system

Abstract

The system according to the embodiment aims to enable a user to quickly understand how to operate an app and how to solve a problem. [Solution] A system according to an embodiment includes a collection unit, a learning unit, a guidance unit, a defect investigation unit, and a help desk collaboration unit. The collection unit collects operation history. The learning unit performs learning based on the operation history collected by the collection unit. The guidance unit provides guidance based on information obtained by the learning unit. The defect investigation unit investigates defects based on the guidance provided by the guidance unit. The help desk collaboration unit automatically queries the help desk if the defect investigation unit does not find a defect.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult for users to quickly understand how to operate an app or how to solve problems, and there is room for improvement.

[0005] The system according to the embodiment aims to enable a user to quickly understand how to operate an app and how to solve a problem. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a guidance unit, a defect investigation unit, and a help desk collaboration unit. The collection unit collects operation history. The learning unit performs learning based on the operation history collected by the collection unit. The guidance unit provides guidance based on information obtained by the learning unit. The defect investigation unit performs defect investigation based on the guidance provided by the guidance unit. The help desk collaboration unit automatically queries the help desk if the defect investigation unit does not find a defect. [Effects of the Invention]

[0007] The system according to the embodiment can enable a user to quickly understand how to operate an app and how to solve a problem. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) A guidance system according to an embodiment of the present invention provides guidance to users of web and smartphone apps on how to operate or resolve a problem. This guidance system provides optimal guidance based on the user's operation history and learning from the operation history and screen transitions of past app users. The more users and the more frequently the app is used, the more accurate the guidance. Furthermore, if a user encounters a problem while using the app and wants to inquire about it, they can press a "Fault Investigate" button, which automatically executes an investigation tool and determines whether or not there is a problem. If no problem is found, a function is also provided that automatically contacts the help desk. For example, when a user wants to know how to operate or resolve a problem, they press a "Help" button within the app. The user's operation history is then collected, and optimal guidance is provided based on learning from the operation history and screen transitions of past app users. For example, if a user is trying to use a specific function but does not know how to use it, specific guidance on how to use that function is provided. Furthermore, if a problem occurs while using the app, the user presses the "Fault Investigate" button. The investigation tool then automatically executes and checks for the presence or absence of the problem. If a problem is found, the user is notified of the details. If no problem is found, an inquiry is automatically made to the help desk, and the user can receive additional support. This system allows users to quickly learn how to operate the app and how to solve the problem, and any problems that occur while using the app can be dealt with quickly. This improves user satisfaction and promotes app usage. This allows the guidance system to provide optimal guidance based on the user's operation history and respond quickly if a problem occurs.

[0029] The guidance system according to the embodiment includes a collection unit, a learning unit, a guidance unit, a defect investigation unit, and a help desk linkage unit. The collection unit collects a user's operation history. The user's operation history includes, but is not limited to, clicks, scrolls, and inputs. For example, the collection unit records operations performed by the user within an app in real time and stores the operations in a database. The collection unit can also periodically back up the user's operation history to prevent data loss. The learning unit performs learning based on the collected operation history, past operation history, and screen transitions. For example, the learning unit uses a machine learning algorithm to extract patterns from the operation history and predict user behavior. The learning unit can also use deep learning technology to build a more advanced predictive model. The guidance unit provides optimal guidance to the user based on the information obtained by the learning unit. The guidance unit provides operation instructions in text format, for example. The guidance unit can also provide audio guides and video tutorials. The guidance unit can also provide real-time guidance on the next operation to be performed based on the user's operation history. The problem investigation unit automatically conducts an investigation when the problem investigation button is pressed, and checks for the presence or absence of a problem. The problem investigation unit, for example, analyzes the application's log file and checks for error messages. The problem investigation unit can also monitor the application's operating status in real time and detect signs of a problem. The help desk collaboration unit automatically makes an inquiry to the help desk if no problem is found. The help desk collaboration unit sends an inquiry to the help desk, for example, via email or chat. The help desk collaboration unit can also automatically make an inquiry by telephone. As a result, the guidance system according to the embodiment can provide optimal guidance based on the user's operation history and respond quickly if a problem occurs.

[0030] The collection unit can collect a user's operation history. For example, the collection unit records operations performed by a user within an app in real time and stores the operations in a database. For example, the collection unit records buttons clicked by a user and text entered by a user. The collection unit can also collect a history of a user's scroll position and page transitions. Furthermore, the collection unit can periodically back up the user's operation history to prevent data loss. For example, the collection unit backs up the operation history every night and stores it in a database. The collection unit can also encrypt and store the user's operation history to ensure data security. In this way, by collecting the user's operation history, data can be obtained to guide the user on the next operation method or a solution.

[0031] The learning unit can perform learning based on the collected operation history and past operation history or screen transitions. The learning unit, for example, uses a machine learning algorithm to extract patterns from the operation history and predict user behavior. For example, the learning unit predicts the operation a user will perform after clicking a specific button and provides guidance on the next operation. The learning unit can also use deep learning technology to build a more advanced prediction model. For example, the learning unit uses the user's operation history as input data and trains a prediction model using a neural network. Furthermore, the learning unit can analyze user behavior patterns based on past operation history and screen transitions and generate data for providing optimal guidance. For example, the learning unit clusters past operation history and identifies user groups with similar operation patterns. This allows the system to provide more accurate guidance by learning based on past operation history and screen transitions.

[0032] The guidance unit can provide optimal guidance to the user based on the information obtained by the learning unit. The guidance unit, for example, provides guidance on operation methods in text format. For example, when the user is trying to use a specific function, the guidance unit explains how to use the function step by step. The guidance unit can also provide audio guides and video tutorials. For example, when the user selects audio guides, the guidance unit provides audio guidance on operation methods. When the user selects video tutorials, the guidance unit provides video guidance on operation methods. Furthermore, the guidance unit can provide real-time guidance on the next operation to be performed based on the user's operation history. For example, after the user performs a specific operation, the guidance unit provides a pop-up message with guidance on the next operation to be performed. In this way, optimal guidance can be provided based on the information obtained by the learning unit, thereby quickly providing guidance on operation methods and solutions to the user.

[0033] The defect investigation unit can automatically conduct an investigation when the defect investigation button is pressed to check for the presence or absence of a defect. For example, the defect investigation unit analyzes the app's log file and checks for error messages. For example, the defect investigation unit scans the app's log file and extracts error or warning messages. The defect investigation unit can also monitor the app's operation status in real time to detect signs of a defect. For example, the defect investigation unit monitors the app's CPU usage and memory usage and detects abnormal values. The defect investigation unit can also analyze the user's operation history and identify the operation that caused the defect. For example, if the app crashes after the user performs a specific operation, the defect investigation unit identifies that operation and investigates the cause. In this way, by automatically conducting an investigation when the defect investigation button is pressed, the presence or absence of a defect can be quickly confirmed.

[0034] The help desk collaboration unit can automatically make an inquiry to the help desk if no defect is found. The help desk collaboration unit sends an inquiry to the help desk, for example, via email or chat. For example, if no defect is found, the help desk collaboration unit automatically sends an email and makes an inquiry to the help desk. The help desk collaboration unit can also make inquiries to the help desk in real time using a chatbot. For example, when a user makes an inquiry through a chatbot, the help desk collaboration unit automatically transfers the inquiry to the help desk. The help desk collaboration unit can also automatically make inquiries by phone. For example, if no defect is found, the help desk collaboration unit automatically makes a phone call and makes an inquiry to the help desk. In this way, by automatically making an inquiry to the help desk if no defect is found, the user can receive additional support.

[0035] The collection unit can analyze the user's past operation history and select the optimal collection method. The collection unit, for example, prioritizes collection of operations that the user frequently performed in the past. For example, the collection unit analyzes buttons clicked by the user in the past and text entered by the user to identify frequently performed operations. The collection unit can also predict operations that will be performed during a specific time period from the user's past operation history and concentrate collection on that time period. For example, the collection unit analyzes the user's tendency to use an app during a specific time period and collects operation history during that time period. The collection unit can also analyze the user's past operation history and collect important operations and unimportant operations separately. For example, the collection unit identifies operations in which the user performed important setting changes and prioritizes collection of those operations. In this way, the optimal collection method can be selected by analyzing the user's past operation history.

[0036] When collecting operation histories, the collection unit may filter the operation histories based on the user's current app usage status and areas of interest. For example, if the user is using a specific function, the collection unit may preferentially collect operation histories related to that function. For example, if the user frequently uses a specific function within an app, the collection unit may filter and collect operation histories related to that function. Furthermore, if the user is using apps in a specific category, the collection unit may collect operation histories related to that category. For example, if the user is using a media playback app, the collection unit may filter and collect operation histories related to that category. Furthermore, the collection unit may monitor the user's current app usage status in real time and filter the operation histories based on the user's areas of interest. For example, the collection unit may monitor the categories and functions of apps currently used by the user in real time and collect highly relevant operation histories. In this way, highly relevant data can be collected by filtering the operation histories based on the user's current app usage status and areas of interest.

[0037] When collecting operation histories, the collection unit can prioritize collecting highly relevant histories by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting operation histories related to that area. For example, when the user is in a specific city, the collection unit filters and collects operation histories related to that city. Furthermore, when the user is traveling, the collection unit can also collect operation histories related to the user's destination. For example, the collection unit prioritizes collecting operation histories of apps used by the user while traveling. Furthermore, the collection unit can monitor the user's geographical location information in real time and filter out highly relevant operation histories. For example, the collection unit acquires the user's GPS data in real time and collects operation histories related to the user's current location. In this way, highly relevant operation histories can be prioritized by taking into account the user's geographical location information.

[0038] When collecting the operation history, the collection unit can analyze the user's social media activities and collect related history. The collection unit collects related operation history based on, for example, the content shared by the user on social media. For example, the collection unit analyzes links and posts shared by the user on social media and filters and collects related operation history. The collection unit can also analyze the time periods during which the user is active on social media and collect operation history for those time periods. For example, the collection unit identifies the time periods during which the user is most active on social media and collects operation history for those time periods. The collection unit can also analyze the user's areas of interest on social media and filter related operation history. For example, the collection unit collects operation history related to topics in which the user has shown interest on social media. In this way, related operation history can be collected by analyzing the user's social media activities.

[0039] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past operation history data and identifies the most effective learning algorithm. The learning unit can also adjust parameters to improve learning accuracy from past learning data. For example, the learning unit uses past learning data to adjust hyperparameters and improve model accuracy. The learning unit can also analyze past learning data to identify areas for improvement in the learning algorithm. For example, the learning unit uses past learning data to evaluate the performance of the algorithm and find areas for improvement. In this way, by referring to past learning data, the learning algorithm can be optimized and accuracy can be improved.

[0040] During learning, the learning unit can apply different learning algorithms to each category of the operation history. For example, if the operation history is related to navigation, the learning unit applies a learning algorithm dedicated to navigation. For example, the learning unit predicts user behavior using an algorithm specialized for navigation operations. Furthermore, if the operation history is related to media playback, the learning unit can also apply a learning algorithm dedicated to media playback. For example, the learning unit predicts user behavior using an algorithm specialized for media playback operations. Furthermore, if the operation history is related to setting changes, the learning unit can also apply a learning algorithm dedicated to setting changes. For example, the learning unit predicts user behavior using an algorithm specialized for setting change operations. In this way, by applying different learning algorithms to each category of the operation history, the accuracy of learning can be improved.

[0041] During learning, the learning unit can weight the learning data based on the time when the operation history was submitted. The learning unit, for example, weights the learning data by placing emphasis on recent operation history. For example, the learning unit weights recent operation history highly and older operation history low. The learning unit can also weight the learning data by placing emphasis on operation history performed during a specific time period. For example, the learning unit weights operation history performed by a user during a specific time period highly. The learning unit can also weight the learning data by placing emphasis on operation history performed by a user during a specific event. For example, the learning unit weights operation history performed by a user during a specific campaign period highly. In this way, weighting the learning data based on the time when the operation history was submitted can improve the accuracy of learning.

[0042] During learning, the learning unit can improve the accuracy of the learning by referring to literature related to the operation history. The learning unit, for example, improves the accuracy of the learning by referring to technical literature related to the operation history. For example, the learning unit searches a database for technical literature related to the operation history and reflects it in the learning algorithm. The learning unit can also improve the accuracy of the learning by referring to a user manual related to the operation history. For example, the learning unit analyzes the user manual related to the operation history and uses it as learning data. The learning unit can also improve the accuracy of the learning by referring to research papers related to the operation history. For example, the learning unit reads research papers related to the operation history and reflects them in the learning algorithm. In this way, the accuracy of the learning can be improved by referring to literature related to the operation history.

[0043] When providing guidance, the guidance unit can adjust the level of detail of the guidance based on the importance of the operation. The guidance unit, for example, provides detailed guidance for important operations. For example, when the user makes an important setting change, the guidance unit explains the procedure in detail. The guidance unit can also provide concise guidance for general operations. For example, when the user performs a general operation, the guidance unit briefly explains the procedure. The guidance unit can also provide guidance that covers the main points for operations that the user frequently performs. For example, the guidance unit provides concise guidance that covers the main points for operations that the user frequently performs. In this way, by adjusting the level of detail of the guidance based on the importance of the operation, it is possible to provide optimal guidance for the user.

[0044] When providing guidance, the guidance unit can apply different guidance algorithms depending on the category of the operation. For example, the guidance unit applies a guidance algorithm dedicated to navigation to an operation related to navigation. For example, the guidance unit provides guidance to the user using an algorithm specialized for navigation operations. Furthermore, the guidance unit can also apply a guidance algorithm dedicated to media playback to an operation related to media playback. For example, the guidance unit provides guidance to the user using an algorithm specialized for media playback operations. Furthermore, the guidance unit can also apply a guidance algorithm dedicated to setting changes to an operation related to setting changes. For example, the guidance unit provides guidance to the user using an algorithm specialized for setting change operations. In this way, by applying different guidance algorithms depending on the category of the operation, more appropriate guidance can be provided.

[0045] When providing guidance, the guidance unit can determine the priority of the guidance based on the time of submission of the operation. For example, the guidance unit prioritizes providing guidance for operations performed recently. For example, the guidance unit prioritizes providing guidance for operations performed recently by the user. Furthermore, the guidance unit can provide guidance related to a time period for operations performed during a specific time period. For example, the guidance unit provides guidance related to a time period for operations performed by the user during a specific time period. Furthermore, the guidance unit can provide guidance related to the event for operations performed by the user during a specific event. For example, the guidance unit provides guidance related to a campaign for operations performed by the user during a specific campaign period. In this way, by determining the priority of the guidance based on the time of submission of the operation, guidance can be provided at a more appropriate time.

[0046] When providing guidance, the guidance unit can adjust the order of guidance based on the relevance of operations. For example, the guidance unit provides guidance for important operations first. For example, when the user is making an important setting change, the guidance unit provides guidance for that procedure first. The guidance unit can also provide guidance for general operations at a later date. For example, when the user is performing a general operation, the guidance unit provides guidance for that procedure at a later date. The guidance unit can also provide guidance preferentially for operations that the user frequently performs. For example, the guidance unit provides guidance preferentially for operations that the user frequently performs. In this way, by adjusting the order of guidance based on the relevance of operations, it is possible to provide guidance in a more appropriate order.

[0047] When investigating a defect, the defect investigation department can optimize the investigation algorithm by referring to past defect data. The defect investigation department, for example, selects the optimal investigation algorithm based on past defect data. For example, the defect investigation department analyzes past defect data and identifies the most effective investigation algorithm. The defect investigation department can also adjust parameters to improve the accuracy of the investigation from the past defect data. For example, the defect investigation department uses past defect data to adjust hyperparameters and improve the accuracy of the investigation algorithm. The defect investigation department can also analyze past defect data to identify areas for improvement in the investigation algorithm. For example, the defect investigation department uses past defect data to evaluate the performance of the algorithm and find areas for improvement. In this way, by referring to past defect data, the investigation algorithm can be optimized and its accuracy can be improved.

[0048] When investigating a problem, the problem investigation unit can apply different investigation methods to each category of operation history. For example, for a problem related to navigation, the problem investigation unit applies an investigation method dedicated to navigation. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for navigation operations. Furthermore, the problem investigation unit can also apply an investigation method dedicated to media playback to a problem related to media playback. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for media playback operations. Furthermore, the problem investigation unit can also apply an investigation method dedicated to setting changes to a problem related to setting changes. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for setting change operations. In this way, by applying different investigation methods to each category of operation history, the accuracy of the investigation can be improved.

[0049] When investigating a problem, the defect investigation unit can weight the investigation data based on the time when the operation history was submitted. The defect investigation unit, for example, weights the investigation data by placing emphasis on recent operation history. For example, the defect investigation unit weights recent operation history more highly and older operation history less highly. The defect investigation unit can also weight the investigation data by placing emphasis on operation history performed during a specific time period. For example, the defect investigation unit weights operation history performed by a user during a specific time period more highly. The defect investigation unit can also weight the investigation data by placing emphasis on operation history performed by a user during a specific event. For example, the defect investigation unit weights operation history performed by a user during a specific campaign period more highly. In this way, weighting the investigation data based on the time when the operation history was submitted can improve the accuracy of the investigation.

[0050] When investigating a defect, the defect investigation unit can improve the accuracy of the investigation by referring to literature related to the operation history. The defect investigation unit, for example, refers to technical literature related to the operation history to improve the accuracy of the investigation. For example, the defect investigation unit searches a database for technical literature related to the operation history and reflects it in the investigation algorithm. The defect investigation unit can also improve the accuracy of the investigation by referring to a user manual related to the operation history. For example, the defect investigation unit analyzes the user manual related to the operation history and uses it as investigation data. The defect investigation unit can also improve the accuracy of the investigation by referring to research papers related to the operation history. For example, the defect investigation unit reads research papers related to the operation history and reflects it in the investigation algorithm. In this way, by referring to literature related to the operation history, the accuracy of the investigation can be improved.

[0051] During help desk collaboration, the help desk collaboration unit can optimize the collaboration algorithm by referring to past inquiry data. The help desk collaboration unit, for example, selects an optimal collaboration algorithm based on past inquiry data. For example, the help desk collaboration unit analyzes past inquiry data and identifies the most effective collaboration algorithm. The help desk collaboration unit can also adjust parameters to improve the accuracy of collaboration based on the past inquiry data. For example, the help desk collaboration unit uses past inquiry data to adjust hyperparameters and improve the accuracy of the collaboration algorithm. The help desk collaboration unit can also analyze past inquiry data to identify areas for improvement in the collaboration algorithm. For example, the help desk collaboration unit uses past inquiry data to evaluate the performance of the algorithm and find areas for improvement. In this way, the collaboration algorithm can be optimized and its accuracy improved by referring to the past inquiry data.

[0052] When coordinating with the help desk, the help desk coordination unit can apply different coordination methods for each category of operation history. For example, the help desk coordination unit applies a coordination method dedicated to navigation to an inquiry related to navigation. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for navigation operations. The help desk coordination unit can also apply a coordination method dedicated to media playback to an inquiry related to media playback. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for media playback operations. The help desk coordination unit can also apply a coordination method dedicated to setting changes to an inquiry related to setting changes. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for setting change operations. In this way, by applying different coordination methods to each category of operation history, the accuracy of coordination can be improved.

[0053] During help desk collaboration, the help desk collaboration unit can weight the linked data based on the time when the operation history was submitted. The help desk collaboration unit, for example, weights the linked data by placing emphasis on recent operation history. For example, the help desk collaboration unit weights recent operation history more highly and older operation history less highly. The help desk collaboration unit can also weight the linked data by placing emphasis on operation history performed during a specific time period. For example, the help desk collaboration unit weights operation history performed by a user during a specific time period more highly. The help desk collaboration unit can also weight the linked data by placing emphasis on operation history performed by a user during a specific event. For example, the help desk collaboration unit weights operation history performed by a user during a specific campaign period more highly. In this way, weighting the linked data based on the time when the operation history was submitted can improve the accuracy of collaboration.

[0054] The help desk collaboration unit can improve the accuracy of collaboration by referring to literature related to the operation history during help desk collaboration. The help desk collaboration unit, for example, refers to technical literature related to the operation history to improve the accuracy of collaboration. For example, the help desk collaboration unit searches a database for technical literature related to the operation history and reflects it in the collaboration algorithm. The help desk collaboration unit can also improve the accuracy of collaboration by referring to a user manual related to the operation history. For example, the help desk collaboration unit analyzes the user manual related to the operation history and uses it as collaboration data. The help desk collaboration unit can also improve the accuracy of collaboration by referring to research papers related to the operation history. For example, the help desk collaboration unit reads research papers related to the operation history and reflects them in the collaboration algorithm. In this way, the accuracy of collaboration can be improved by referring to literature related to the operation history.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The guidance system can also learn the user's preferences and habits based on the user's operation history and provide personalized guidance. For example, if a user frequently uses a specific function, guidance related to that function can be provided preferentially. Also, if a user tends to use the app during a specific time of day, guidance tailored to that time of day can be provided. Furthermore, the system can analyze the user's past operation history and provide guidance based on the success stories of other users who perform similar operations. This can improve user satisfaction by providing personalized guidance based on the user's preferences and habits.

[0057] In addition to the user's operation history, the collection unit can also collect the user's device information and network status. For example, the collection unit can record the user's device type and OS version to identify problems related to a specific device. The collection unit can also monitor the user's network connection status to identify problems caused by network problems. Furthermore, the collection unit can collect the user's device's remaining battery level and storage usage status to analyze whether these factors affect the operation of the app. This allows for more accurate problem investigation by taking the user's device information and network status into consideration.

[0058] The learning unit can also estimate the user's skill level based on the user's operation history and provide guidance of an appropriate level of difficulty. For example, the learning unit can analyze the success rate and operation time of the user's past operations to evaluate the user's skill level. The learning unit can also predict how much support the user will need for a specific operation and provide guidance of an appropriate level of difficulty. Furthermore, the learning unit can adjust the content and format of the guidance according to the user's skill level. This can improve the user's learning effect by providing guidance appropriate to the user's skill level.

[0059] The guidance unit can analyze the success rate of operations performed by the user in the past based on the user's operation history, and provide guidance that focuses on operations with a low success rate. For example, if the user frequently fails at a particular operation, detailed guidance for that operation can be provided. Also, if the user takes a long time to perform a particular operation, hints for performing that operation efficiently can be provided. Furthermore, based on the success rate of operations performed by the user in the past, it can also provide guidance on success stories of other users who perform similar operations. In this way, by providing guidance that focuses on the user's operation history, it is possible to improve the user's success rate in operations.

[0060] In addition to the user's operation history, the collection unit can also collect user feedback and improve the method of collecting the operation history. For example, the collection unit can record feedback provided by the user after an operation and adjust the method of collecting the operation history. The collection unit can also collect real-time feedback provided by the user during an operation and immediately improve the collection method. Furthermore, the collection unit can analyze the user's feedback, identify problems with the collection of the operation history, and take measures to improve it. In this way, by utilizing the user's feedback to improve the method of collecting the operation history, more accurate data can be collected.

[0061] The learning unit can also predict a user's behavioral patterns based on the user's operation history and provide guidance based on the predicted behavior. For example, the learning unit can predict the next operation the user will perform after performing a specific operation and provide guidance for that operation in advance. The learning unit can also predict the operation the user will perform during a specific time period and provide guidance tailored to that time period. Furthermore, the learning unit can analyze the behavioral patterns of other users who perform similar operations based on the user's past operation history and provide optimal guidance. In this way, by predicting the user's behavioral patterns and providing guidance, the user's operation efficiency can be improved.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The collection unit collects the user's operation history. The user's operation history includes clicks, scrolls, input contents, etc. The collection unit records the user's operations within the app in real time and stores them in a database. The collection unit can also periodically back up the user's operation history to prevent data loss. Step 2: The learning unit learns based on the collected operation history, past operation history, and screen transitions. The learning unit uses machine learning algorithms to extract patterns from the operation history and predict user behavior. Deep learning technology can also be used to build more advanced predictive models. Step 3: The guidance unit provides the user with optimal guidance based on the information obtained by the learning unit. The guidance unit can provide operation instructions in text format, as well as audio guides and video tutorials. It can also provide real-time guidance on the next operation to be performed based on the user's operation history. Step 4: The Problem Investigation Department automatically conducts an investigation when the Problem Investigation button is pressed to check for any problems. The Problem Investigation Department analyzes the app's log files and checks for error messages. It can also monitor the app's operation status in real time to detect signs of problems. Step 5: If no problem is found, the Help Desk Integration Unit automatically sends an inquiry to the Help Desk. The Help Desk Integration Unit can send an inquiry to the Help Desk via email or chat, and can also automatically make an inquiry by phone.

[0064] (Example 2) A guidance system according to an embodiment of the present invention provides guidance to users of web and smartphone apps on how to operate or resolve a problem. This guidance system provides optimal guidance based on the user's operation history and learning from the operation history and screen transitions of past app users. The more users and the more frequently the app is used, the more accurate the guidance. Furthermore, if a user encounters a problem while using the app and wants to inquire about it, they can press a "Fault Investigate" button, which automatically executes an investigation tool and determines whether or not there is a problem. If no problem is found, a function is also provided that automatically contacts the help desk. For example, when a user wants to know how to operate or resolve a problem, they press a "Help" button within the app. The user's operation history is then collected, and optimal guidance is provided based on learning from the operation history and screen transitions of past app users. For example, if a user is trying to use a specific function but does not know how to use it, specific guidance on how to use that function is provided. Furthermore, if a problem occurs while using the app, the user presses the "Fault Investigate" button. The investigation tool then automatically executes and checks for the presence or absence of the problem. If a problem is found, the user is notified of the details. If no problem is found, an inquiry is automatically made to the help desk, and the user can receive additional support. This system allows users to quickly learn how to operate the app and how to solve the problem, and any problems that occur while using the app can be dealt with quickly. This improves user satisfaction and promotes app usage. This allows the guidance system to provide optimal guidance based on the user's operation history and respond quickly if a problem occurs.

[0065] The guidance system according to the embodiment includes a collection unit, a learning unit, a guidance unit, a defect investigation unit, and a help desk linkage unit. The collection unit collects a user's operation history. The user's operation history includes, but is not limited to, clicks, scrolls, and inputs. For example, the collection unit records operations performed by the user within an app in real time and stores the operations in a database. The collection unit can also periodically back up the user's operation history to prevent data loss. The learning unit performs learning based on the collected operation history, past operation history, and screen transitions. For example, the learning unit uses a machine learning algorithm to extract patterns from the operation history and predict user behavior. The learning unit can also use deep learning technology to build a more advanced predictive model. The guidance unit provides optimal guidance to the user based on the information obtained by the learning unit. The guidance unit provides operation instructions in text format, for example. The guidance unit can also provide audio guides and video tutorials. The guidance unit can also provide real-time guidance on the next operation to be performed based on the user's operation history. The problem investigation unit automatically conducts an investigation when the problem investigation button is pressed, and checks for the presence or absence of a problem. The problem investigation unit, for example, analyzes the application's log file and checks for error messages. The problem investigation unit can also monitor the application's operating status in real time and detect signs of a problem. The help desk collaboration unit automatically makes an inquiry to the help desk if no problem is found. The help desk collaboration unit sends an inquiry to the help desk, for example, via email or chat. The help desk collaboration unit can also automatically make an inquiry by telephone. As a result, the guidance system according to the embodiment can provide optimal guidance based on the user's operation history and respond quickly if a problem occurs.

[0066] The collection unit can collect a user's operation history. For example, the collection unit records operations performed by a user within an app in real time and stores the operations in a database. For example, the collection unit records buttons clicked by a user and text entered by a user. The collection unit can also collect a history of a user's scroll position and page transitions. Furthermore, the collection unit can periodically back up the user's operation history to prevent data loss. For example, the collection unit backs up the operation history every night and stores it in a database. The collection unit can also encrypt and store the user's operation history to ensure data security. In this way, by collecting the user's operation history, data can be obtained to guide the user on the next operation method or a solution.

[0067] The learning unit can perform learning based on the collected operation history and past operation history or screen transitions. The learning unit, for example, uses a machine learning algorithm to extract patterns from the operation history and predict user behavior. For example, the learning unit predicts the operation a user will perform after clicking a specific button and provides guidance on the next operation. The learning unit can also use deep learning technology to build a more advanced prediction model. For example, the learning unit uses the user's operation history as input data and trains a prediction model using a neural network. Furthermore, the learning unit can analyze user behavior patterns based on past operation history and screen transitions and generate data for providing optimal guidance. For example, the learning unit clusters past operation history and identifies user groups with similar operation patterns. This allows the system to provide more accurate guidance by learning based on past operation history and screen transitions.

[0068] The guidance unit can provide optimal guidance to the user based on the information obtained by the learning unit. The guidance unit, for example, provides guidance on operation methods in text format. For example, when the user is trying to use a specific function, the guidance unit explains how to use the function step by step. The guidance unit can also provide audio guides and video tutorials. For example, when the user selects audio guides, the guidance unit provides audio guidance on operation methods. When the user selects video tutorials, the guidance unit provides video guidance on operation methods. Furthermore, the guidance unit can provide real-time guidance on the next operation to be performed based on the user's operation history. For example, after the user performs a specific operation, the guidance unit provides a pop-up message with guidance on the next operation to be performed. In this way, optimal guidance can be provided based on the information obtained by the learning unit, thereby quickly providing guidance on operation methods and solutions to the user.

[0069] The defect investigation unit can automatically conduct an investigation when the defect investigation button is pressed to check for the presence or absence of a defect. For example, the defect investigation unit analyzes the app's log file and checks for error messages. For example, the defect investigation unit scans the app's log file and extracts error or warning messages. The defect investigation unit can also monitor the app's operation status in real time to detect signs of a defect. For example, the defect investigation unit monitors the app's CPU usage and memory usage and detects abnormal values. The defect investigation unit can also analyze the user's operation history and identify the operation that caused the defect. For example, if the app crashes after the user performs a specific operation, the defect investigation unit identifies that operation and investigates the cause. In this way, by automatically conducting an investigation when the defect investigation button is pressed, the presence or absence of a defect can be quickly confirmed.

[0070] The help desk collaboration unit can automatically make an inquiry to the help desk if no defect is found. The help desk collaboration unit sends an inquiry to the help desk, for example, via email or chat. For example, if no defect is found, the help desk collaboration unit automatically sends an email and makes an inquiry to the help desk. The help desk collaboration unit can also make inquiries to the help desk in real time using a chatbot. For example, when a user makes an inquiry through a chatbot, the help desk collaboration unit automatically transfers the inquiry to the help desk. The help desk collaboration unit can also automatically make inquiries by phone. For example, if no defect is found, the help desk collaboration unit automatically makes a phone call and makes an inquiry to the help desk. In this way, by automatically making an inquiry to the help desk if no defect is found, the user can receive additional support.

[0071] The collection unit can estimate the user's emotions and adjust the timing of collecting the operation history based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit temporarily stops collecting the operation history and resumes it when the user is relaxed. For example, the collection unit captures the user's facial expression with a camera and detects stress using an emotion estimation algorithm. Furthermore, if the user is relaxed, the collection unit can frequently collect the operation history to obtain detailed data. For example, the collection unit records the user's voice and detects the relaxed state using voice analysis technology. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting only important operations and postpone other operations. For example, the collection unit measures the user's heart rate with a sensor to detect a state of hurry. By adjusting the timing of collecting the operation history based on the user's emotions, data can be collected at a more appropriate time.

[0072] The collection unit can analyze the user's past operation history and select the optimal collection method. The collection unit, for example, prioritizes collection of operations that the user frequently performed in the past. For example, the collection unit analyzes buttons clicked by the user in the past and text entered by the user to identify frequently performed operations. The collection unit can also predict operations that will be performed during a specific time period from the user's past operation history and concentrate collection on that time period. For example, the collection unit analyzes the user's tendency to use an app during a specific time period and collects operation history during that time period. The collection unit can also analyze the user's past operation history and collect important operations and unimportant operations separately. For example, the collection unit identifies operations in which the user performed important setting changes and prioritizes collection of those operations. In this way, the optimal collection method can be selected by analyzing the user's past operation history.

[0073] When collecting operation histories, the collection unit may filter the operation histories based on the user's current app usage status and areas of interest. For example, if the user is using a specific function, the collection unit may preferentially collect operation histories related to that function. For example, if the user frequently uses a specific function within an app, the collection unit may filter and collect operation histories related to that function. Furthermore, if the user is using apps in a specific category, the collection unit may collect operation histories related to that category. For example, if the user is using a media playback app, the collection unit may filter and collect operation histories related to that category. Furthermore, the collection unit may monitor the user's current app usage status in real time and filter the operation histories based on the user's areas of interest. For example, the collection unit may monitor the categories and functions of apps currently used by the user in real time and collect highly relevant operation histories. In this way, highly relevant data can be collected by filtering the operation histories based on the user's current app usage status and areas of interest.

[0074] The collection unit can estimate the user's emotions and determine the priority of the operation history to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit prioritizes collecting only important operation history. For example, the collection unit can capture the user's facial expression with a camera and detect stress using an emotion estimation algorithm. Furthermore, if the user is relaxed, the collection unit can collect detailed operation history to improve data accuracy. For example, the collection unit can record the user's voice and detect the relaxed state using voice analysis technology. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting operations performed quickly. For example, the collection unit can measure the user's heart rate with a sensor and detect the user's state of hurry. In this way, by determining the priority of the operation history based on the user's emotions, important data can be collected preferentially.

[0075] When collecting operation histories, the collection unit can prioritize collecting highly relevant histories by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting operation histories related to that area. For example, when the user is in a specific city, the collection unit filters and collects operation histories related to that city. Furthermore, when the user is traveling, the collection unit can also collect operation histories related to the user's destination. For example, the collection unit prioritizes collecting operation histories of apps used by the user while traveling. Furthermore, the collection unit can monitor the user's geographical location information in real time and filter out highly relevant operation histories. For example, the collection unit acquires the user's GPS data in real time and collects operation histories related to the user's current location. In this way, highly relevant operation histories can be prioritized by taking into account the user's geographical location information.

[0076] When collecting the operation history, the collection unit can analyze the user's social media activities and collect related history. The collection unit collects related operation history based on, for example, the content shared by the user on social media. For example, the collection unit analyzes links and posts shared by the user on social media and filters and collects related operation history. The collection unit can also analyze the time periods during which the user is active on social media and collect operation history for those time periods. For example, the collection unit identifies the time periods during which the user is most active on social media and collects operation history for those time periods. The collection unit can also analyze the user's areas of interest on social media and filter related operation history. For example, the collection unit collects operation history related to topics in which the user has shown interest on social media. In this way, related operation history can be collected by analyzing the user's social media activities.

[0077] The learning unit can estimate the user's emotions and select learning data based on the estimated user emotions. For example, if the user is feeling stressed, the learning unit selects learning data that will help reduce stress. For example, the learning unit captures the user's facial expression with a camera and detects stress using an emotion estimation algorithm. Furthermore, if the user is relaxed, the learning unit can select more detailed learning data to improve accuracy. For example, the learning unit records the user's voice and detects the relaxed state using voice analysis technology. Furthermore, if the user is in a hurry, the learning unit can select data that can be learned quickly. For example, the learning unit measures the user's heart rate with a sensor and detects a state of hurry. In this way, by selecting learning data based on the user's emotions, more appropriate data can be used for learning.

[0078] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past operation history data and identifies the most effective learning algorithm. The learning unit can also adjust parameters to improve learning accuracy from past learning data. For example, the learning unit uses past learning data to adjust hyperparameters and improve model accuracy. The learning unit can also analyze past learning data to identify areas for improvement in the learning algorithm. For example, the learning unit uses past learning data to evaluate the performance of the algorithm and find areas for improvement. In this way, by referring to past learning data, the learning algorithm can be optimized and accuracy can be improved.

[0079] During learning, the learning unit can apply different learning algorithms to each category of the operation history. For example, if the operation history is related to navigation, the learning unit applies a learning algorithm dedicated to navigation. For example, the learning unit predicts user behavior using an algorithm specialized for navigation operations. Furthermore, if the operation history is related to media playback, the learning unit can also apply a learning algorithm dedicated to media playback. For example, the learning unit predicts user behavior using an algorithm specialized for media playback operations. Furthermore, if the operation history is related to setting changes, the learning unit can also apply a learning algorithm dedicated to setting changes. For example, the learning unit predicts user behavior using an algorithm specialized for setting change operations. In this way, by applying different learning algorithms to each category of the operation history, the accuracy of learning can be improved.

[0080] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, if the user is feeling stressed, the learning unit reduces the frequency of learning to reduce the burden on the user. For example, the learning unit captures the user's facial expression with a camera and detects stress using an emotion estimation algorithm. The learning unit can also increase the frequency of learning to improve data accuracy if the user is relaxed. For example, the learning unit records the user's voice and detects the relaxed state using voice analysis technology. The learning unit can also adjust the frequency of learning to speed up learning if the user is in a hurry. For example, the learning unit measures the user's heart rate with a sensor and detects a state of hurry. In this way, by adjusting the frequency of learning based on the user's emotions, the accuracy of learning can be improved while reducing the burden on the user.

[0081] During learning, the learning unit can weight the learning data based on the time when the operation history was submitted. The learning unit, for example, weights the learning data by placing emphasis on recent operation history. For example, the learning unit weights recent operation history highly and older operation history low. The learning unit can also weight the learning data by placing emphasis on operation history performed during a specific time period. For example, the learning unit weights operation history performed by a user during a specific time period highly. The learning unit can also weight the learning data by placing emphasis on operation history performed by a user during a specific event. For example, the learning unit weights operation history performed by a user during a specific campaign period highly. In this way, weighting the learning data based on the time when the operation history was submitted can improve the accuracy of learning.

[0082] During learning, the learning unit can improve the accuracy of the learning by referring to literature related to the operation history. The learning unit, for example, improves the accuracy of the learning by referring to technical literature related to the operation history. For example, the learning unit searches a database for technical literature related to the operation history and reflects it in the learning algorithm. The learning unit can also improve the accuracy of the learning by referring to a user manual related to the operation history. For example, the learning unit analyzes the user manual related to the operation history and uses it as learning data. The learning unit can also improve the accuracy of the learning by referring to research papers related to the operation history. For example, the learning unit reads research papers related to the operation history and reflects them in the learning algorithm. In this way, the accuracy of the learning can be improved by referring to literature related to the operation history.

[0083] The guidance unit can estimate the user's emotions and adjust the way in which guidance is presented based on the estimated user emotions. For example, if the user is feeling stressed, the guidance unit provides a simple and easy-to-understand way of presentation. For example, the guidance unit captures the user's facial expression with a camera, detects stress using an emotion estimation algorithm, and provides simple guidance. Furthermore, if the user is relaxed, the guidance unit can provide a way of presentation that includes detailed explanations. For example, the guidance unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and provide detailed guidance. Furthermore, if the user is in a hurry, the guidance unit can provide a concise way of presentation that focuses on the main points. For example, the guidance unit can measure the user's heart rate with a sensor, detect the user's state of hurry, and provide concise guidance. This allows the guidance unit to adjust the way in which guidance is presented based on the user's emotions, thereby providing more appropriate guidance.

[0084] When providing guidance, the guidance unit can adjust the level of detail of the guidance based on the importance of the operation. The guidance unit, for example, provides detailed guidance for important operations. For example, when the user makes an important setting change, the guidance unit explains the procedure in detail. The guidance unit can also provide concise guidance for general operations. For example, when the user performs a general operation, the guidance unit briefly explains the procedure. The guidance unit can also provide guidance that covers the main points for operations that the user frequently performs. For example, the guidance unit provides concise guidance that covers the main points for operations that the user frequently performs. In this way, by adjusting the level of detail of the guidance based on the importance of the operation, it is possible to provide optimal guidance for the user.

[0085] When providing guidance, the guidance unit can apply different guidance algorithms depending on the category of the operation. For example, the guidance unit applies a guidance algorithm dedicated to navigation to an operation related to navigation. For example, the guidance unit provides guidance to the user using an algorithm specialized for navigation operations. Furthermore, the guidance unit can also apply a guidance algorithm dedicated to media playback to an operation related to media playback. For example, the guidance unit provides guidance to the user using an algorithm specialized for media playback operations. Furthermore, the guidance unit can also apply a guidance algorithm dedicated to setting changes to an operation related to setting changes. For example, the guidance unit provides guidance to the user using an algorithm specialized for setting change operations. In this way, by applying different guidance algorithms depending on the category of the operation, more appropriate guidance can be provided.

[0086] The guidance unit can estimate the user's emotions and adjust the length of the guidance based on the estimated user emotions. For example, if the user is feeling stressed, the guidance unit can provide short, to-the-point guidance. For example, the guidance unit can capture the user's facial expressions with a camera, detect stress using an emotion estimation algorithm, and provide short guidance. Furthermore, if the user is relaxed, the guidance unit can provide longer guidance with detailed explanations. For example, the guidance unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and provide detailed guidance. Furthermore, if the user is in a hurry, the guidance unit can provide short guidance that can be quickly understood. For example, the guidance unit can measure the user's heart rate with a sensor, detect the user's state of hurry, and provide short guidance. This allows the length of the guidance to be adjusted based on the user's emotions, thereby providing more appropriate guidance.

[0087] When providing guidance, the guidance unit can determine the priority of the guidance based on the time of submission of the operation. For example, the guidance unit prioritizes providing guidance for operations performed recently. For example, the guidance unit prioritizes providing guidance for operations performed recently by the user. Furthermore, the guidance unit can provide guidance related to a time period for operations performed during a specific time period. For example, the guidance unit provides guidance related to a time period for operations performed by the user during a specific time period. Furthermore, the guidance unit can provide guidance related to the event for operations performed by the user during a specific event. For example, the guidance unit provides guidance related to a campaign for operations performed by the user during a specific campaign period. In this way, by determining the priority of the guidance based on the time of submission of the operation, guidance can be provided at a more appropriate time.

[0088] When providing guidance, the guidance unit can adjust the order of guidance based on the relevance of operations. For example, the guidance unit provides guidance for important operations first. For example, when the user is making an important setting change, the guidance unit provides guidance for that procedure first. The guidance unit can also provide guidance for general operations at a later date. For example, when the user is performing a general operation, the guidance unit provides guidance for that procedure at a later date. The guidance unit can also provide guidance preferentially for operations that the user frequently performs. For example, the guidance unit provides guidance preferentially for operations that the user frequently performs. In this way, by adjusting the order of guidance based on the relevance of operations, it is possible to provide guidance in a more appropriate order.

[0089] The defect investigation unit can estimate the user's emotions and adjust the defect investigation method based on the estimated user emotions. For example, if the user is feeling stressed, the defect investigation unit quickly conducts a defect investigation and provides the results. For example, the defect investigation unit captures the user's facial expression with a camera, detects stress using an emotion estimation algorithm, and quickly conducts an investigation. The defect investigation unit can also conduct a detailed defect investigation to improve accuracy if the user is relaxed. For example, the defect investigation unit records the user's voice, detects the relaxed state using voice analysis technology, and conducts a detailed investigation. The defect investigation unit can also prioritize investigating only important defects if the user is in a hurry. For example, the defect investigation unit measures the user's heart rate with a sensor, detects that the user is in a hurry, and prioritizes investigating important defects. This allows the defect investigation method to be adjusted based on the user's emotions, thereby enabling the defect investigation to be conducted in a more appropriate manner.

[0090] When investigating a defect, the defect investigation department can optimize the investigation algorithm by referring to past defect data. The defect investigation department, for example, selects the optimal investigation algorithm based on past defect data. For example, the defect investigation department analyzes past defect data and identifies the most effective investigation algorithm. The defect investigation department can also adjust parameters to improve the accuracy of the investigation from the past defect data. For example, the defect investigation department uses past defect data to adjust hyperparameters and improve the accuracy of the investigation algorithm. The defect investigation department can also analyze past defect data to identify areas for improvement in the investigation algorithm. For example, the defect investigation department uses past defect data to evaluate the performance of the algorithm and find areas for improvement. In this way, by referring to past defect data, the investigation algorithm can be optimized and its accuracy can be improved.

[0091] When investigating a problem, the problem investigation unit can apply different investigation methods to each category of operation history. For example, for a problem related to navigation, the problem investigation unit applies an investigation method dedicated to navigation. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for navigation operations. Furthermore, the problem investigation unit can also apply an investigation method dedicated to media playback to a problem related to media playback. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for media playback operations. Furthermore, the problem investigation unit can also apply an investigation method dedicated to setting changes to a problem related to setting changes. For example, the problem investigation unit identifies the cause of the problem using an investigation method specialized for setting change operations. In this way, by applying different investigation methods to each category of operation history, the accuracy of the investigation can be improved.

[0092] The defect investigation unit can estimate the user's emotions and determine the priority of defect investigations based on the estimated user emotions. For example, if the user is feeling stressed, the defect investigation unit prioritizes investigating important defects. For example, the defect investigation unit captures the user's facial expression with a camera, detects stress using an emotion estimation algorithm, and prioritizes investigating important defects. The defect investigation unit can also conduct detailed defect investigations to improve accuracy if the user is relaxed. For example, the defect investigation unit can record the user's voice, detect the user's relaxed state using voice analysis technology, and conduct detailed investigations. The defect investigation unit can also prioritize investigating defects that can be investigated quickly if the user is in a hurry. For example, the defect investigation unit can measure the user's heart rate with a sensor, detect the user's state of hurry, and conduct investigations quickly. In this way, by determining the priority of defect investigations based on the user's emotions, important defects can be investigated preferentially.

[0093] When investigating a problem, the defect investigation unit can weight the investigation data based on the time when the operation history was submitted. The defect investigation unit, for example, weights the investigation data by placing emphasis on recent operation history. For example, the defect investigation unit weights recent operation history more highly and older operation history less highly. The defect investigation unit can also weight the investigation data by placing emphasis on operation history performed during a specific time period. For example, the defect investigation unit weights operation history performed by a user during a specific time period more highly. The defect investigation unit can also weight the investigation data by placing emphasis on operation history performed by a user during a specific event. For example, the defect investigation unit weights operation history performed by a user during a specific campaign period more highly. In this way, weighting the investigation data based on the time when the operation history was submitted can improve the accuracy of the investigation.

[0094] When investigating a defect, the defect investigation unit can improve the accuracy of the investigation by referring to literature related to the operation history. The defect investigation unit, for example, refers to technical literature related to the operation history to improve the accuracy of the investigation. For example, the defect investigation unit searches a database for technical literature related to the operation history and reflects it in the investigation algorithm. The defect investigation unit can also improve the accuracy of the investigation by referring to a user manual related to the operation history. For example, the defect investigation unit analyzes the user manual related to the operation history and uses it as investigation data. The defect investigation unit can also improve the accuracy of the investigation by referring to research papers related to the operation history. For example, the defect investigation unit reads research papers related to the operation history and reflects it in the investigation algorithm. In this way, by referring to literature related to the operation history, the accuracy of the investigation can be improved.

[0095] The help desk linking unit can estimate the user's emotions and adjust the content of the inquiry to the help desk based on the estimated user emotions. For example, if the user is feeling stressed, the help desk linking unit provides concise and easy-to-understand inquiry content. For example, the help desk linking unit captures the user's facial expression with a camera, detects stress using an emotion estimation algorithm, and provides concise inquiry content. Furthermore, if the user is relaxed, the help desk linking unit can provide detailed inquiry content. For example, the help desk linking unit records the user's voice, detects a relaxed state using voice analysis technology, and provides detailed inquiry content. Furthermore, if the user is in a hurry, the help desk linking unit can provide inquiry content that can be quickly responded to. For example, the help desk linking unit measures the user's heart rate with a sensor, detects a state of hurry, and provides inquiry content that can be quickly responded to. In this way, by adjusting the inquiry content based on the user's emotions, more appropriate inquiries can be made.

[0096] During help desk collaboration, the help desk collaboration unit can optimize the collaboration algorithm by referring to past inquiry data. The help desk collaboration unit, for example, selects an optimal collaboration algorithm based on past inquiry data. For example, the help desk collaboration unit analyzes past inquiry data and identifies the most effective collaboration algorithm. The help desk collaboration unit can also adjust parameters to improve the accuracy of collaboration based on the past inquiry data. For example, the help desk collaboration unit uses past inquiry data to adjust hyperparameters and improve the accuracy of the collaboration algorithm. The help desk collaboration unit can also analyze past inquiry data to identify areas for improvement in the collaboration algorithm. For example, the help desk collaboration unit uses past inquiry data to evaluate the performance of the algorithm and find areas for improvement. In this way, the collaboration algorithm can be optimized and its accuracy improved by referring to the past inquiry data.

[0097] When coordinating with the help desk, the help desk coordination unit can apply different coordination methods for each category of operation history. For example, the help desk coordination unit applies a coordination method dedicated to navigation to an inquiry related to navigation. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for navigation operations. The help desk coordination unit can also apply a coordination method dedicated to media playback to an inquiry related to media playback. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for media playback operations. The help desk coordination unit can also apply a coordination method dedicated to setting changes to an inquiry related to setting changes. For example, the help desk coordination unit makes an inquiry to the help desk using a coordination method specialized for setting change operations. In this way, by applying different coordination methods to each category of operation history, the accuracy of coordination can be improved.

[0098] The help desk collaboration unit can estimate the user's emotions and determine the priority of inquiries to the help desk based on the estimated user emotions. For example, if the user is feeling stressed, the help desk collaboration unit prioritizes important inquiries. For example, the help desk collaboration unit captures the user's facial expression with a camera, detects stress using an emotion estimation algorithm, and prioritizes important inquiries. The help desk collaboration unit can also prioritize detailed inquiries if the user is relaxed. For example, the help desk collaboration unit records the user's voice, detects the user's relaxed state using voice analysis technology, and prioritizes detailed inquiries. The help desk collaboration unit can also prioritize inquiries that can be handled quickly if the user is in a hurry. For example, the help desk collaboration unit measures the user's heart rate with a sensor, detects the user's state of hurry, and prioritizes inquiries that can be handled quickly. In this way, by determining the priority of inquiries based on the user's emotions, important inquiries can be handled with priority.

[0099] During help desk collaboration, the help desk collaboration unit can weight the linked data based on the time when the operation history was submitted. The help desk collaboration unit, for example, weights the linked data by placing emphasis on recent operation history. For example, the help desk collaboration unit weights recent operation history more highly and older operation history less highly. The help desk collaboration unit can also weight the linked data by placing emphasis on operation history performed during a specific time period. For example, the help desk collaboration unit weights operation history performed by a user during a specific time period more highly. The help desk collaboration unit can also weight the linked data by placing emphasis on operation history performed by a user during a specific event. For example, the help desk collaboration unit weights operation history performed by a user during a specific campaign period more highly. In this way, weighting the linked data based on the time when the operation history was submitted can improve the accuracy of collaboration.

[0100] The help desk collaboration unit can improve the accuracy of collaboration by referring to literature related to the operation history during help desk collaboration. The help desk collaboration unit, for example, refers to technical literature related to the operation history to improve the accuracy of collaboration. For example, the help desk collaboration unit searches a database for technical literature related to the operation history and reflects it in the collaboration algorithm. The help desk collaboration unit can also improve the accuracy of collaboration by referring to a user manual related to the operation history. For example, the help desk collaboration unit analyzes the user manual related to the operation history and uses it as collaboration data. The help desk collaboration unit can also improve the accuracy of collaboration by referring to research papers related to the operation history. For example, the help desk collaboration unit reads research papers related to the operation history and reflects them in the collaboration algorithm. In this way, the accuracy of collaboration can be improved by referring to literature related to the operation history. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, learning unit, guidance unit, problem investigation unit, and help desk linking unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and records the user's operation history in real time and stores it in a database. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a machine learning algorithm to extract patterns from the operation history and predict the user's behavior. The guidance unit is implemented, for example, by the control unit 46A of the smart device 14 and provides text, audio guides, and video tutorials. The problem investigation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes app log files and checks error messages. The help desk linking unit is implemented, for example, by the control unit 46A of the smart device 14 and sends inquiries to the help desk via email or chat. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, learning unit, guidance unit, fault investigation unit, and help desk linkage unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214 and records the user's operation history in real time and stores it in a database. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts patterns from the operation history using a machine learning algorithm to predict the user's behavior. The guidance unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides text, audio guides, and video tutorials. The fault investigation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes app log files and checks error messages. The help desk linkage unit is realized, for example, by the control unit 46A of the smart glasses 214 and sends inquiries to the help desk via email or chat. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, learning unit, guidance unit, problem investigation unit, and help desk linking unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and records the user's operation history in real time and stores it in a database. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a machine learning algorithm to extract patterns from the operation history and predict the user's behavior. The guidance unit is implemented, for example, by the control unit 46A of the headset terminal 314 and provides text, audio guides, and video tutorials. The problem investigation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes app log files and checks error messages. The help desk linking unit is implemented, for example, by the control unit 46A of the headset terminal 314 and sends inquiries to the help desk via email or chat. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, learning unit, guidance unit, problem investigation unit, and help desk linking unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414 and records the user's operation history in real time and stores it in a database. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts patterns from the operation history using a machine learning algorithm and predicts the user's behavior. The guidance unit is realized, for example, by the control unit 46A of the robot 414 and provides text, audio guides, and video tutorials. The problem investigation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the application log file and checks error messages. The help desk linking unit is realized, for example, by the control unit 46A of the robot 414 and sends inquiries to the help desk via email or chat.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The guidance system can also learn the user's preferences and habits based on the user's operation history and provide personalized guidance. For example, if a user frequently uses a specific function, guidance related to that function can be provided preferentially. Also, if a user tends to use the app during a specific time of day, guidance tailored to that time of day can be provided. Furthermore, the system can analyze the user's past operation history and provide guidance based on the success stories of other users who perform similar operations. This can improve user satisfaction by providing personalized guidance based on the user's preferences and habits.

[0103] In addition to the user's operation history, the collection unit can also collect the user's device information and network status. For example, the collection unit can record the user's device type and OS version to identify problems related to a specific device. The collection unit can also monitor the user's network connection status to identify problems caused by network problems. Furthermore, the collection unit can collect the user's device's remaining battery level and storage usage status to analyze whether these factors affect the operation of the app. This allows for more accurate problem investigation by taking the user's device information and network status into consideration.

[0104] The learning unit can also estimate the user's skill level based on the user's operation history and provide guidance of an appropriate level of difficulty. For example, the learning unit can analyze the success rate and operation time of the user's past operations to evaluate the user's skill level. The learning unit can also predict how much support the user will need for a specific operation and provide guidance of an appropriate level of difficulty. Furthermore, the learning unit can adjust the content and format of the guidance according to the user's skill level. This can improve the user's learning effect by providing guidance appropriate to the user's skill level.

[0105] The guidance unit can also estimate the user's emotions and adjust the tone and style of the guidance based on the estimated user's emotions. For example, if the user is feeling stressed, the guidance unit can provide an encouraging message in a gentle tone. If the user is feeling relaxed, the guidance unit can provide guidance including detailed explanations. Furthermore, if the user is in a hurry, the guidance unit can provide concise and quickly understandable guidance. This makes it possible to improve user satisfaction by providing guidance in an appropriate tone and style according to the user's emotions.

[0106] The defect investigation unit can also estimate the user's emotions and determine the priority of defect investigations based on the estimated user emotions. For example, if the user is feeling stressed, it can prioritize investigating important defects. Also, if the user is relaxed, it can conduct detailed defect investigations to improve accuracy. Furthermore, if the user is in a hurry, it can prioritize investigating defects that can be investigated quickly. In this way, by determining the priority of defect investigations based on the user's emotions, it is possible to prioritize investigating important defects.

[0107] The help desk linking unit can also estimate the user's emotions and adjust the content of inquiries to the help desk based on the estimated user emotions. For example, if the user is feeling stressed, it can provide simple and easy-to-understand inquiry content. If the user is relaxed, it can also provide detailed inquiry content. Furthermore, if the user is in a hurry, it can also provide inquiry content that can be quickly responded to. In this way, by adjusting the content of the inquiry based on the user's emotions, it is possible to make more appropriate inquiries.

[0108] The guidance unit can analyze the success rate of operations performed by the user in the past based on the user's operation history, and provide guidance that focuses on operations with a low success rate. For example, if the user frequently fails at a particular operation, detailed guidance for that operation can be provided. Also, if the user takes a long time to perform a particular operation, hints for performing that operation efficiently can be provided. Furthermore, based on the success rate of operations performed by the user in the past, it can also provide guidance on success stories of other users who perform similar operations. In this way, by providing guidance that focuses on the user's operation history, it is possible to improve the user's success rate in operations.

[0109] In addition to the user's operation history, the collection unit can also collect user feedback and improve the method of collecting the operation history. For example, the collection unit can record feedback provided by the user after an operation and adjust the method of collecting the operation history. The collection unit can also collect real-time feedback provided by the user during an operation and immediately improve the collection method. Furthermore, the collection unit can analyze the user's feedback, identify problems with the collection of the operation history, and take measures to improve it. In this way, by utilizing the user's feedback to improve the method of collecting the operation history, more accurate data can be collected.

[0110] The learning unit can also predict a user's behavioral patterns based on the user's operation history and provide guidance based on the predicted behavior. For example, the learning unit can predict the next operation the user will perform after performing a specific operation and provide guidance for that operation in advance. The learning unit can also predict the operation the user will perform during a specific time period and provide guidance tailored to that time period. Furthermore, the learning unit can analyze the behavioral patterns of other users who perform similar operations based on the user's past operation history and provide optimal guidance. In this way, by predicting the user's behavioral patterns and providing guidance, the user's operation efficiency can be improved.

[0111] The guidance unit can also estimate the user's emotions and adjust the length of the guidance based on the estimated user's emotions. For example, if the user is feeling stressed, short, to-the-point guidance can be provided. If the user is relaxed, longer guidance including detailed explanations can be provided. Furthermore, if the user is in a hurry, short guidance that can be quickly understood can be provided. In this way, by adjusting the length of the guidance based on the user's emotions, more appropriate guidance can be provided.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The collection unit collects the user's operation history. The user's operation history includes clicks, scrolls, input contents, etc. The collection unit records the user's operations within the app in real time and stores them in a database. The collection unit can also periodically back up the user's operation history to prevent data loss. Step 2: The learning unit learns based on the collected operation history, past operation history, and screen transitions. The learning unit uses machine learning algorithms to extract patterns from the operation history and predict user behavior. Deep learning technology can also be used to build more advanced predictive models. Step 3: The guidance unit provides the user with optimal guidance based on the information obtained by the learning unit. The guidance unit can provide operation instructions in text format, as well as audio guides and video tutorials. It can also provide real-time guidance on the next operation to be performed based on the user's operation history. Step 4: The Problem Investigation Department automatically conducts an investigation when the Problem Investigation button is pressed to check for any problems. The Problem Investigation Department analyzes the app's log files and checks for error messages. It can also monitor the app's operation status in real time to detect signs of problems. Step 5: If no problem is found, the Help Desk Integration Unit automatically sends an inquiry to the Help Desk. The Help Desk Integration Unit can send an inquiry to the Help Desk via email or chat, and can also automatically make an inquiry by phone.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0116] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 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.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0148] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0157] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0158] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0168] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0169] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0170] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0171] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0172] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0174] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0175] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0176] 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.

[0177] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0178] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0179] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0180] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0181] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0182] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0183] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0184] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0185] [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects operation histories; a learning unit that performs learning based on the operation history collected by the collection unit; a guidance unit that provides guidance based on the information obtained by the learning unit; a defect investigation unit that investigates defects based on the guidance provided by the guidance unit; a help desk cooperation unit that automatically inquires at a help desk when no defect is found by the defect investigation unit; A system characterized by:

2. The collecting unit Collect user operation history The system of claim 1 .

3. The learning unit Learning is performed based on collected operation history and past operation history or screen transitions The system of claim 1 .

4. The guide unit is Based on the information obtained by the learning unit, optimal guidance is provided to the user. The system of claim 1 .

5. The defect investigation unit When the defect investigation button is pressed, an investigation is automatically performed to check for any defects. The system of claim 1 .

6. The help desk collaboration unit: Automatically contact the help desk if no issues are found The system of claim 1 .

7. The collecting unit The system estimates the user's emotions and adjusts the timing of collecting operation history based on the estimated user emotions. The system of claim 1 .

8. The collecting unit Analyze the user's past operation history and select the optimal collection method The system of claim 1 .

9. The collecting unit When collecting operation history, filtering is performed based on the user's current app usage and areas of interest. The system of claim 1 .

Images