly approves the request. The approval unit can also prioritize approving detailed requests when the user is relaxed. For example, if the approval unit estimates that the user is relaxed, the approval unit prioritizes approving detailed requests. The approval unit can also prioritize approving simple requests when the user is stressed. For example, if the approval unit estimates that the user is stressed, the approval unit prioritizes approving simple requests. This allows the approval criteria to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the approval unit may be performed using AI or without AI. For example, the approval department can use AI to estimate the user's emotions and adjust the approval criteria based on the results.

[0073] The approval department can adjust the level of detail in the approval process based on the importance of the request. For example, the approval department can conduct a detailed review of high-priority requests to improve the accuracy of the approval. For example, the approval department can evaluate the importance of requests and conduct a detailed review of high-priority requests. Alternatively, the approval department can conduct a simpler review of low-priority requests and approve them quickly. For example, the approval department can evaluate the importance of requests and conduct a simpler review of low-priority requests. Furthermore, the approval department can adjust the number of steps in the approval process according to the importance of the request. For example, the approval department can conduct a detailed review through multiple steps for high-priority requests and approve low-priority requests quickly with fewer steps. This allows the level of detail in the approval process to be adjusted based on the importance of the request. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to evaluate the importance of requests and adjust the level of detail in the approval process based on the results.

[0074] The approval department can apply different approval algorithms depending on the category of the request during the approval process. For example, for requests to add new features, the approval department can apply an algorithm that conducts a detailed technical review. For example, for requests to add new features, the approval department can apply an algorithm that evaluates the technical feasibility and scope of impact in detail. The approval department can also apply an algorithm that emphasizes user feedback for requests to improve existing features. For example, for requests to improve existing features, the approval department can apply an algorithm that evaluates them with an emphasis on user feedback and usage. Furthermore, the approval department can apply an algorithm that ensures a rapid response for requests to fix bugs. For example, for requests to fix bugs, the approval department can apply an algorithm that quickly identifies the problem and determines whether it can be fixed. This allows for the application of different approval algorithms depending on the category of the request. Some or all of the above processes in the approval department may be performed using AI or not. For example, the approval department can use AI to classify the categories of requests and apply an appropriate approval algorithm based on the results.

[0075] The approval unit can estimate the user's emotions and determine the priority of approvals based on the estimated user's emotions. For example, if the user feels an urgency, the approval unit prioritizes approving the request. For example, if the approval unit estimates that the user feels an urgency, the approval unit prioritizes approving the request. Furthermore, if the user is relaxed, the approval unit can prioritize approving detailed requests. For example, if the approval unit estimates that the user is relaxed, the approval unit prioritizes approving detailed requests. Furthermore, if the user is stressed, the approval unit can prioritize approving simple requests. For example, if the approval unit estimates that the user is stressed, the approval unit prioritizes approving simple requests. This allows the priority of approvals to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the approval unit may be performed using AI or without AI. For example, the approval department can use AI to estimate the user's emotions and determine the approval priority based on the results.

[0076] At the time of approval, the approval unit can determine the priority of approval based on the time of submission of the request. The approval unit can determine the priority based on, for example, the time of day when the request is submitted. For example, the approval unit can analyze the time of day when the request is submitted and prioritize approval of requests submitted during that time of day. The approval unit can also determine the priority based on the day of the week when the request is submitted. For example, the approval unit can analyze the day of the week when the request is submitted and prioritize approval of requests submitted on that day. The approval unit can also determine the priority based on the season when the request is submitted. For example, the approval unit can analyze the season when the request is submitted and prioritize approval of requests submitted during that season. In this way, the priority of approval can be determined based on the time of submission of the request. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without using AI. For example, the approval unit can analyze the time of submission of the request using AI and determine the priority of approval based on the results.

[0077] The approval unit can adjust the approval order based on the relevance of requests during approval. For example, the approval unit prioritizes approval of requests that are highly relevant to other requests. For example, if the approval unit determines that a request is highly relevant to other requests, it prioritizes approval of the request. Furthermore, if a request is related to a specific project, the approval unit can approve it based on the progress of the project. For example, if the approval unit determines that a request is related to a specific project, it approves it based on the progress of the project. Furthermore, if a request is related to a specific function, the approval unit can approve it based on the importance of the function. For example, if the approval unit determines that a request is related to a specific function, it approves it based on the importance of the function. This allows the approval order to be adjusted based on the relevance of requests. Some or all of the above-described processing in the approval unit may be performed using AI, or may be performed without using AI. For example, the approval unit can analyze the relevance of requests using AI and adjust the approval order based on the results.

[0078] The generation unit can estimate the user's emotion and adjust the expression method of the generated program code based on the estimated user's emotion. For example, if the user is relaxed, the generation unit generates program code with detailed comments. For example, if the generation unit estimates that the user is relaxed, the generation unit generates program code with detailed comments. The generation unit can also generate concise program code if the user is in a hurry. For example, if the generation unit estimates that the user is in a hurry, the generation unit generates concise program code. Furthermore, if the user is excited, the generation unit can also generate visually easy-to-understand program code. For example, if the generation unit estimates that the user is excited, the generation unit generates visually easy-to-understand program code. This makes it possible to adjust the expression method of the program code based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can use a generation AI to estimate the user's emotions and adjust the way the program code is expressed based on the results.

[0079] When generating program code, the generation unit can adjust the level of detail of the generated program code based on the importance of the request. For example, the generation unit generates detailed program code for requests with high importance. For example, the generation unit evaluates the importance of the request and generates detailed program code for requests with high importance. The generation unit can also generate concise program code for requests with low importance. For example, the generation unit evaluates the importance of the request and generates concise program code for requests with low importance. Furthermore, the generation unit can adjust comments and explanations in the program code based on the importance of the request. For example, the generation unit evaluates the importance of the request and generates program code including detailed comments and explanations for requests with high importance, and generates program code including concise comments and explanations for requests with low importance. This allows the level of detail of the generated program code to be adjusted based on the importance of the request. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can evaluate the importance of the request using a generation AI and adjust the level of detail of the generated program code based on the evaluation result.

[0080] When generating program code, the generation unit can apply different generation algorithms depending on the category of the request. For example, for a request to add a new function, the generation unit applies an algorithm that performs a detailed technical review. For example, for a request to add a new function, the generation unit applies an algorithm that performs a detailed evaluation of the technical feasibility and the scope of impact. The generation unit can also apply an algorithm that emphasizes user feedback to a request to improve an existing function. For example, for a request to improve an existing function, the generation unit applies an algorithm that emphasizes user feedback and usage status in evaluation. Furthermore, the generation unit can also apply an algorithm that provides a rapid response to a request to fix a bug. For example, for a request to fix a bug, the generation unit applies an algorithm that quickly identifies the problem and determines whether the fix is ​​possible. This allows the optimal generation algorithm to be applied depending on the category of the request. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can classify the category of the request using a generation AI and apply an appropriate generation algorithm based on the results.

[0081] The generation unit can estimate the user's emotions and adjust the length of the generated program code based on the estimated user's emotions. For example, if the user is in a hurry, the generation unit generates short, concise program code. For example, if the generation unit estimates that the user is in a hurry, the generation unit generates short, concise program code. The generation unit can also generate longer program code with detailed explanations if the user is relaxed. For example, if the generation unit estimates that the user is relaxed, the generation unit generates longer program code with detailed explanations. The generation unit can also generate visually easy-to-understand program code if the user is excited. For example, if the generation unit estimates that the user is excited, the generation unit generates visually easy-to-understand program code. This allows the length of the program code to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the generation unit can use a generation AI to estimate the user's emotions and adjust the length of the program code based on the results.

[0082] When generating program code, the generation unit can determine the generation priority based on the time of request submission. The generation unit can determine the generation priority based on, for example, the time period in which the requests are submitted. For example, the generation unit can analyze the time period in which the requests are submitted and prioritize generating requests submitted during that time period. The generation unit can also determine the generation priority based on the day of the week in which the requests are submitted. For example, the generation unit can analyze the day of the week in which the requests are submitted and prioritize generating requests submitted during that day. The generation unit can also determine the generation priority based on the season in which the requests are submitted. For example, the generation unit can analyze the season in which the requests are submitted and prioritize generating requests submitted during that season. In this way, the generation priority can be determined based on the time of request submission. Some or all of the above-described processing in the generation unit can be performed using a generation AI, or can be performed without using a generation AI. For example, the generation unit can analyze the time of request submission using a generation AI and determine the generation priority based on the results.

[0083] When generating program code, the generation unit can adjust the order of generation based on the relevance of requests. For example, if a request is highly relevant to other requests, the generation unit generates the request with priority. For example, if the generation unit determines that a request is highly relevant to other requests, the generation unit generates the request with priority. Furthermore, if a request is related to a specific project, the generation unit can generate the request according to the progress of the project. For example, if the generation unit determines that a request is related to a specific project, the generation unit generates the request according to the progress of the project. Furthermore, if a request is related to a specific function, the generation unit can generate the request according to the importance of the function. For example, if the generation unit determines that a request is related to a specific function, the generation unit generates the request according to the importance of the function. This allows the order of generation to be adjusted based on the relevance of requests. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can analyze the relevance of requests using a generation AI and adjust the order of generation based on the results.

[0084] The utilization unit can estimate the user's emotions and adjust the method of providing the program code based on the estimated user's emotions. For example, if the user is nervous, the utilization unit provides a simple, highly visible method of providing the program code. For example, if the utilization unit estimates that the user is nervous, the utilization unit provides a simple, highly visible method of providing the program code. Furthermore, if the user is relaxed, the utilization unit can provide a method of providing detailed information. For example, if the utilization unit estimates that the user is relaxed, the utilization unit provides a method of providing detailed information. Furthermore, if the user is in a hurry, the utilization unit can provide a method of providing the program code that focuses on the main points. For example, if the utilization unit estimates that the user is in a hurry, the utilization unit provides a method of providing the program code that focuses on the main points. This makes it possible to adjust the method of providing the program code based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the utilization unit may be performed using AI or without AI. For example, the utilization unit can use AI to estimate the user's emotions and adjust the way the program code is provided based on the results.

[0085] When providing program code, the utilization unit can select the optimal delivery method by referring to the user's past usage history. For example, the utilization unit prioritizes proposing delivery methods (email, download link, etc.) that the user has used in the past. For example, the utilization unit analyzes the user's past usage history, identifies the delivery method that the user has used most frequently, and prioritizes proposing that method. The utilization unit can also propose the optimal delivery method for a specific time period based on the user's past usage history. For example, the utilization unit analyzes the user's past usage history and proposes the optimal delivery method for a specific time period. Furthermore, the utilization unit can select the optimal delivery method based on the format of the program code that the user has used in the past (source code, binary, etc.). For example, the utilization unit analyzes the user's past usage history, identifies the format of the program code that the user has used in the past, and selects the optimal delivery method based on that format. This allows the optimal delivery method to be selected based on the user's past usage history. Some or all of the above-described processing in the utilization unit may be performed using AI, or may be performed without AI. For example, the utilization unit can analyze the user's past usage history using AI and select the optimal delivery method based on the results.

[0086] When providing program code, the utilization unit can customize the provided content based on the user's current project or area of ​​interest. For example, the utilization unit can prioritize providing program code related to the project the user is currently working on. For example, the utilization unit can analyze the content of the project the user is currently working on and prioritize providing program code related to that project. The utilization unit can also customize and provide related program code based on the user's area of ​​interest. For example, the utilization unit can analyze the user's area of ​​interest and customize and provide program code related to that area. Furthermore, the utilization unit can provide highly relevant program code by referring to the user's past project history. For example, the utilization unit can analyze the user's past project history and prioritize providing program code related to projects the user worked on in the past. This allows the provided content to be customized based on the user's current project or area of ​​interest. Some or all of the above-mentioned processing in the utilization unit may be performed using AI or without AI. For example, the utilization unit can analyze the user's project or area of ​​interest using AI and customize the provided content based on the results.

[0087] The utilization unit can estimate the user's emotions and adjust the order in which program codes are provided based on the estimated user's emotions. For example, if the user feels an urgent need, the utilization unit prioritizes providing that program code. For example, if the utilization unit estimates that the user feels an urgent need, the utilization unit prioritizes providing that program code. Furthermore, if the user is relaxed, the utilization unit can prioritize providing detailed program code. For example, if the utilization unit estimates that the user is relaxed, the utilization unit prioritizes providing detailed program code. Furthermore, if the user is stressed, the utilization unit can prioritize providing simple program code. For example, if the utilization unit estimates that the user is stressed, the utilization unit prioritizes providing simple program code. This allows the order in which program codes are provided to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the utilization unit may be performed using AI or without AI. For example, the utilization unit can use AI to estimate the user's emotions and adjust the order in which program codes are provided based on the results.

[0088] When providing program code, the utilization unit can select the optimal delivery method by taking into account the user's geographical location information. For example, if the user is in a specific region, the utilization unit prioritizes providing program code related to that region. For example, if the utilization unit determines that the user is in a specific region, the utilization unit prioritizes providing program code related to that region. The utilization unit can also prioritize providing program code related to locations close to the user's current location. For example, the utilization unit prioritizes providing program code related to locations close to the user's current location. Furthermore, the utilization unit can also prioritize providing region-specific program code based on the user's geographical location information. For example, the utilization unit prioritizes providing region-specific program code based on the user's geographical location information. This allows the optimal delivery method to be selected based on the user's geographical location information. Some or all of the above-described processing in the utilization unit may be performed using AI, or may be performed without AI. For example, the utilization unit can analyze the user's geographical location information using AI and select the optimal delivery method based on the results.

[0089] When providing the program code, the utilization unit can analyze the user's social media activity and customize the provided content. For example, the utilization unit can prioritize providing related program code based on the content mentioned by the user on social media. For example, the utilization unit can analyze the content mentioned by the user on social media and prioritize providing program code related to that content. The utilization unit can also customize and provide program code related to topics of interest to the user based on the user's social media activity. For example, the utilization unit can analyze the user's social media activity and customize and provide program code related to topics of interest. Furthermore, the utilization unit can analyze the user's feedback on social media and provide related program code. For example, the utilization unit can analyze the user's feedback on social media and provide program code related to the feedback. This allows the provided content to be customized based on the user's social media activity. Some or all of the above-described processing in the utilization unit may be performed using AI, or may be performed without using AI. For example, the utilization unit can analyze the user's social media activity using AI and customize the provided content based on the results. === Hard Collateral 1-1 === Each of the multiple elements including the request receiving unit, approval unit, generation unit, and utilization unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the request receiving unit can receive a user's request through the reception device 38 of the smart device 14. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the importance and urgency of the request. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates program code using a generation AI. The utilization unit provides the generated program code to the user, for example, through the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the request receiving unit, approval unit, generation unit, and utilization unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the request receiving unit can receive a user's request through the microphone 238 of the smart glasses 214. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the importance and urgency of the request. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates program code using a generation AI. The utilization unit provides the generated program code to the user, for example, through the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the request receiving unit, approval unit, generation unit, and utilization unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the request receiving unit can receive a user's request through the microphone 238 of the headset type terminal 314. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the importance and urgency of the request. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates program code using a generation AI. The utilization unit provides the generated program code to the user, for example, through the display 343 of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the request receiving unit, approval unit, generation unit, and utilization unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the request receiving unit can receive a user's request through the microphone 238 of the robot 414. The approval unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the importance and urgency of the request. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates program code using a generation AI. The utilization unit provides the generated program code to the user through, for example, the speaker 240 of the robot 414.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The request receiving unit can analyze the user's past request submission history and select the optimal submission method. For example, it can preferentially suggest submission methods (voice, text, etc.) that the user has frequently used in the past. The request receiving unit can also suggest the optimal submission method for a specific time period based on the user's past request submission history. Furthermore, the request receiving unit can analyze the content of requests that the user has submitted in the past and make it easy to submit similar requests. This makes it possible to select the optimal submission method based on the user's past history.

[0092] When a request is submitted, the request receiving unit can filter the requests based on the user's current project or area of ​​interest. For example, requests related to the project the user is currently working on are preferentially received. The request receiving unit can also filter related requests based on the user's area of ​​interest and encourage submission of the requests. Furthermore, the request receiving unit can refer to the user's past project history and preferentially receive highly relevant requests. This allows requests to be filtered based on the user's current project or area of ​​interest.

[0093] The approval unit can estimate the user's emotions and adjust the approval criteria based on the estimated user's emotions. For example, if the user feels urgent, the approval criteria can be relaxed and approval can be given quickly. In addition, if the user is relaxed, the approval unit can also give priority to approving detailed requests. Furthermore, if the user is stressed, the approval unit can also give priority to approving simple requests. In this way, the approval criteria can be adjusted based on the user's emotions.

[0094] The generation unit can estimate the user's emotion and adjust the expression method of the generated program code based on the estimated user's emotion. For example, if the user is relaxed, the generation unit can generate program code with detailed comments. If the user is in a hurry, the generation unit can also generate concise program code. Furthermore, if the user is excited, the generation unit can also generate visually easy-to-understand program code. In this way, the expression method of the program code can be adjusted based on the user's emotion.

[0095] The utilization unit can estimate the user's emotions and adjust the method of providing the program code based on the estimated user's emotions. For example, if the user is nervous, a simple and highly visible method of providing the program code is provided. If the user is relaxed, the utilization unit can also provide a method of providing the program code that includes detailed information. Furthermore, if the user is in a hurry, the utilization unit can also provide a method of providing the program code that focuses on the main points. In this way, the method of providing the program code can be adjusted based on the user's emotions.

[0096] When a request is submitted, the request receiving unit can prioritize receiving highly relevant requests by taking into account the user's geographical location information. For example, if the user is in a specific area, requests related to that area are prioritized. The request receiving unit can also prioritize processing requests related to locations close to the user's current location. Furthermore, the request receiving unit can also prioritize receiving requests specific to a region based on the user's geographical location information. This allows requests to be prioritized based on the user's geographical location information.

[0097] The approval department can adjust the level of detail of approval based on the importance of the request at the time of approval. For example, requests with high importance can be subject to detailed review to increase the accuracy of approval. The approval department can also perform simple review and quickly approve requests with low importance. Furthermore, the approval department can adjust the number of steps in the approval process depending on the importance of the request. This makes it possible to adjust the level of detail of approval based on the importance of the request.

[0098] When generating program code, the generation unit can apply different generation algorithms depending on the category of request. For example, for a request to add a new function, the generation unit can apply an algorithm that performs detailed technical review. For a request to improve an existing function, the generation unit can also apply an algorithm that emphasizes user feedback. Furthermore, for a request to fix a bug, the generation unit can also apply an algorithm that provides a quick response. This makes it possible to apply the optimal generation algorithm depending on the category of request.

[0099] When providing program code, the utilization unit can select the optimal delivery method by referring to the user's past usage history. For example, it can preferentially suggest delivery methods (email, download link, etc.) that the user has used in the past. The utilization unit can also suggest the optimal delivery method for a specific time period based on the user's past usage history. Furthermore, the utilization unit can select the optimal delivery method based on the format of the program code that the user has used in the past (source code, binary, etc.). This allows the optimal delivery method to be selected based on the user's past usage history.

[0100] When providing the program code, the utilization unit can analyze the user's social media activity and customize the provided content. For example, the utilization unit can prioritize providing related program code based on what the user has mentioned on social media. The utilization unit can also customize and provide program code related to topics of high interest to the user based on the user's social media activity. Furthermore, the utilization unit can analyze the user's feedback on social media and provide related program code. This allows the provided content to be customized based on the user's social media activity.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The request receiving unit provides an interface for users to submit requests for the app. Users can submit requests through a web interface, a mobile app interface, or a voice input interface. For example, the request is converted into text using voice recognition technology and accepted as a request. Step 2: The approval department sets criteria for approving user requests and approves them based on those criteria. For example, requests are evaluated and approved based on criteria such as the importance and urgency of the request, and technical feasibility. Requests can also be evaluated using AI. Step 3: The generator uses a generation AI to generate program code based on the user's requests. For example, it generates program code using machine learning models or natural language processing techniques, generating code to add specific functions or improve existing functions. Step 4: The user provides the generated program code to the user and provides support for the user to use the code to modify or add functions to the application. For example, the generated program code can be provided through a web interface or mobile app interface, or sent via email. The user can also provide a user guide and FAQs, and provide technical support.

[0103] 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.

[0104] 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> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0110] 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.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] 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.

[0115] 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.

[0116] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0126] 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.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] 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.

[0131] 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.

[0132] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0142] 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0147] 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.

[0148] 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.

[0149] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0158] 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.

[0159] 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).

[0160] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0161] 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."

[0162] 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.

[0163] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes 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.

[0168] The hardware resource that executes the specific process 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 process may be a single processor.

[0169] 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.

[0170] 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.

[0171] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a request receiving unit that receives a request from a user; an approval unit that approves the request accepted by the request acceptance unit; a generation unit that analyzes the request approved by the approval unit and generates a program code; a utilization unit that provides a user with the program code generated by the generation unit. A system characterized by:

2. The request receiving unit Provide an interface for users to submit requests for the app 2. The system of claim 1.

3. The approval unit Set criteria for approving user requests and approve requests based on those criteria 2. The system of claim 1.

4. The generation unit Using generative AI to generate program code based on user requests 2. The system of claim 1.

5. The utilization unit includes: Provide the generated program code to the user and provide support for the user to use the code to modify or add functions to the application.

2. The system of claim 1.

6. The request receiving unit Estimate the user's emotions and adjust the timing of request submission based on the estimated user emotions 2. The system of claim 1.

7. The request receiving unit Analyze the user's past request submission history and select the optimal submission method 2. The system of claim 1.

8. The request receiving unit Filter requests based on your current projects and interests when submitting them 2. The system of claim 1.

Images