system

Abstract

The system according to this embodiment aims to efficiently perform complex tasks by recording user operations and using them to train a generating AI. [Solution] The system according to the embodiment comprises a recording unit, a learning unit, a work unit, and a verification unit. The recording unit records the user's operations. The learning unit uses the operation data recorded by the recording unit to enable the generated AI to learn. The work unit performs tasks based on the content learned by the learning unit. The verification unit verifies the results of the tasks performed by the work unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is necessary to describe detailed conditions for the generative AI to learn complex operations, which takes time.

[0005] The system according to the embodiment aims to efficiently perform complex operations by recording a user's operation and having the generative AI learn it.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recording unit, a learning unit, a work unit, and a verification unit. The recording unit records user operations. The learning unit uses the operation data recorded by the recording unit to enable the generating AI to learn. The work unit performs tasks based on the content learned by the learning unit. The verification unit verifies the results of the tasks performed by the work unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently perform complex tasks by recording user operations and using the resulting AI to learn from them. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, 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 system according to an embodiment of the present invention is a system for streamlining complex tasks in Excel. In this system, the user actually performs the task manually once, and the generation AI learns from that movement. Next, the generation AI performs the task once based on what it has learned, and a human checks the result. If it is correct, the generation AI performs all the tasks in Excel. This mechanism eliminates the need to describe complex conditions in detail, thus saving time. For example, the user actually performs the task manually once. For example, for a sheet "aiu" containing many records, if the text color in column A of the "kakiku" sheet is blue and column Q matches the value in column B of the "aiu" sheet, the user replaces the value in column D of the "kakiku" sheet with the value in column O of the "aiu" sheet. In this case, all of the user's operations are recorded and learned by the generation AI. Next, the generation AI performs the task once based on what it has learned. The generation AI reproduces the operations performed by the user and performs the task under the same conditions. For example, if the text color in column A of the "kakiku" sheet is blue and column Q matches the value in column B of the "aiu" sheet, the AI ​​will replace the value in column D of the "kakiku" sheet with the value in column O of the "aiu" sheet. After that, a human will verify the results of the work performed by the generation AI. If the results are correct, the generation AI will perform all the Excel work. This eliminates the need for the user to meticulously enter complex conditions, saving time. This mechanism streamlines complex tasks in Excel and reduces the burden on the user. For example, automating tasks that are performed under the same conditions every time prevents manual errors and improves the accuracy of the work. Furthermore, as the generation AI learns, it will be able to handle even more complex tasks in the future. This streamlines complex tasks in Excel.

[0029] The Excel work efficiency system according to the embodiment comprises a recording unit, a learning unit, a work unit, and a verification unit. The recording unit records user operations. User operations include, but are not limited to, clicks, inputs, and drag-and-drops. The recording unit can record, for example, the timestamp of an operation and the type of operation. The learning unit allows a generating AI to learn based on the operation data recorded by the recording unit. The generating AI learns using, for example, a specific algorithm or model. The learning unit learns based on, for example, the dataset and learning algorithm used. The work unit performs tasks based on what has been learned by the learning unit. Tasks include, for example, data entry, calculations, and report generation. The work unit can, for example, enter data based on what has been learned. The verification unit verifies the results of the work performed by the work unit. Verification includes, for example, checking the accuracy of the results and error checking. The verification unit can, for example, check the accuracy of the work results. As a result, the Excel work efficiency system according to the embodiment can streamline complex tasks in Excel by recording user operations, having the generating AI learn from those operations, performing the tasks, and verifying the results.

[0030] The recording unit can record user actions. For example, it can record user actions such as clicks, inputs, and drag-and-drops. For instance, the recording unit can record a timestamp of an action. Furthermore, the recording unit can also record the type of action. For example, it can record a timestamp for a click and record the type of input action. This allows the recording of user actions to provide data for the generative AI to learn from.

[0031] The learning unit allows the generative AI to learn based on the operation data recorded by the recording unit. For example, the learning unit can use specific algorithms or models to learn. For instance, the learning unit can learn operation data using a neural network. It can also learn operation data using a decision tree. Furthermore, the learning unit can learn operation data using a support vector machine. This enables the generative AI to learn user operation data, thereby automating tasks.

[0032] The work unit can perform tasks based on what it has learned from the learning unit. For example, the work unit can input data based on what it has learned from the learning unit. For example, the work unit can input data into Excel cells based on what it has learned. The work unit can also perform calculations based on what it has learned. For example, the work unit can input formulas into Excel cells and perform calculations based on what it has learned. Furthermore, the work unit can generate reports based on what it has learned. For example, the work unit can generate reports on Excel sheets based on what it has learned. This improves the efficiency of tasks by allowing the generating AI to perform tasks based on what it has learned.

[0033] The verification unit can verify the results of the work performed by the work unit. For example, the verification unit can check the accuracy of the results of the work performed by the work unit. For example, the verification unit can check the accuracy of the data entered by the work unit. The verification unit can also check the results of calculations performed by the work unit. For example, the verification unit can check the results of formulas entered by the work unit. Furthermore, the verification unit can check the content of reports generated by the work unit. For example, the verification unit can check the content of reports generated by the work unit and evaluate their accuracy. In this way, by verifying the results of the work, the accuracy of the work performed by the generating AI can be guaranteed.

[0034] The recording unit may include an operation data storage unit for storing operation data. The operation data storage unit, for example, stores operation data recorded by the recording unit. For example, the operation data storage unit can store the timestamp of an operation. The operation data storage unit can also store the type of operation. For example, the operation data storage unit can store the timestamp of a click operation and the type of input operation. This allows the operation data to be referenced later.

[0035] The learning unit may include an algorithm unit that provides the algorithm for learning. The algorithm unit provides, for example, the algorithm used by the learning unit during learning. For instance, the algorithm unit can provide a neural network. It can also provide a decision tree. Furthermore, the algorithm unit can provide a support vector machine. This improves the learning efficiency of the generative AI by providing a learning algorithm.

[0036] The work unit may include a condition analysis unit that analyzes the conditions under which the work is performed. The condition analysis unit, for example, analyzes the conditions under which the work unit performs the work. For instance, the condition analysis unit can analyze the format of the input data. Furthermore, the condition analysis unit can also analyze the processing priority. For example, the condition analysis unit can analyze the format of the input data and determine the processing priority. This allows for more accurate work by analyzing the work conditions.

[0037] The verification unit may include a result evaluation unit that evaluates the work results. The result evaluation unit, for example, evaluates the work results as performed by the verification unit. For example, the result evaluation unit can evaluate the accuracy of the work results. The result evaluation unit can also perform error checking on the work results. For example, the result evaluation unit can evaluate the accuracy of the work results and perform error checking. By evaluating the work results, the accuracy of the work performed by the generating AI can be improved.

[0038] The recording unit can adjust the level of detail in the recording based on the user's operation speed and frequency. For example, if the user operates quickly, the recording unit can record only important operations and reduce the level of detail. Conversely, if the user operates slowly, the recording unit can record all operations in detail. Furthermore, if the user operates frequently, the recording unit can prioritize recording frequently performed operations. By adjusting the level of detail according to the user's operation speed and frequency, efficient recording becomes possible.

[0039] The recording unit can apply different recording formats depending on the type of operation during recording. For example, the recording unit can record in text format for data entry operations. It can also record in mathematical formula format for numerical calculation operations. Furthermore, for graph creation operations, it can record in a format that includes graph setting information. This allows for appropriate recording by applying the appropriate recording format for each type of operation.

[0040] The recording unit can select the optimal recording method based on the user's device information during recording. For example, the recording unit can select the optimal recording method considering the user's device information. For instance, if the user is using a smartphone, the recording unit can select a lightweight recording format. Similarly, if the user is using a tablet, the recording unit can select a recording format optimized for larger screens. Furthermore, if the user is using a desktop computer, the recording unit can select a high-resolution recording format. This allows for efficient recording by selecting the optimal recording method according to the user's device information.

[0041] The recording unit can improve the accuracy of recordings by referring to the user's past operation history during recording. For example, the recording unit can prioritize recording operations that the user has frequently performed in the past. Furthermore, the recording unit can identify important operations from the user's past operation history and record them in detail. In addition, the recording unit can analyze the user's past operation patterns and suggest the optimal recording method. This improves the accuracy of recordings by referring to the user's past operation history.

[0042] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit can select the most effective algorithm from past learning data. The learning unit can also analyze past learning data and adjust the algorithm parameters. Furthermore, the learning unit can develop new algorithms based on past learning data. This makes it possible to optimize the learning algorithm by referring to past learning data.

[0043] The learning unit can apply different learning methods depending on the type of data being manipulated during training. For example, the learning unit can apply text analysis methods in the case of data input operations. It can also apply numerical analysis methods in the case of numerical calculation operations. Furthermore, it can apply image analysis methods in the case of graph creation operations. This allows for effective learning by applying learning methods appropriate to the type of data being manipulated.

[0044] The learning unit can weight the training data based on when the operation data was acquired during training. For example, the learning unit can weight the training data based on when the operation data was acquired. For instance, the learning unit can assign a higher weight to the most recent operation data during training. It can also assign a lower weight to past operation data during training. Furthermore, the learning unit can adjust the weighting based on operation data for a specific period. This enables effective training by weighting the training data based on when the operation data was acquired.

[0045] The learning unit can adjust the learning order based on the relevance of the operation data during training. For example, the learning unit can prioritize learning highly relevant operation data. It can also postpone learning less relevant operation data. Furthermore, the learning unit can analyze the relevance of the operation data and determine the optimal learning order. This allows for effective learning by adjusting the learning order based on the relevance of the operation data.

[0046] The work unit can adjust the level of detail of its work based on the importance of the operational data during the work process. For example, the work unit can perform detailed work on important operational data. It can also perform simplified work on less important operational data. Furthermore, the work unit can analyze the importance of the operational data and determine the optimal level of detail. This allows for more efficient work by adjusting the level of detail according to the importance of the operational data.

[0047] The work unit can apply different work algorithms depending on the category of the data being worked on. For example, the work unit can apply a text analysis algorithm for data entry operations. It can also apply a numerical analysis algorithm for numerical calculation operations. Furthermore, it can apply an image analysis algorithm for graph creation operations. This allows for more efficient work by applying work algorithms appropriate to the category of the data being worked on.

[0048] The work unit can adjust the order of tasks based on the timing of operation data submission. For example, the work unit can prioritize the most recent operation data. Alternatively, the work unit can postpone processing older operation data. Furthermore, the work unit can adjust the order of tasks based on operation data from a specific period. This allows for more efficient work by adjusting the order of tasks based on the timing of operation data submission.

[0049] The work unit can adjust the order of tasks based on the relationships between operation data during the work process. For example, the work unit can prioritize tasks with highly relevant operation data. It can also postpone tasks with less relevant operation data. Furthermore, the work unit can analyze the relationships between operation data and determine the optimal order of tasks. This allows for more efficient work by adjusting the order of tasks based on the relationships between operation data.

[0050] The verification unit can adjust the level of detail of the verification based on the importance of the operation data during the verification process. For example, the verification unit can perform detailed verification on important operation data. It can also perform simplified verification on operation data of lower importance. Furthermore, the verification unit can analyze the importance of the operation data and determine the optimal level of detail. This allows for efficient verification by adjusting the level of detail according to the importance of the operation data.

[0051] The verification unit can apply different verification methods depending on the category of the operation data during verification. For example, the verification unit can apply text analysis methods in the case of data input operations. It can also apply numerical analysis methods in the case of numerical calculation operations. Furthermore, it can apply image analysis methods in the case of graph creation operations. This allows for effective verification by applying verification methods appropriate to the category of the operation data.

[0052] The verification unit can adjust the order of verification based on the submission date of the operation data. For example, the verification unit can prioritize the verification of the most recent operation data. It can also postpone the verification of older operation data. Furthermore, the verification unit can adjust the order of verification based on operation data from a specific period. This allows for more efficient verification by adjusting the order of verification based on the submission date of the operation data.

[0053] The verification unit can adjust the order of verification based on the relevance of the operation data during verification. For example, the verification unit can prioritize verification of highly relevant operation data. It can also postpone verification of less relevant operation data. Furthermore, the verification unit can analyze the relevance of the operation data and determine the optimal verification order. This allows for more effective verification by adjusting the order of verification based on the relevance of the operation data.

[0054] The operation data storage unit can adjust the level of detail of the operation data during storage based on its importance. For example, the operation data storage unit can perform detailed storage for important operation data. It can also perform simplified storage for less important operation data. Furthermore, the operation data storage unit can analyze the importance of the operation data and determine the optimal level of detail for storage. This allows for efficient storage by adjusting the level of detail according to the importance of the operation data.

[0055] The operation data storage unit can weight the stored data based on when the operation data was acquired. For example, the operation data storage unit can weight the stored data based on when the operation data was acquired. For example, the operation data storage unit can assign a higher weight to the most recent operation data and store it with a lower weight. Furthermore, the operation data storage unit can adjust the weighting based on operation data for a specific period. This enables effective storage by weighting the stored data based on when the operation data was acquired.

[0056] The algorithm unit can provide the optimal algorithm by referring to past algorithm data when providing an algorithm. For example, the algorithm unit can provide the optimal algorithm by referring to past algorithm data. For example, the algorithm unit can select the most effective algorithm from past algorithm data. The algorithm unit can also analyze past algorithm data and adjust the algorithm parameters. Furthermore, the algorithm unit can develop new algorithms based on past algorithm data. In this way, the optimal algorithm can be provided by referring to past algorithm data.

[0057] The algorithm unit can weight algorithms based on the timing of operation data acquisition when providing algorithms. For example, the algorithm unit can weight algorithms based on the timing of operation data acquisition. For instance, the algorithm unit can provide algorithms with a higher weight given to the most recent operation data. It can also provide algorithms with a lower weight given to past operation data. Furthermore, the algorithm unit can adjust the weighting based on operation data for a specific period. This enables the provision of effective algorithms by weighting algorithms based on the timing of operation data acquisition.

[0058] The condition analysis unit can adjust the level of detail of the analysis based on the importance of the operation data during condition analysis. For example, the condition analysis unit can perform a detailed condition analysis on important operation data. It can also perform a simplified condition analysis on operation data of lower importance. Furthermore, the condition analysis unit can analyze the importance of the operation data and determine the optimal level of detail for the condition analysis. This allows for efficient condition analysis by adjusting the level of detail of the analysis according to the importance of the operation data.

[0059] The condition analysis unit can adjust the order of analysis based on the timing of operation data acquisition during condition analysis. For example, the condition analysis unit can prioritize the analysis of the most recent operation data. It can also postpone the analysis of older operation data. Furthermore, the condition analysis unit can adjust the order of analysis based on operation data for a specific period. By adjusting the order of analysis based on the timing of operation data acquisition, efficient condition analysis becomes possible.

[0060] The results evaluation unit can adjust the level of detail of the evaluation based on the importance of the operation data during the results evaluation. For example, the results evaluation unit can perform a detailed evaluation on important operation data. It can also perform a simplified evaluation on operation data of low importance. Furthermore, the results evaluation unit can analyze the importance of the operation data and determine the optimal level of detail for the evaluation. This enables efficient results evaluation by adjusting the level of detail of the evaluation according to the importance of the operation data.

[0061] The results evaluation unit can adjust the evaluation order based on the timing of operation data acquisition during results evaluation. For example, the results evaluation unit can prioritize the evaluation of the most recent operation data. It can also postpone the evaluation of past operation data. Furthermore, the results evaluation unit can adjust the evaluation order based on operation data for a specific period. This allows for efficient results evaluation by adjusting the evaluation order based on the timing of operation data acquisition.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The recording unit not only records user actions but can also estimate the intent behind those actions. For example, if a user repeatedly performs a particular action, the recording unit can estimate the intent behind that action and automate subsequent actions. Furthermore, if a user interrupts an action, the recording unit can estimate the reason for the interruption and provide appropriate assistance. In addition, the recording unit can record environmental information (e.g., time of day and ambient noise level) when the user performs an action, allowing for a more accurate estimation of the intent. This enables more efficient operation support by estimating the user's intent.

[0064] The learning unit not only uses the operation data recorded by the recording unit to enable the generating AI to learn, but can also incorporate operation data from other users. For example, the learning unit can collect operation data from other users performing the same task and learn common patterns. Furthermore, the learning unit can incorporate operation data from different industries and applications to perform more generalized learning. In addition, the learning unit can compare past and current operation data to analyze operation trends. This allows for more advanced learning by incorporating operation data from other users.

[0065] The work unit not only performs tasks based on what it has learned from the learning unit, but it can also monitor the progress of the tasks in real time. For example, the work unit can visualize the progress of the tasks and provide feedback to the user. Furthermore, the work unit can dynamically allocate the necessary resources according to the progress of the tasks. In addition, the work unit can predict the next work step based on the progress of the tasks and prepare for it in advance. This real-time monitoring of the progress of the tasks enables efficient work.

[0066] The verification unit can not only verify the results of the work performed by the work unit, but also evaluate the quality of those results. For example, the verification unit can score the quality of the work results and provide feedback to the user. Furthermore, the verification unit can determine the need for retraining based on the quality of the work results. In addition, the verification unit can compare the quality of the work results with those of other users and provide benchmarks. This allows for higher quality work by evaluating the quality of the work results.

[0067] The recording unit can adjust the level of detail in the recording based on the user's operation speed and frequency. For example, if the user operates quickly, the recording unit can record only important operations with a lower level of detail. Conversely, if the user operates slowly, the recording unit can record all operations in detail. Furthermore, if the user operates frequently, the recording unit can prioritize recording frequently performed operations. By adjusting the level of detail in the recording according to the user's operation speed and frequency, efficient recording becomes possible.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The recording unit records user actions. User actions include clicks, input, drag-and-drop, etc. The recording unit can record the timestamp and type of action of each action. Step 2: The learning unit uses the operation data recorded by the recording unit to train the generative AI. The generative AI trains using specific algorithms and models. The learning unit trains based on the dataset and learning algorithm used. Step 3: The work unit performs tasks based on what it has learned from the learning unit. These tasks include data entry, calculations, and report generation. The work unit can perform data entry based on what it has learned. Step 4: The verification unit verifies the results of the work performed by the work unit. Verification includes checking the accuracy of the results and error checking. The verification unit can check the accuracy of the work results.

[0070] (Example of form 2) The system according to an embodiment of the present invention is a system for streamlining complex tasks in Excel. In this system, the user actually performs the task manually once, and the generation AI learns from that movement. Next, the generation AI performs the task once based on what it has learned, and a human checks the result. If it is correct, the generation AI performs all the tasks in Excel. This mechanism eliminates the need to describe complex conditions in detail, thus saving time. For example, the user actually performs the task manually once. For example, for a sheet "aiu" containing many records, if the text color in column A of the "kakiku" sheet is blue and column Q matches the value in column B of the "aiu" sheet, the user replaces the value in column D of the "kakiku" sheet with the value in column O of the "aiu" sheet. In this case, all of the user's operations are recorded and learned by the generation AI. Next, the generation AI performs the task once based on what it has learned. The generation AI reproduces the operations performed by the user and performs the task under the same conditions. For example, if the text color in column A of the "kakiku" sheet is blue and column Q matches the value in column B of the "aiu" sheet, the AI ​​will replace the value in column D of the "kakiku" sheet with the value in column O of the "aiu" sheet. After that, a human will verify the results of the work performed by the generation AI. If the results are correct, the generation AI will perform all the Excel work. This eliminates the need for the user to meticulously enter complex conditions, saving time. This mechanism streamlines complex tasks in Excel and reduces the burden on the user. For example, automating tasks that are performed under the same conditions every time prevents manual errors and improves the accuracy of the work. Furthermore, as the generation AI learns, it will be able to handle even more complex tasks in the future. This streamlines complex tasks in Excel.

[0071] The Excel work efficiency system according to the embodiment comprises a recording unit, a learning unit, a work unit, and a verification unit. The recording unit records user operations. User operations include, but are not limited to, clicks, inputs, and drag-and-drops. The recording unit can record, for example, the timestamp of an operation and the type of operation. The learning unit allows a generating AI to learn based on the operation data recorded by the recording unit. The generating AI learns using, for example, a specific algorithm or model. The learning unit learns based on, for example, the dataset and learning algorithm used. The work unit performs tasks based on what has been learned by the learning unit. Tasks include, for example, data entry, calculations, and report generation. The work unit can, for example, enter data based on what has been learned. The verification unit verifies the results of the work performed by the work unit. Verification includes, for example, checking the accuracy of the results and error checking. The verification unit can, for example, check the accuracy of the work results. As a result, the Excel work efficiency system according to the embodiment can streamline complex tasks in Excel by recording user operations, having the generating AI learn from those operations, performing the tasks, and verifying the results.

[0072] The recording unit can record user actions. For example, it can record user actions such as clicks, inputs, and drag-and-drops. For instance, the recording unit can record a timestamp of an action. Furthermore, the recording unit can also record the type of action. For example, it can record a timestamp for a click and record the type of input action. This allows the recording of user actions to provide data for the generative AI to learn from.

[0073] The learning unit allows the generative AI to learn based on the operation data recorded by the recording unit. For example, the learning unit can use specific algorithms or models to learn. For instance, the learning unit can learn operation data using a neural network. It can also learn operation data using a decision tree. Furthermore, the learning unit can learn operation data using a support vector machine. This enables the generative AI to learn user operation data, thereby automating tasks.

[0074] The work unit can perform tasks based on what it has learned from the learning unit. For example, the work unit can input data based on what it has learned from the learning unit. For example, the work unit can input data into Excel cells based on what it has learned. The work unit can also perform calculations based on what it has learned. For example, the work unit can input formulas into Excel cells and perform calculations based on what it has learned. Furthermore, the work unit can generate reports based on what it has learned. For example, the work unit can generate reports on Excel sheets based on what it has learned. This improves the efficiency of tasks by allowing the generating AI to perform tasks based on what it has learned.

[0075] The verification unit can verify the results of the work performed by the work unit. For example, the verification unit can check the accuracy of the results of the work performed by the work unit. For example, the verification unit can check the accuracy of the data entered by the work unit. The verification unit can also check the results of calculations performed by the work unit. For example, the verification unit can check the results of formulas entered by the work unit. Furthermore, the verification unit can check the content of reports generated by the work unit. For example, the verification unit can check the content of reports generated by the work unit and evaluate their accuracy. In this way, by verifying the results of the work, the accuracy of the work performed by the generating AI can be guaranteed.

[0076] The recording unit may include an operation data storage unit for storing operation data. The operation data storage unit, for example, stores operation data recorded by the recording unit. For example, the operation data storage unit can store the timestamp of an operation. The operation data storage unit can also store the type of operation. For example, the operation data storage unit can store the timestamp of a click operation and the type of input operation. This allows the operation data to be referenced later.

[0077] The learning unit may include an algorithm unit that provides the algorithm for learning. The algorithm unit provides, for example, the algorithm used by the learning unit during learning. For instance, the algorithm unit can provide a neural network. It can also provide a decision tree. Furthermore, the algorithm unit can provide a support vector machine. This improves the learning efficiency of the generative AI by providing a learning algorithm.

[0078] The work unit may include a condition analysis unit that analyzes the conditions under which the work is performed. The condition analysis unit, for example, analyzes the conditions under which the work unit performs the work. For instance, the condition analysis unit can analyze the format of the input data. Furthermore, the condition analysis unit can also analyze the processing priority. For example, the condition analysis unit can analyze the format of the input data and determine the processing priority. This allows for more accurate work by analyzing the work conditions.

[0079] The verification unit may include a result evaluation unit that evaluates the work results. The result evaluation unit, for example, evaluates the work results as performed by the verification unit. For example, the result evaluation unit can evaluate the accuracy of the work results. The result evaluation unit can also perform error checking on the work results. For example, the result evaluation unit can evaluate the accuracy of the work results and perform error checking. By evaluating the work results, the accuracy of the work performed by the generating AI can be improved.

[0080] The recording unit can estimate the user's emotions and adjust the recording method based on those emotions. For example, if the user is stressed, the recording unit can provide a simple interface and minimize the steps involved in recording the operation. If the user is relaxed, the recording unit can provide detailed recording options and suggest a customizable recording method. Furthermore, if the user is in a hurry, the recording unit can prioritize voice input to quickly record the operation. This allows for more appropriate recording by adjusting the recording method according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the recording unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0081] The recording unit can adjust the level of detail in the recording based on the user's operation speed and frequency. For example, if the user operates quickly, the recording unit can record only important operations and reduce the level of detail. Conversely, if the user operates slowly, the recording unit can record all operations in detail. Furthermore, if the user operates frequently, the recording unit can prioritize recording frequently performed operations. By adjusting the level of detail according to the user's operation speed and frequency, efficient recording becomes possible.

[0082] The recording unit can apply different recording formats depending on the type of operation during recording. For example, the recording unit can record in text format for data entry operations. It can also record in mathematical formula format for numerical calculation operations. Furthermore, for graph creation operations, it can record in a format that includes graph setting information. This allows for appropriate recording by applying the appropriate recording format for each type of operation.

[0083] The recording unit can estimate the user's emotions and determine the priority of operations to record based on the estimated emotions. For example, if the user is stressed, the recording unit can prioritize recording important operations. If the user is relaxed, the recording unit can record all operations equally. Furthermore, if the user is in a hurry, the recording unit can prioritize recording time-consuming operations. In this way, by prioritizing operations according to the user's emotions, important operations can be recorded preferentially. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the recording unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0084] The recording unit can select the optimal recording method based on the user's device information during recording. For example, the recording unit can select the optimal recording method considering the user's device information. For instance, if the user is using a smartphone, the recording unit can select a lightweight recording format. Similarly, if the user is using a tablet, the recording unit can select a recording format optimized for larger screens. Furthermore, if the user is using a desktop computer, the recording unit can select a high-resolution recording format. This allows for efficient recording by selecting the optimal recording method according to the user's device information.

[0085] The recording unit can improve the accuracy of recordings by referring to the user's past operation history during recording. For example, the recording unit can prioritize recording operations that the user has frequently performed in the past. Furthermore, the recording unit can identify important operations from the user's past operation history and record them in detail. In addition, the recording unit can analyze the user's past operation patterns and suggest the optimal recording method. This improves the accuracy of recordings by referring to the user's past operation history.

[0086] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is relaxed, the learning unit can select detailed training data. If the user is in a hurry, the learning unit can select only the most important training data. Furthermore, if the user is excited, the learning unit can select visually stimulating training data. This allows for more effective learning by selecting training data according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and speech analysis. For example, the learning unit can input facial data of the user captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0087] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit can select the most effective algorithm from past learning data. The learning unit can also analyze past learning data and adjust the algorithm parameters. Furthermore, the learning unit can develop new algorithms based on past learning data. This makes it possible to optimize the learning algorithm by referring to past learning data.

[0088] The learning unit can apply different learning methods depending on the type of data being manipulated during training. For example, the learning unit can apply text analysis methods in the case of data input operations. It can also apply numerical analysis methods in the case of numerical calculation operations. Furthermore, it can apply image analysis methods in the case of graph creation operations. This allows for effective learning by applying learning methods appropriate to the type of data being manipulated.

[0089] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can lower the learning frequency if the user is stressed. It can also increase the learning frequency if the user is relaxed. Furthermore, it can optimize the learning frequency if the user is in a hurry. This allows for effective learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the learning unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0090] The learning unit can weight the training data based on when the operation data was acquired during training. For example, the learning unit can weight the training data based on when the operation data was acquired. For instance, the learning unit can assign a higher weight to the most recent operation data during training. It can also assign a lower weight to past operation data during training. Furthermore, the learning unit can adjust the weighting based on operation data for a specific period. This enables effective training by weighting the training data based on when the operation data was acquired.

[0091] The learning unit can adjust the learning order based on the relevance of the operation data during training. For example, the learning unit can prioritize learning highly relevant operation data. It can also postpone learning less relevant operation data. Furthermore, the learning unit can analyze the relevance of the operation data and determine the optimal learning order. This allows for effective learning by adjusting the learning order based on the relevance of the operation data.

[0092] The work unit can estimate the user's emotions and adjust how it performs tasks based on those estimated emotions. For example, if the user is relaxed, the work unit can perform tasks at a leisurely pace. If the user is in a hurry, the work unit can perform tasks quickly. Furthermore, if the user is excited, the work unit can perform tasks with visually stimulating effects. This allows for more appropriate work by adjusting the task performance according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the work unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0093] The work unit can adjust the level of detail of its work based on the importance of the operational data during the work process. For example, the work unit can perform detailed work on important operational data. It can also perform simplified work on less important operational data. Furthermore, the work unit can analyze the importance of the operational data and determine the optimal level of detail. This allows for more efficient work by adjusting the level of detail according to the importance of the operational data.

[0094] The work unit can apply different work algorithms depending on the category of the data being worked on. For example, the work unit can apply a text analysis algorithm for data entry operations. It can also apply a numerical analysis algorithm for numerical calculation operations. Furthermore, it can apply an image analysis algorithm for graph creation operations. This allows for more efficient work by applying work algorithms appropriate to the category of the data being worked on.

[0095] The task force can estimate the user's emotions and determine task priorities based on those estimated emotions. For example, if the user is stressed, the task force can prioritize important tasks. If the user is relaxed, the task force can distribute all tasks evenly. Furthermore, if the user is in a hurry, the task force can prioritize time-consuming tasks. This allows for prioritizing important tasks based on the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the task force can input user facial data captured by a camera into a generating AI and have the generating AI estimate the user's emotions.

[0096] The work unit can adjust the order of tasks based on the timing of operation data submission. For example, the work unit can prioritize the most recent operation data. Alternatively, the work unit can postpone processing older operation data. Furthermore, the work unit can adjust the order of tasks based on operation data from a specific period. This allows for more efficient work by adjusting the order of tasks based on the timing of operation data submission.

[0097] The work unit can adjust the order of tasks based on the relationships between operation data during the work process. For example, the work unit can prioritize tasks with highly relevant operation data. It can also postpone tasks with less relevant operation data. Furthermore, the work unit can analyze the relationships between operation data and determine the optimal order of tasks. This allows for more efficient work by adjusting the order of tasks based on the relationships between operation data.

[0098] The verification unit can estimate the user's emotions and adjust the verification method based on the estimated emotions. For example, if the user is nervous, the verification unit can provide a simple and highly visible verification method. If the user is relaxed, the verification unit can also provide a verification method that includes detailed information. Furthermore, if the user is in a hurry, the verification unit can provide a concise verification method. By adjusting the verification method according to the user's emotions, more appropriate verification becomes possible. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the verification unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0099] The verification unit can adjust the level of detail of the verification based on the importance of the operation data during the verification process. For example, the verification unit can perform detailed verification on important operation data. It can also perform simplified verification on operation data of lower importance. Furthermore, the verification unit can analyze the importance of the operation data and determine the optimal level of detail. This allows for efficient verification by adjusting the level of detail according to the importance of the operation data.

[0100] The verification unit can apply different verification methods depending on the category of the operation data during verification. For example, the verification unit can apply text analysis methods in the case of data input operations. It can also apply numerical analysis methods in the case of numerical calculation operations. Furthermore, it can apply image analysis methods in the case of graph creation operations. This allows for effective verification by applying verification methods appropriate to the category of the operation data.

[0101] The verification unit can estimate the user's emotions and determine the priority of verifications based on the estimated emotions. For example, if the user is feeling stressed, the verification unit can prioritize important verifications. If the user is relaxed, the verification unit can perform all verifications equally. Furthermore, if the user is in a hurry, the verification unit can prioritize time-consuming verifications. In this way, by determining the priority of verifications according to the user's emotions, important verifications can be prioritized. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the verification unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0102] The verification unit can adjust the order of verification based on the submission date of the operation data. For example, the verification unit can prioritize the verification of the most recent operation data. It can also postpone the verification of older operation data. Furthermore, the verification unit can adjust the order of verification based on operation data from a specific period. This allows for more efficient verification by adjusting the order of verification based on the submission date of the operation data.

[0103] The verification unit can adjust the order of verification based on the relevance of the operation data during verification. For example, the verification unit can prioritize verification of highly relevant operation data. It can also postpone verification of less relevant operation data. Furthermore, the verification unit can analyze the relevance of the operation data and determine the optimal verification order. This allows for more effective verification by adjusting the order of verification based on the relevance of the operation data.

[0104] The operation data storage unit can estimate the user's emotions and select data to save based on the estimated emotions. For example, if the user is stressed, the operation data storage unit can save only important data. If the user is relaxed, the operation data storage unit can save all data. Furthermore, if the user is in a hurry, the operation data storage unit can prioritize saving data that can be saved quickly. In this way, by selecting data to save according to the user's emotions, important data can be saved preferentially. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the operation data storage unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0105] The operation data storage unit can adjust the level of detail of the operation data during storage based on its importance. For example, the operation data storage unit can perform detailed storage for important operation data. It can also perform simplified storage for less important operation data. Furthermore, the operation data storage unit can analyze the importance of the operation data and determine the optimal level of detail for storage. This allows for efficient storage by adjusting the level of detail according to the importance of the operation data.

[0106] The operation data storage unit can estimate the user's emotions and adjust the storage frequency based on the estimated emotions. For example, the operation data storage unit can lower the storage frequency when the user is stressed. It can also increase the storage frequency when the user is relaxed. Furthermore, it can optimize the storage frequency when the user is in a hurry. This allows for effective storage by adjusting the storage frequency according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the operation data storage unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0107] The operation data storage unit can weight the stored data based on when the operation data was acquired. For example, the operation data storage unit can weight the stored data based on when the operation data was acquired. For example, the operation data storage unit can assign a higher weight to the most recent operation data and store it with a lower weight. Furthermore, the operation data storage unit can adjust the weighting based on operation data for a specific period. This enables effective storage by weighting the stored data based on when the operation data was acquired.

[0108] The algorithm unit can estimate the user's emotions and select an algorithm based on those emotions. For example, if the user is relaxed, the algorithm unit can select a detailed algorithm. If the user is in a hurry, the algorithm unit can select an algorithm that can process quickly. Furthermore, if the user is excited, the algorithm unit can select a visually stimulating algorithm. By selecting an algorithm according to the user's emotions, a more appropriate algorithm can be provided. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the algorithm unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0109] The algorithm unit can provide the optimal algorithm by referring to past algorithm data when providing an algorithm. For example, the algorithm unit can provide the optimal algorithm by referring to past algorithm data. For example, the algorithm unit can select the most effective algorithm from past algorithm data. The algorithm unit can also analyze past algorithm data and adjust the algorithm parameters. Furthermore, the algorithm unit can develop new algorithms based on past algorithm data. In this way, the optimal algorithm can be provided by referring to past algorithm data.

[0110] The algorithm unit can estimate the user's emotions and adjust the frequency of algorithm delivery based on the estimated emotions. For example, the algorithm unit can lower the frequency of algorithm delivery if the user is stressed. Conversely, it can increase the frequency of algorithm delivery if the user is relaxed. Furthermore, the algorithm unit can optimize the frequency of algorithm delivery if the user is in a hurry. This allows for effective algorithm delivery by adjusting the frequency of algorithm delivery according to the user's emotions. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the algorithm unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0111] The algorithm unit can weight algorithms based on the timing of operation data acquisition when providing algorithms. For example, the algorithm unit can weight algorithms based on the timing of operation data acquisition. For instance, the algorithm unit can provide algorithms with a higher weight given to the most recent operation data. It can also provide algorithms with a lower weight given to past operation data. Furthermore, the algorithm unit can adjust the weighting based on operation data for a specific period. This enables the provision of effective algorithms by weighting algorithms based on the timing of operation data acquisition.

[0112] The condition analysis unit can estimate the user's emotions and adjust the condition analysis method based on the estimated emotions. For example, the condition analysis unit can perform a detailed condition analysis when the user is relaxed. It can also perform a rapid condition analysis when the user is in a hurry. Furthermore, it can perform a visually stimulating condition analysis when the user is excited. By adjusting the condition analysis method according to the user's emotions, more appropriate condition analysis becomes possible. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the condition analysis unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0113] The condition analysis unit can adjust the level of detail of the analysis based on the importance of the operation data during condition analysis. For example, the condition analysis unit can perform a detailed condition analysis on important operation data. It can also perform a simplified condition analysis on operation data of lower importance. Furthermore, the condition analysis unit can analyze the importance of the operation data and determine the optimal level of detail for the condition analysis. This allows for efficient condition analysis by adjusting the level of detail of the analysis according to the importance of the operation data.

[0114] The condition analysis unit can estimate the user's emotions and determine the priority of condition analysis based on the estimated user emotions. For example, if the user is feeling stressed, the condition analysis unit can prioritize important condition analysis. If the user is relaxed, the condition analysis unit can perform all condition analysis equally. Furthermore, if the user is in a hurry, the condition analysis unit can prioritize time-consuming condition analysis. In this way, by determining the priority of condition analysis according to the user's emotions, important condition analysis can be prioritized. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the condition analysis unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0115] The condition analysis unit can adjust the order of analysis based on the timing of operation data acquisition during condition analysis. For example, the condition analysis unit can prioritize the analysis of the most recent operation data. It can also postpone the analysis of older operation data. Furthermore, the condition analysis unit can adjust the order of analysis based on operation data for a specific period. By adjusting the order of analysis based on the timing of operation data acquisition, efficient condition analysis becomes possible.

[0116] The results evaluation unit can estimate the user's emotions and adjust the results evaluation method based on the estimated user emotions. For example, if the user is nervous, the results evaluation unit can provide a simple and highly visual evaluation method. If the user is relaxed, the results evaluation unit can also provide an evaluation method that includes detailed information. Furthermore, if the user is in a hurry, the results evaluation unit can provide a concise evaluation method. By adjusting the results evaluation method according to the user's emotions, more appropriate results evaluation becomes possible. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the results evaluation unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0117] The results evaluation unit can adjust the level of detail of the evaluation based on the importance of the operation data during the results evaluation. For example, the results evaluation unit can perform a detailed evaluation on important operation data. It can also perform a simplified evaluation on operation data of low importance. Furthermore, the results evaluation unit can analyze the importance of the operation data and determine the optimal level of detail for the evaluation. This enables efficient results evaluation by adjusting the level of detail of the evaluation according to the importance of the operation data.

[0118] The results evaluation unit can estimate the user's emotions and determine the priority of the results evaluation based on the estimated user emotions. For example, if the user is feeling stressed, the results evaluation unit can prioritize important evaluations. If the user is relaxed, the results evaluation unit can also evaluate all evaluations equally. Furthermore, if the user is in a hurry, the results evaluation unit can prioritize time-consuming evaluations. In this way, by determining the priority of the results evaluation according to the user's emotions, important results evaluations can be prioritized. Emotion estimation is performed using technologies such as facial recognition and voice analysis. For example, the results evaluation unit can input user facial data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0119] The results evaluation unit can adjust the evaluation order based on the timing of operation data acquisition during results evaluation. For example, the results evaluation unit can prioritize the evaluation of the most recent operation data. It can also postpone the evaluation of past operation data. Furthermore, the results evaluation unit can adjust the evaluation order based on operation data for a specific period. This allows for efficient results evaluation by adjusting the evaluation order based on the timing of operation data acquisition. === Hard Collateral 1-1 === Each of the multiple elements described above, including the recording unit, learning unit, work unit, and verification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records user operations using the control unit 46A of the smart device 14 and processes the recorded operation data using the specific processing unit 290 of the data processing unit 12. The learning unit allows the generating AI to learn based on the operation data recorded by the specific processing unit 290 of the data processing unit 12. The work unit performs tasks based on the learned content using the control unit 46A of the smart device 14. The verification unit verifies the results of the tasks using the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements described above, including the recording unit, learning unit, work unit, and verification unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the user's operations using the control unit 46A of the smart glasses 214 and processes the recorded operation data using the specific processing unit 290 of the data processing unit 12. The learning unit allows the generated AI to learn based on the operation data recorded by the specific processing unit 290 of the data processing unit 12. The work unit performs tasks based on the learned content using the control unit 46A of the smart glasses 214. The verification unit verifies the results of the tasks using the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements described above, including the recording unit, learning unit, work unit, and verification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records user operations using the control unit 46A of the headset terminal 314 and processes the recorded operation data using the specific processing unit 290 of the data processing unit 12. The learning unit allows the generated AI to learn based on the operation data recorded by the specific processing unit 290 of the data processing unit 12. The work unit performs tasks based on the learned content using the control unit 46A of the headset terminal 314. The verification unit verifies the results of the tasks using the control unit 46A of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements described above, including the recording unit, learning unit, work unit, and verification unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the user's operations using the control unit 46A of the robot 414 and processes the recorded operation data using the specific processing unit 290 of the data processing unit 12. The learning unit allows the generating AI to learn based on the operation data recorded by the specific processing unit 290 of the data processing unit 12. The work unit performs tasks based on the content learned by the control unit 46A of the robot 414. The verification unit verifies the results of the tasks using the control unit 46A of the robot 414.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The recording unit not only records user actions but can also estimate the intent behind those actions. For example, if a user repeatedly performs a particular action, the recording unit can estimate the intent behind that action and automate subsequent actions. Furthermore, if a user interrupts an action, the recording unit can estimate the reason for the interruption and provide appropriate assistance. In addition, the recording unit can record environmental information (e.g., time of day and ambient noise level) when the user performs an action, allowing for a more accurate estimation of the intent. This enables more efficient operation support by estimating the user's intent.

[0122] The learning unit not only uses the operation data recorded by the recording unit to enable the generating AI to learn, but can also incorporate operation data from other users. For example, the learning unit can collect operation data from other users performing the same task and learn common patterns. Furthermore, the learning unit can incorporate operation data from different industries and applications to perform more generalized learning. In addition, the learning unit can compare past and current operation data to analyze operation trends. This allows for more advanced learning by incorporating operation data from other users.

[0123] The work unit not only performs tasks based on what it has learned from the learning unit, but it can also monitor the progress of the tasks in real time. For example, the work unit can visualize the progress of the tasks and provide feedback to the user. Furthermore, the work unit can dynamically allocate the necessary resources according to the progress of the tasks. In addition, the work unit can predict the next work step based on the progress of the tasks and prepare for it in advance. This real-time monitoring of the progress of the tasks enables efficient work.

[0124] The verification unit can not only verify the results of the work performed by the work unit, but also evaluate the quality of those results. For example, the verification unit can score the quality of the work results and provide feedback to the user. Furthermore, the verification unit can determine the need for retraining based on the quality of the work results. In addition, the verification unit can compare the quality of the work results with those of other users and provide benchmarks. This allows for higher quality work by evaluating the quality of the work results.

[0125] The recording unit can estimate the user's emotions and adjust the recording method based on those emotions. For example, if the user is stressed, the recording unit can provide a simple interface and minimize the steps involved in recording the operation. If the user is relaxed, the recording unit can provide detailed operation recording options and suggest a customizable recording method. Furthermore, if the user is in a hurry, the recording unit can prioritize voice input to allow for quick recording of the operation. This allows for more appropriate recording by adjusting the recording method according to the user's emotions.

[0126] The learning unit can estimate the user's emotions and select training data based on those emotions. For example, if the user is relaxed, the learning unit can select detailed training data. If the user is in a hurry, the learning unit can select only the most important training data. Furthermore, if the user is excited, the learning unit can select visually stimulating training data. By selecting training data according to the user's emotions, more effective learning becomes possible.

[0127] The task unit can estimate the user's emotions and adjust how it performs tasks based on those emotions. For example, if the user is relaxed, the task unit can perform tasks at a leisurely pace. If the user is in a hurry, the task unit can perform tasks quickly. Furthermore, if the user is excited, the task unit can perform tasks with visually stimulating effects. By adjusting how tasks are performed according to the user's emotions, more appropriate work becomes possible.

[0128] The verification unit can estimate the user's emotions and adjust the verification method based on those emotions. For example, if the user is nervous, the verification unit can provide a simple and highly visible verification method. If the user is relaxed, it can provide a verification method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a concise verification method. By adjusting the verification method according to the user's emotions, more appropriate verification becomes possible.

[0129] The results evaluation unit can estimate the user's emotions and adjust the results evaluation method based on the estimated emotions. For example, if the user is nervous, the results evaluation unit can provide a simple and highly visual evaluation method. If the user is relaxed, the results evaluation unit can provide an evaluation method that includes detailed information. Furthermore, if the user is in a hurry, the results evaluation unit can provide a concise evaluation method. By adjusting the results evaluation method according to the user's emotions, more appropriate results evaluation becomes possible.

[0130] The recording unit can adjust the level of detail in the recording based on the user's operation speed and frequency. For example, if the user operates quickly, the recording unit can record only important operations with a lower level of detail. Conversely, if the user operates slowly, the recording unit can record all operations in detail. Furthermore, if the user operates frequently, the recording unit can prioritize recording frequently performed operations. By adjusting the level of detail in the recording according to the user's operation speed and frequency, efficient recording becomes possible.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The recording unit records user actions. User actions include clicks, input, drag-and-drop, etc. The recording unit can record the timestamp and type of action of each action. Step 2: The learning unit uses the operation data recorded by the recording unit to train the generative AI. The generative AI trains using specific algorithms and models. The learning unit trains based on the dataset and learning algorithm used. Step 3: The work unit performs tasks based on what it has learned from the learning unit. These tasks include data entry, calculations, and report generation. The work unit can perform data entry based on what it has learned. Step 4: The verification unit verifies the results of the work performed by the work unit. Verification includes checking the accuracy of the results and error checking. The verification unit can check the accuracy of the work results.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0135] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0136] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0161] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0177] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0178] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0179] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0180] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0183] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0184] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0185] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0186] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0188] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0189] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0190] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0194] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0195] 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.

[0196] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0197] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0198] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0199] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0201] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0202] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0203] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording unit that records user operations, A learning unit in which the generating AI learns based on the operation data recorded by the recording unit, A work unit that performs work based on the content learned by the learning unit, A system characterized by a verification unit that checks the results of the work performed by the aforementioned work unit, and a function that clearly indicates how the verification will be performed.

2. The aforementioned recording unit is Record user actions The system according to feature 1.

3. The aforementioned learning unit, The generating AI learns based on the operation data recorded by the recording unit. The system according to feature 1.

4. The aforementioned work unit is The work is performed based on the content learned by the aforementioned learning unit. The system according to feature 1.

5. The aforementioned verification unit is The results of the work performed by the aforementioned work unit are confirmed. The system according to feature 1.

6. The recording unit is, It is equipped with an operation data storage unit for storing operation data. The system according to feature 1.

7. The aforementioned learning unit, It includes an algorithm section that provides the algorithm for learning. The system according to feature 1.

8. The aforementioned work unit is It includes a condition analysis unit that analyzes the conditions under which the work is performed. The system according to feature 1.

Images