JP7796834B2 - system - Google Patents

Description

The technology disclosed herein relates to a system.

Patent document 1 discloses a persona chatbot control method executed 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's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Japanese Patent Application Laid-Open No. 2022-180282

With conventional technology, product instruction manuals were long and difficult to understand, making repair work difficult.

The system in this embodiment aims to summarize product instruction manuals and repair products using robots.

The system according to the embodiment includes an acquisition unit, a summarization unit, and a repair unit. The acquisition unit acquires the contents of the product's instruction manual. The summarization unit summarizes the contents of the instruction manual acquired by the acquisition unit using a generation AI. The repair unit operates a robot using the generation AI to repair the product based on the contents summarized by the summarization unit.

The system in accordance with the embodiment can summarize product instruction manuals and repair products using robots.

1 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a first embodiment. 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. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a second embodiment. 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. FIG. 10 is a conceptual diagram illustrating an example of the configuration of a data processing system according to a third embodiment. 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. FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. 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. 1 shows an emotion map onto which multiple emotions are mapped. 1 shows an emotion map onto which multiple emotions are mapped.

Below, an example of an embodiment of a system relating to the technology disclosed herein will be described with reference to the accompanying drawings.

First, let me explain the terminology used in the following explanation.

In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, a processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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).

In the following embodiments, coded random access memory (RAM) is memory in which information is temporarily stored and is used as work memory by the processor.

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

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

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 A alone, B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and/or B" also applies when three or more things are expressed connected by "and/or."

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

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, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

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 (e.g., a pen or a finger) to receive user input via the pointer. The microphone 38B detects the user's voice to receive user input via 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 Figure 2) acquires the data indicating the user input.

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

The communication I/F 44 is connected to the 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.

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

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

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 the 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 emotions, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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 communicates with the server device having the data generation model 58 to obtain processing results (prediction results, etc.) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

(Example 1)
A repair assistance system according to an embodiment of the present invention analyzes and summarizes a product's instruction manual and operates a robot to perform repairs. This repair assistance system analyzes the product's instruction manual using a camera, and a generation AI summarizes the contents. Then, the system operates a robot to repair the product based on the contents summarized by the generation AI. For example, when a user photographs a product's instruction manual with a camera, the system acquires the contents and the generation AI summarizes them. Based on the summarized contents, the robot's hands operate and repair the product. Furthermore, the user can input symptoms of the product's malfunction, and this information is also reflected in the repair. This allows the repair assistance system to analyze and summarize the product's instruction manual and operate a robot to perform repairs.

The repair assistance system according to the embodiment includes an acquisition unit, a summarization unit, and a repair unit. The acquisition unit acquires the contents of a product's instruction manual. For example, the acquisition unit uses a camera to photograph the instruction manual and acquire the image data. The acquisition unit can also directly acquire a digital instruction manual. For example, the acquisition unit acquires an instruction manual in PDF or text format. The summarization unit uses a generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using a text generation AI (e.g., LLM). For example, the generation AI receives a prompt such as, "Please summarize the main points of this instruction manual," and generates a summary. The repair unit uses the generation AI to operate a robot to repair the product based on the content summarized by the summarization unit. The repair unit, for example, operates a robotic hand to repair the product. The robotic hand, for example, has an arm capable of precise movement and performs accurate repairs based on the instruction manual. This allows the repair assistance system to analyze and summarize the product's instruction manual and activate the robot to perform the repair.

The acquisition unit acquires the contents of the product's instruction manual. For example, the acquisition unit uses a camera to photograph the instruction manual and acquires the image data. Specifically, the acquisition unit uses a high-resolution camera to photograph each page of the instruction manual and performs character recognition using image processing technology. This allows the contents of the instruction manual to be acquired as digital data. The acquisition unit can also acquire digital instruction manuals directly. For example, the acquisition unit acquires instruction manuals in PDF or text format. This includes downloading them from the Internet or reading them from external storage devices such as USB memory. The acquisition unit can also acquire instruction manuals from cloud storage services, ensuring that the latest instruction manuals are always available. The acquisition unit centrally manages this data and can connect with other departments and systems as needed. For example, the acquired instruction manual data is stored on a cloud server and made accessible to the summary department and repair department. The acquisition unit also has the function of classifying the contents of instruction manuals, allowing for quick search for instruction manuals for specific products. This allows the acquisition unit to acquire instruction manual contents efficiently and effectively, improving overall system performance.

The summarization unit uses the generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using text generation AI (e.g., LLM). Specifically, the generation AI analyzes the text of the instruction manual using natural language processing technology and extracts important keywords and phrases. Next, based on these keywords and phrases, it generates a summary that concisely summarizes the key points of the instruction manual. For example, the generation AI receives a prompt such as, "Please summarize the key points of this instruction manual," and generates a summary. The generation AI can learn from data from past instruction manuals and user feedback to improve the accuracy of the summary. Furthermore, the summarization unit provides the generated summary to the user, allowing the user to quickly obtain the information they need. For example, the summarization unit displays the summary on a smartphone or tablet for easy user access. The summarization unit also has a function to read the summary content aloud, making it accessible to visually impaired users. This allows the summarization unit to efficiently summarize the contents of the retrieved instruction manual and provide it in a format that is easy for the user to use.

The repair department uses the generative AI to operate a robot to repair the product based on the content summarized by the summarization department. The repair department, for example, operates the robot's hand to repair the product. Specifically, the robot's hand is equipped with an arm capable of precise movement and accurately performs repairs based on the instruction manual. The generative AI analyzes the summarized content of the instruction manual and instructs the robot on the repair procedure. For example, the generative AI receives a prompt such as, "Please tell me the repair procedure for this product" and generates a repair procedure. The generative AI can study past repair data and the contents of the instruction manual to propose the optimal repair procedure. The repair department controls the robot's arm based on the generated repair procedure to perform precise repair work. For example, the robot's arm can accurately perform operations such as turning screws, removing parts, and installing parts. Furthermore, the repair department can monitor the progress of the repair work in real time and respond immediately if an abnormality occurs. For example, if the robot's sensor detects an abnormality, the repair work is paused, the cause of the abnormality is identified, and the problem is corrected. The repair department also records the repair work history and can use it as a reference for future repair work. This allows the repair department to repair products efficiently and accurately based on the summarized contents of the instruction manual.

The repair department can operate the robotic hand to repair the product. The robotic hand, for example, is equipped with an arm capable of precise movement and performs repairs accurately based on the instruction manual. For example, the robotic hand can remove parts from the product and install new parts. The robotic hand can also inspect the inside of the product and identify the defective part. Furthermore, the robotic hand can check the operation of the product and determine whether the repair is complete. In this way, product repairs can be automated by operating the robotic hand.

The reception unit can accept input of information indicating the product's malfunction symptoms from the user. The repair unit can operate the robot based on the summarized content and the information accepted by the reception unit. The reception unit, for example, accepts input of the malfunction symptoms by the user in text format. The reception unit can also accept input of the malfunction symptoms by the user in image format. The reception unit can also accept input of the malfunction symptoms by the user in voice format. For example, if the user inputs "The product won't turn on," the reception unit accepts that information. The repair unit operates the robot to perform repairs based on the information accepted by the reception unit. For example, the repair unit operates the robot's hands to repair the product's power supply based on the malfunction symptoms entered by the user. This allows for more accurate repairs to be performed based on the information entered by the user.

When acquiring an instruction manual, the acquisition unit can analyze the user's past repair history and select an acquisition method. For example, the acquisition unit may prioritize acquiring instruction manuals for products that the user has previously repaired. The acquisition unit may also prioritize acquiring instruction manuals for specific brands or models based on the user's past repair history. Furthermore, the acquisition unit can analyze the user's past repair history and select the most efficient acquisition method. For example, the acquisition unit may search a database for instruction manuals for products that the user has previously repaired and acquire them preferentially. This makes it possible to provide the most optimal method for acquiring an instruction manual by taking the user's past repair history into consideration. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

When acquiring instruction manuals, the acquisition unit can filter them based on the user's repair skill level. For example, if the user is a beginner, the acquisition unit can prioritize acquiring simple instruction manuals. The acquisition unit can also acquire detailed instruction manuals if the user is an intermediate user. Furthermore, the acquisition unit can acquire specialized instruction manuals if the user is an advanced user. For example, the acquisition unit can acquire the user's repair skill level from a database and filter and provide instruction manuals according to that level. This can improve the success rate of repairs by providing instruction manuals according to the user's repair skill level. Some or all of the above-mentioned processing by the acquisition unit can be performed, for example, using AI, or can be performed without using AI.

When acquiring instruction manuals, the acquisition unit can prioritize acquiring highly relevant instruction manuals based on the user's geographical location information. For example, if the user is in a specific area, the acquisition unit can prioritize acquiring instruction manuals for products sold in that area. Also, if the user is traveling, the acquisition unit can prioritize acquiring instruction manuals for products to be used at the user's destination. Furthermore, the acquisition unit can acquire the most relevant instruction manuals based on the user's geographical location information. For example, the acquisition unit can acquire the user's geographical location information from GPS data and filter and provide instruction manuals based on that information. In this way, highly relevant instruction manuals can be provided by taking the user's geographical location information into consideration. Some or all of the above-described processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

When acquiring instruction manuals, the acquisition unit can acquire relevant instruction manuals based on the user's social media activity. For example, the acquisition unit may prioritize acquiring instruction manuals for products mentioned by the user on social media. The acquisition unit can also acquire instruction manuals for products in which the user is interested based on the user's social media activity. Furthermore, the acquisition unit can analyze the user's social media activity to acquire the most relevant instruction manuals. For example, the acquisition unit may analyze the content of the user's social media posts and filter and provide instruction manuals based on that information. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant instruction manuals. Some or all of the above-described processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

When generating a summary, the summarizing unit can adjust the level of detail of the summary based on the importance of the instruction manual. For example, in the case of an important instruction manual, the summarizing unit generates a detailed summary. In the case of a general instruction manual, the summarizing unit can also generate a concise summary. Furthermore, the summarizing unit can adjust the level of detail of the summary depending on the importance of the instruction manual. For example, the summarizing unit obtains the importance of the instruction manual from a database and adjusts the level of detail of the summary based on that information. In this way, by adjusting the level of detail of the summary depending on the importance of the instruction manual, it is possible to provide the necessary information appropriately. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When generating a summary, the summarization unit can apply different summarization algorithms based on the category of the instruction manual. For example, in the case of an instruction manual for an electronic device, the summarization unit can apply a technical summarization algorithm. In the case of an instruction manual for furniture, the summarization unit can also apply a summarization algorithm specialized for assembly procedures. Furthermore, the summarization unit can apply the optimal summarization algorithm depending on the category of the instruction manual. For example, the summarization unit can obtain the category of the instruction manual from a database and select a summarization algorithm based on that information. In this way, the optimal summary can be provided by applying a summarization algorithm depending on the category of the instruction manual. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When generating summaries, the summarizing unit can determine the priority of summaries based on the publication date of the instruction manual. For example, the summarizing unit prioritizes summarizing the most recent instruction manual. The summarizing unit can also lower the priority of summaries for older instruction manuals. Furthermore, the summarizing unit can determine the priority of summaries based on the publication date of the instruction manual. For example, the summarizing unit obtains the publication date of the instruction manual from a database and determines the priority of summaries based on that information. In this way, by determining the priority of summaries based on the publication date of the instruction manual, it is possible to provide the most recent information preferentially. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When generating summaries, the summarizing unit can adjust the order of summaries based on the relevance of the instruction manual. For example, the summarizing unit summarizes the most relevant parts first. The summarizing unit can also postpone summarizing less relevant parts. Furthermore, the summarizing unit can adjust the order of summaries based on the relevance of the instruction manual. For example, the summarizing unit obtains the relevance of the instruction manual from a database and adjusts the order of summaries based on that information. In this way, by adjusting the order of summaries based on the relevance of the instruction manual, important information can be provided preferentially. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When repairing, the repair department can analyze the user's past repair history and select a repair method. For example, the repair department may refer to repair methods used by the user on products that have been repaired in the past. The repair department can also select the most effective repair method from the user's past repair history. Furthermore, the repair department can analyze the user's past repair history and select the optimal repair method. For example, the repair department may obtain the user's past repair history from a database and select a repair method based on that information. This makes it possible to provide the optimal repair method by taking the user's past repair history into consideration. Some or all of the above-mentioned processing in the repair department may be performed, for example, using generation AI, or may be performed without using generation AI.

When performing repairs, the repair unit can customize repair procedures based on the user's repair skill level. For example, if the user is a beginner, the repair unit can provide simple repair procedures. If the user is an intermediate repairer, the repair unit can also provide detailed repair procedures. Furthermore, if the user is an advanced repairer, the repair unit can also provide specialized repair procedures. For example, the repair unit can obtain the user's repair skill level from a database and customize and provide repair procedures according to that level. In this way, by providing repair procedures according to the user's repair skill level, the success rate of repairs can be improved. Some or all of the above-mentioned processing in the repair unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When performing repairs, the repair unit can select a repair method based on the user's geographical location information. For example, if the user is in a specific area, the repair unit selects a repair method available in that area. Also, if the user is traveling, the repair unit can select a repair method available at the user's travel destination. Furthermore, the repair unit can select the optimal repair method based on the user's geographical location information. For example, the repair unit obtains the user's geographical location information from GPS data and selects a repair method based on that information. In this way, the optimal repair method can be provided by taking the user's geographical location information into consideration. Some or all of the above-mentioned processing in the repair unit may be performed, for example, using AI, or may be performed without using AI.

When making repairs, the repair department can suggest repair procedures based on the user's social media activity. For example, the repair department can suggest repair procedures for products that the user has mentioned on social media. The repair department can also suggest repair procedures for products that the user is interested in based on their social media activity. Furthermore, the repair department can analyze the user's social media activity and suggest the most relevant repair procedures. For example, the repair department can analyze the content of the user's social media posts and suggest repair procedures based on that information. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant repair procedures. Some or all of the above-mentioned processing in the repair department may be performed, for example, using AI, or may be performed without using AI.

When entering malfunction information, the reception unit can select an input method based on the user's past malfunction history. For example, the reception unit automatically displays malfunction information that the user has frequently entered in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest an input method to be used during a specific time period based on the user's past malfunction history. For example, the reception unit can obtain the user's past malfunction history from a database and select an input method based on that information. This makes it possible to provide the optimal input method by taking the user's past malfunction history into consideration. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

When entering malfunction information, the reception unit can select an input method based on the user's device information. For example, if the user is using a smartphone, the reception unit can provide an input method that matches the screen size. Furthermore, if the user is using a tablet, the reception unit can also provide an input method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the reception unit can also provide an input method that is simple and highly visible. For example, the reception unit obtains the user's device information from a database and selects an input method based on that information. In this way, the optimal input method can be provided by taking the user's device information into consideration. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

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

The repair assistance system can further include a diagnostic unit. The diagnostic unit analyzes sensor data to identify the location of a product failure. For example, the diagnostic unit acquires data such as temperature, vibration, and current from sensors installed inside the product and detects abnormalities. The diagnostic unit can also identify the cause of the failure by comparing it with past failure data. Furthermore, the diagnostic unit can detect signs of failure and suggest preventive repairs. This enables the repair assistance system to achieve early detection and prevention of failures, extending the lifespan of products.

When operating the robot's hand, the repair department can refer to the user's repair history to select the optimal repair procedure. For example, the repair department can refer to a database of products that the user has previously repaired and suggest the optimal repair procedure if a similar malfunction occurs. The repair department can also analyze the probability that a specific repair procedure will be successful from the user's repair history and select that procedure as a priority. Furthermore, the repair department can customize the repair procedure based on the user's repair history and provide the user with the most efficient repair method. This allows the repair department to utilize the user's past experience to achieve more effective repairs.

The acquisition unit can prioritize acquiring highly relevant instruction manuals based on the user's geographical location information. For example, if the user is in a specific area, instruction manuals for products sold in that area can be acquired preferentially. Also, if the user is traveling, instruction manuals for products to be used at the user's destination can be acquired preferentially. Furthermore, the acquisition unit can acquire the most relevant instruction manuals based on the user's geographical location information. This makes it possible to provide highly relevant instruction manuals by taking the user's geographical location information into consideration.

When repairing, the repair department can customize repair procedures based on the user's repair skill level. For example, if the user is a beginner, simple repair procedures can be provided. If the user is an intermediate user, detailed repair procedures can be provided. Furthermore, if the user is an advanced user, specialized repair procedures can be provided. This can improve the success rate of repairs by providing repair procedures that are appropriate for the user's repair skill level.

When repairing a product, the repair department can analyze the user's past repair history and select a repair method. For example, they can refer to the repair methods used by the user on products they have previously repaired. They can also select the most effective repair method from the user's past repair history. They can also analyze the user's past repair history and select the optimal repair method. This makes it possible to provide the optimal repair method by taking the user's past repair history into consideration.

When retrieving instruction manuals, the retrieval unit can retrieve relevant instruction manuals based on the user's social media activity. For example, it can prioritize retrieving instruction manuals for products that the user has mentioned on social media. It can also retrieve instruction manuals for products that the user is interested in based on the user's social media activity. It can also analyze the user's social media activity and retrieve the most relevant instruction manuals. This makes it possible to provide highly relevant instruction manuals by analyzing the user's social media activity.

When generating a summary, the summarization unit can apply different summarization algorithms based on the category of the instruction manual. For example, for an instruction manual for an electronic device, a technical summarization algorithm can be applied. For an instruction manual for furniture, a summarization algorithm specialized for assembly instructions can be applied. Furthermore, the most appropriate summarization algorithm can be applied depending on the category of the instruction manual. This makes it possible to provide the most appropriate summary by applying a summarization algorithm according to the category of the instruction manual.

The processing flow for Example 1 is briefly explained below.

Step 1: The acquisition unit acquires the contents of the product's instruction manual. For example, the acquisition unit may take a photograph of the instruction manual using a camera and acquire the image data. The acquisition unit may also directly acquire a digital instruction manual. For example, the acquisition unit may acquire an instruction manual in PDF format or text format.
Step 2: The summarization unit uses the generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using a text generation AI (e.g., LLM). For example, the generation AI receives a prompt such as "Please summarize the main points of this instruction manual" and generates a summary.
Step 3: The repair unit uses the generative AI to operate a robot based on the content summarized by the summarization unit to repair the product. The repair unit operates, for example, the robot's hand to repair the product. The robot's hand has, for example, an arm capable of precise movement, and accurately performs repairs based on the instruction manual.

(Example 2)
A repair assistance system according to an embodiment of the present invention analyzes and summarizes a product's instruction manual and operates a robot to perform repairs. This repair assistance system analyzes the product's instruction manual using a camera, and a generation AI summarizes the contents. Then, the system operates a robot to repair the product based on the contents summarized by the generation AI. For example, when a user photographs a product's instruction manual with a camera, the system acquires the contents and the generation AI summarizes them. Based on the summarized contents, the robot's hands operate and repair the product. Furthermore, the user can input symptoms of the product's malfunction, and this information is also reflected in the repair. This allows the repair assistance system to analyze and summarize the product's instruction manual and operate a robot to perform repairs.

The repair assistance system according to the embodiment includes an acquisition unit, a summarization unit, and a repair unit. The acquisition unit acquires the contents of a product's instruction manual. For example, the acquisition unit uses a camera to photograph the instruction manual and acquire the image data. The acquisition unit can also directly acquire a digital instruction manual. For example, the acquisition unit acquires an instruction manual in PDF or text format. The summarization unit uses a generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using a text generation AI (e.g., LLM). For example, the generation AI receives a prompt such as, "Please summarize the main points of this instruction manual," and generates a summary. The repair unit uses the generation AI to operate a robot to repair the product based on the content summarized by the summarization unit. The repair unit, for example, operates a robotic hand to repair the product. The robotic hand, for example, has an arm capable of precise movement and performs accurate repairs based on the instruction manual. This allows the repair assistance system to analyze and summarize the product's instruction manual and activate the robot to perform the repair.

The acquisition unit acquires the contents of the product's instruction manual. For example, the acquisition unit uses a camera to photograph the instruction manual and acquires the image data. Specifically, the acquisition unit uses a high-resolution camera to photograph each page of the instruction manual and performs character recognition using image processing technology. This allows the contents of the instruction manual to be acquired as digital data. The acquisition unit can also acquire digital instruction manuals directly. For example, the acquisition unit acquires instruction manuals in PDF or text format. This includes downloading them from the Internet or reading them from external storage devices such as USB memory. The acquisition unit can also acquire instruction manuals from cloud storage services, ensuring that the latest instruction manuals are always available. The acquisition unit centrally manages this data and can connect with other departments and systems as needed. For example, the acquired instruction manual data is stored on a cloud server and made accessible to the summary department and repair department. The acquisition unit also has the function of classifying the contents of instruction manuals, allowing for quick search for instruction manuals for specific products. This allows the acquisition unit to acquire instruction manual contents efficiently and effectively, improving overall system performance.

The summarization unit uses the generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using text generation AI (e.g., LLM). Specifically, the generation AI analyzes the text of the instruction manual using natural language processing technology and extracts important keywords and phrases. Next, based on these keywords and phrases, it generates a summary that concisely summarizes the key points of the instruction manual. For example, the generation AI receives a prompt such as, "Please summarize the key points of this instruction manual," and generates a summary. The generation AI can learn from data from past instruction manuals and user feedback to improve the accuracy of the summary. Furthermore, the summarization unit provides the generated summary to the user, allowing the user to quickly obtain the information they need. For example, the summarization unit displays the summary on a smartphone or tablet for easy user access. The summarization unit also has a function to read the summary content aloud, making it accessible to visually impaired users. This allows the summarization unit to efficiently summarize the contents of the retrieved instruction manual and provide it in a format that is easy for the user to use.

The repair department uses the generative AI to operate a robot to repair the product based on the content summarized by the summarization department. The repair department, for example, operates the robot's hand to repair the product. Specifically, the robot's hand is equipped with an arm capable of precise movement and accurately performs repairs based on the instruction manual. The generative AI analyzes the summarized content of the instruction manual and instructs the robot on the repair procedure. For example, the generative AI receives a prompt such as, "Please tell me the repair procedure for this product" and generates a repair procedure. The generative AI can study past repair data and the contents of the instruction manual to propose the optimal repair procedure. The repair department controls the robot's arm based on the generated repair procedure to perform precise repair work. For example, the robot's arm can accurately perform operations such as turning screws, removing parts, and installing parts. Furthermore, the repair department can monitor the progress of the repair work in real time and respond immediately if an abnormality occurs. For example, if the robot's sensor detects an abnormality, the repair work is paused, the cause of the abnormality is identified, and the problem is corrected. The repair department also records the repair work history and can use it as a reference for future repair work. This allows the repair department to repair products efficiently and accurately based on the summarized contents of the instruction manual.

The repair department can operate the robotic hand to repair the product. The robotic hand, for example, is equipped with an arm capable of precise movement and performs repairs accurately based on the instruction manual. For example, the robotic hand can remove parts from the product and install new parts. The robotic hand can also inspect the inside of the product and identify the defective part. Furthermore, the robotic hand can check the operation of the product and determine whether the repair is complete. In this way, product repairs can be automated by operating the robotic hand.

The reception unit can accept input of information indicating the product's malfunction symptoms from the user. The repair unit can operate the robot based on the summarized content and the information accepted by the reception unit. The reception unit, for example, accepts input of the malfunction symptoms by the user in text format. The reception unit can also accept input of the malfunction symptoms by the user in image format. The reception unit can also accept input of the malfunction symptoms by the user in voice format. For example, if the user inputs "The product won't turn on," the reception unit accepts that information. The repair unit operates the robot to perform repairs based on the information accepted by the reception unit. For example, the repair unit operates the robot's hands to repair the product's power supply based on the malfunction symptoms entered by the user. This allows for more accurate repairs to be performed based on the information entered by the user.

The acquisition unit can estimate the user's emotions and adjust the timing of acquiring the instruction manual based on the emotions. The acquisition unit, for example, captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the acquisition unit can immediately acquire the instruction manual and begin analysis. Alternatively, if the user is relaxed, the acquisition unit can wait for the user's instructions before acquiring the instruction manual. Furthermore, if the user is in a hurry, the acquisition unit can quickly acquire the instruction manual. This allows the user's stress to be reduced by adjusting the timing of acquiring the instruction manual according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When acquiring an instruction manual, the acquisition unit can analyze the user's past repair history and select an acquisition method. For example, the acquisition unit may prioritize acquiring instruction manuals for products that the user has previously repaired. The acquisition unit may also prioritize acquiring instruction manuals for specific brands or models based on the user's past repair history. Furthermore, the acquisition unit can analyze the user's past repair history and select the most efficient acquisition method. For example, the acquisition unit may search a database for instruction manuals for products that the user has previously repaired and acquire them preferentially. This makes it possible to provide the most optimal method for acquiring an instruction manual by taking the user's past repair history into consideration. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

When acquiring instruction manuals, the acquisition unit can filter them based on the user's repair skill level. For example, if the user is a beginner, the acquisition unit can prioritize acquiring simple instruction manuals. The acquisition unit can also acquire detailed instruction manuals if the user is an intermediate user. Furthermore, the acquisition unit can acquire specialized instruction manuals if the user is an advanced user. For example, the acquisition unit can acquire the user's repair skill level from a database and filter and provide instruction manuals according to that level. This can improve the success rate of repairs by providing instruction manuals according to the user's repair skill level. Some or all of the above-mentioned processing by the acquisition unit can be performed, for example, using AI, or can be performed without using AI.

The acquisition unit can estimate the user's emotions and determine the priority of the instruction manuals to be acquired based on the emotions. The acquisition unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, if the user is feeling stressed, the acquisition unit may prioritize acquiring simple instruction manuals. Alternatively, if the user is relaxed, the acquisition unit may also acquire detailed instruction manuals. Furthermore, if the user is in a hurry, the acquisition unit may prioritize acquiring instruction manuals containing the most important parts. In this way, by determining the priority of instruction manuals according to the user's emotions, it is possible to provide information that meets the user's needs. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When acquiring instruction manuals, the acquisition unit can prioritize acquiring highly relevant instruction manuals based on the user's geographical location information. For example, if the user is in a specific area, the acquisition unit can prioritize acquiring instruction manuals for products sold in that area. Also, if the user is traveling, the acquisition unit can prioritize acquiring instruction manuals for products to be used at the user's destination. Furthermore, the acquisition unit can acquire the most relevant instruction manuals based on the user's geographical location information. For example, the acquisition unit can acquire the user's geographical location information from GPS data and filter and provide instruction manuals based on that information. In this way, highly relevant instruction manuals can be provided by taking the user's geographical location information into consideration. Some or all of the above-described processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

When acquiring instruction manuals, the acquisition unit can acquire relevant instruction manuals based on the user's social media activity. For example, the acquisition unit may prioritize acquiring instruction manuals for products mentioned by the user on social media. The acquisition unit can also acquire instruction manuals for products in which the user is interested based on the user's social media activity. Furthermore, the acquisition unit can analyze the user's social media activity to acquire the most relevant instruction manuals. For example, the acquisition unit may analyze the content of the user's social media posts and filter and provide instruction manuals based on that information. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant instruction manuals. Some or all of the above-described processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI.

The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the emotions. For example, the summarization unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the summarization unit generates a concise and easy-to-understand summary. The summarization unit can also generate a detailed summary if the user is relaxed. Furthermore, if the user is in a hurry, the summarization unit can generate a summary that highlights the most important parts. In this way, by adjusting the way the summary is presented based on the user's emotions, it is possible to provide a summary that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When generating a summary, the summarizing unit can adjust the level of detail of the summary based on the importance of the instruction manual. For example, in the case of an important instruction manual, the summarizing unit generates a detailed summary. In the case of a general instruction manual, the summarizing unit can also generate a concise summary. Furthermore, the summarizing unit can adjust the level of detail of the summary depending on the importance of the instruction manual. For example, the summarizing unit obtains the importance of the instruction manual from a database and adjusts the level of detail of the summary based on that information. In this way, by adjusting the level of detail of the summary depending on the importance of the instruction manual, it is possible to provide the necessary information appropriately. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When generating a summary, the summarization unit can apply different summarization algorithms based on the category of the instruction manual. For example, in the case of an instruction manual for an electronic device, the summarization unit can apply a technical summarization algorithm. In the case of an instruction manual for furniture, the summarization unit can also apply a summarization algorithm specialized for assembly procedures. Furthermore, the summarization unit can apply the optimal summarization algorithm depending on the category of the instruction manual. For example, the summarization unit can obtain the category of the instruction manual from a database and select a summarization algorithm based on that information. In this way, the optimal summary can be provided by applying a summarization algorithm depending on the category of the instruction manual. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using generation AI, or may be performed without using generation AI.

The summarization unit can estimate the user's emotions and adjust the length of the summary based on the emotions. For example, the summarization unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the summarization unit generates a short, concise summary. If the user is relaxed, the summarization unit can also generate a detailed summary. Furthermore, if the user is in a hurry, the summarization unit can generate a short summary that highlights the most important parts. In this way, by adjusting the length of the summary according to the user's emotions, it is possible to provide an optimal summary for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When generating summaries, the summarizing unit can determine the priority of summaries based on the publication date of the instruction manual. For example, the summarizing unit prioritizes summarizing the most recent instruction manual. The summarizing unit can also lower the priority of summaries for older instruction manuals. Furthermore, the summarizing unit can determine the priority of summaries based on the publication date of the instruction manual. For example, the summarizing unit obtains the publication date of the instruction manual from a database and determines the priority of summaries based on that information. In this way, by determining the priority of summaries based on the publication date of the instruction manual, it is possible to provide the most recent information preferentially. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

When generating summaries, the summarizing unit can adjust the order of summaries based on the relevance of the instruction manual. For example, the summarizing unit summarizes the most relevant parts first. The summarizing unit can also postpone summarizing less relevant parts. Furthermore, the summarizing unit can adjust the order of summaries based on the relevance of the instruction manual. For example, the summarizing unit obtains the relevance of the instruction manual from a database and adjusts the order of summaries based on that information. In this way, by adjusting the order of summaries based on the relevance of the instruction manual, important information can be provided preferentially. Some or all of the above-mentioned processing in the summarizing unit may be performed, for example, using generation AI, or may be performed without using generation AI.

The repair unit can estimate the user's emotions and adjust the repair method based on the emotions. For example, the repair unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the repair unit selects a simple and quick repair method. The repair unit can also provide detailed repair procedures if the user is relaxed. Furthermore, the repair unit can select the most efficient repair method if the user is in a hurry. In this way, by adjusting the repair method according to the user's emotions, it is possible to provide the optimal repair method for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be text generation AI (e.g., LLM) or multimodal generation AI, but is not limited to these examples.

When repairing, the repair department can analyze the user's past repair history and select a repair method. For example, the repair department may refer to repair methods used by the user on products that have been repaired in the past. The repair department can also select the most effective repair method from the user's past repair history. Furthermore, the repair department can analyze the user's past repair history and select the optimal repair method. For example, the repair department may obtain the user's past repair history from a database and select a repair method based on that information. This makes it possible to provide the optimal repair method by taking the user's past repair history into consideration. Some or all of the above-mentioned processing in the repair department may be performed, for example, using generation AI, or may be performed without using generation AI.

When performing repairs, the repair unit can customize repair procedures based on the user's repair skill level. For example, if the user is a beginner, the repair unit can provide simple repair procedures. If the user is an intermediate repairer, the repair unit can also provide detailed repair procedures. Furthermore, if the user is an advanced repairer, the repair unit can also provide specialized repair procedures. For example, the repair unit can obtain the user's repair skill level from a database and customize and provide repair procedures according to that level. In this way, by providing repair procedures according to the user's repair skill level, the success rate of repairs can be improved. Some or all of the above-mentioned processing in the repair unit may be performed, for example, using generation AI, or may be performed without using generation AI.

The repair unit can estimate the user's emotions and determine repair priorities based on the emotions. The repair unit, for example, captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the repair unit can prioritize the simplest repairs. Alternatively, if the user is relaxed, the repair unit can prioritize detailed repairs. Furthermore, if the user is in a hurry, the repair unit can prioritize the most important repairs. In this way, repair priorities can be determined according to the user's emotions, making it possible to provide repairs that meet the user's needs. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When performing repairs, the repair unit can select a repair method based on the user's geographical location information. For example, if the user is in a specific area, the repair unit selects a repair method available in that area. Also, if the user is traveling, the repair unit can select a repair method available at the user's travel destination. Furthermore, the repair unit can select the optimal repair method based on the user's geographical location information. For example, the repair unit obtains the user's geographical location information from GPS data and selects a repair method based on that information. In this way, the optimal repair method can be provided by taking the user's geographical location information into consideration. Some or all of the above-mentioned processing in the repair unit may be performed, for example, using AI, or may be performed without using AI.

When making repairs, the repair department can suggest repair procedures based on the user's social media activity. For example, the repair department can suggest repair procedures for products that the user has mentioned on social media. The repair department can also suggest repair procedures for products that the user is interested in based on their social media activity. Furthermore, the repair department can analyze the user's social media activity and suggest the most relevant repair procedures. For example, the repair department can analyze the content of the user's social media posts and suggest repair procedures based on that information. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant repair procedures. Some or all of the above-mentioned processing in the repair department may be performed, for example, using AI, or may be performed without using AI.

The reception unit can estimate the user's emotions and adjust the input method for malfunction information based on the emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize the input steps. Alternatively, if the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and enable the user to input malfunction information quickly. In this way, by adjusting the input method for malfunction information according to the user's emotions, an easy-to-use interface for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When entering malfunction information, the reception unit can select an input method based on the user's past malfunction history. For example, the reception unit automatically displays malfunction information that the user has frequently entered in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest an input method to be used during a specific time period based on the user's past malfunction history. For example, the reception unit can obtain the user's past malfunction history from a database and select an input method based on that information. This makes it possible to provide the optimal input method by taking the user's past malfunction history into consideration. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

The reception unit can estimate the user's emotions and prioritize the malfunction information based on the emotions. The reception unit, for example, captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, if the user is feeling stressed, the reception unit may prioritize processing the simplest malfunction information. Alternatively, if the user is relaxed, the reception unit may prioritize processing detailed malfunction information. Furthermore, if the user is in a hurry, the reception unit may prioritize processing the most important malfunction information. This allows for a response that meets the user's needs by prioritizing the malfunction information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

When entering malfunction information, the reception unit can select an input method based on the user's device information. For example, if the user is using a smartphone, the reception unit can provide an input method that matches the screen size. Furthermore, if the user is using a tablet, the reception unit can also provide an input method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the reception unit can also provide an input method that is simple and highly visible. For example, the reception unit obtains the user's device information from a database and selects an input method based on that information. In this way, the optimal input method can be provided by taking the user's device information into consideration. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI.

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

The repair assistance system can further include a diagnostic unit. The diagnostic unit analyzes sensor data to identify the location of a product failure. For example, the diagnostic unit acquires data such as temperature, vibration, and current from sensors installed inside the product and detects abnormalities. The diagnostic unit can also identify the cause of the failure by comparing it with past failure data. Furthermore, the diagnostic unit can detect signs of failure and suggest preventive repairs. This enables the repair assistance system to achieve early detection and prevention of failures, extending the lifespan of products.

When operating the robot's hand, the repair department can refer to the user's repair history to select the optimal repair procedure. For example, the repair department can refer to a database of products that the user has previously repaired and suggest the optimal repair procedure if a similar malfunction occurs. The repair department can also analyze the probability that a specific repair procedure will be successful from the user's repair history and select that procedure as a priority. Furthermore, the repair department can customize the repair procedure based on the user's repair history and provide the user with the most efficient repair method. This allows the repair department to utilize the user's past experience to achieve more effective repairs.

The reception unit can estimate the user's emotions and adjust the method for inputting malfunction information based on the emotions. For example, the reception unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is feeling stressed, the reception unit can provide a simple interface and minimize the input steps. If the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input, allowing the user to input malfunction information quickly. In this way, an easy-to-use interface can be provided by adjusting the input method for malfunction information according to the user's emotions.

The acquisition unit can prioritize acquiring highly relevant instruction manuals based on the user's geographical location information. For example, if the user is in a specific area, instruction manuals for products sold in that area can be acquired preferentially. Also, if the user is traveling, instruction manuals for products to be used at the user's destination can be acquired preferentially. Furthermore, the acquisition unit can acquire the most relevant instruction manuals based on the user's geographical location information. This makes it possible to provide highly relevant instruction manuals by taking the user's geographical location information into consideration.

The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on those emotions. For example, the summarization unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. If the user is feeling stressed, it can generate a concise and easy-to-understand summary. If the user is relaxed, it can also generate a detailed summary. Furthermore, if the user is in a hurry, it can generate a summary that emphasizes the most important parts. In this way, by adjusting the way the summary is presented according to the user's emotions, it is possible to provide a summary that is easy for the user to understand.

The repair unit can estimate the user's emotions and adjust the repair method based on those emotions. For example, the repair unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is feeling stressed, a simple and quick repair method can be selected. If the user is relaxed, detailed repair instructions can be provided. Furthermore, if the user is in a hurry, the most efficient repair method can be selected. In this way, the repair method can be adjusted according to the user's emotions, making it possible to provide the optimal repair method for the user.

When repairing, the repair department can customize repair procedures based on the user's repair skill level. For example, if the user is a beginner, simple repair procedures can be provided. If the user is an intermediate user, detailed repair procedures can be provided. Furthermore, if the user is an advanced user, specialized repair procedures can be provided. This can improve the success rate of repairs by providing repair procedures that are appropriate for the user's repair skill level.

When repairing a product, the repair department can analyze the user's past repair history and select a repair method. For example, they can refer to the repair methods used by the user on products they have previously repaired. They can also select the most effective repair method from the user's past repair history. They can also analyze the user's past repair history and select the optimal repair method. This makes it possible to provide the optimal repair method by taking the user's past repair history into consideration.

When retrieving instruction manuals, the retrieval unit can retrieve relevant instruction manuals based on the user's social media activity. For example, it can prioritize retrieving instruction manuals for products that the user has mentioned on social media. It can also retrieve instruction manuals for products that the user is interested in based on the user's social media activity. It can also analyze the user's social media activity and retrieve the most relevant instruction manuals. This makes it possible to provide highly relevant instruction manuals by analyzing the user's social media activity.

When generating a summary, the summarization unit can apply different summarization algorithms based on the category of the instruction manual. For example, for an instruction manual for an electronic device, a technical summarization algorithm can be applied. For an instruction manual for furniture, a summarization algorithm specialized for assembly instructions can be applied. Furthermore, the most appropriate summarization algorithm can be applied depending on the category of the instruction manual. This makes it possible to provide the most appropriate summary by applying a summarization algorithm according to the category of the instruction manual.

The processing flow for Example 2 is briefly explained below.

Step 1: The acquisition unit acquires the contents of the product's instruction manual. For example, the acquisition unit may take a photograph of the instruction manual using a camera and acquire the image data. The acquisition unit may also directly acquire a digital instruction manual. For example, the acquisition unit may acquire an instruction manual in PDF format or text format.
Step 2: The summarization unit uses the generation AI to summarize the contents of the instruction manual acquired by the acquisition unit. For example, the generation AI analyzes the contents of the instruction manual, extracts important information, and generates a summary. The generation AI performs the summarization using a text generation AI (e.g., LLM). For example, the generation AI receives a prompt such as "Please summarize the main points of this instruction manual" and generates a summary.
Step 3: The repair unit uses the generative AI to operate a robot based on the content summarized by the summarization unit to repair the product. The repair unit operates, for example, the robot's hand to repair the product. The robot's hand has, for example, an arm capable of precise movement, and accurately performs repairs based on the instruction manual.

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 38B acquires audio indicating the user input regarding the results 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.

The data generation model 58 is what is known as generative AI (artificial intelligence). An example of a data generation model 58 is generative AI such as ChatGPT (registered trademark) (Internet search <URL: https://openai.com/blog/chatgpt>). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data) is also input. The data generation model 58 performs inference on the input inference data in accordance with the instructions indicated by the prompt and outputs the inference results in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 that outputs inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12 or the like includes multiple types of data generation models 58, and the data generation model 58 includes AI other than the generation AI. Examples of AI other than the generation AI include 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, and can perform various processes, but are 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 AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. In addition, processing performed by AI, including generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generation AI.

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, etc., and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

For example, the acquisition unit may photograph the instruction manual using the camera 42 of the smart device 14 and acquire the image data. The acquisition unit may also directly acquire the digital instruction manual using the specific processing unit 290 of the data processing device 12. For example, the summarization unit may use generated AI by the specific processing unit 290 of the data processing device 12 to summarize the contents of the instruction manual acquired by the acquisition unit. The repair unit may operate a robot to repair the product based on the contents summarized by the control unit 46A of the smart device 14, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

As shown in FIG. 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.

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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.

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, RAM 48, and storage 50. The processor 46, RAM 48, and 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.

The microphone 238 receives instructions and other information 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 in accordance with instructions from the processor 46.

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).

The communication I/F 44 is connected to the 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 manner.

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

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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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 the 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 emotions, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

In the smart glasses 214, 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 emotion identification model similar to the data generation model 58 and emotion identification model 59, and can use these models to perform processing similar to that of the specific processing unit 290.

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 processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

The data generation model 58 is what is known as generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 that outputs inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12 or the like includes multiple types of data generation models 58, and the data generation model 58 includes AI other than the generation AI. Examples of AI other than the generation AI include 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, and can perform various processes, but are 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 AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. In addition, processing performed by AI, including generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generation AI.

The data processing system 210 according to the second embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. 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. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

For example, the acquisition unit photographs the instruction manual using the camera 42 of the smart glasses 214 and acquires the image data. The acquisition unit can also directly acquire the digital instruction manual using the specific processing unit 290 of the data processing device 12. For example, the summarization unit summarizes the contents of the instruction manual acquired by the acquisition unit using generated AI by the specific processing unit 290 of the data processing device 12. The repair unit operates a robot to repair the product based on the contents summarized by the control unit 46A of the smart glasses 214, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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.

The headset 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, RAM 48, and storage 50. The processor 46, RAM 48, and 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.

The microphone 238 receives instructions and other information 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 in accordance with instructions from the processor 46.

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).

The communication I/F 44 is connected to the 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 manner.

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

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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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 the 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 emotions, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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 processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

The data generation model 58 is what is known as generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 that outputs inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12 or the like includes multiple types of data generation models 58, and the data generation model 58 includes AI other than the generation AI. Examples of AI other than the generation AI include 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, and can perform various processes, but are 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 AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. In addition, processing performed by AI, including generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generation AI.

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. 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 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 terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

For example, the acquisition unit photographs the instruction manual using the camera 42 of the headset terminal 314 and acquires the image data. The acquisition unit can also directly acquire the digital instruction manual using the specific processing unit 290 of the data processing device 12. For example, the summarization unit summarizes the contents of the instruction manual acquired by the acquisition unit using generated AI by the specific processing unit 290 of the data processing device 12. The repair unit operates a robot to repair the product based on the contents summarized by the control unit 46A of the headset terminal 314, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

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

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, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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.

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, RAM 48, and storage 50. The processor 46, RAM 48, and 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.

The microphone 238 receives instructions and other information 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 in accordance with instructions from the processor 46.

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 CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

The communication I/F 44 is connected to the 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 manner.

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.

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

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 the specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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 the 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 emotions, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

In robot 414, specific processing is performed by processor 46. Specific program 60 is stored in storage 50. Processor 46 reads specific program 60 from storage 50 and executes the read specific program 60 on RAM 48. The specific processing is realized by processor 46 operating as control unit 46A in accordance with specific program 60 executed on RAM 48. Robot 414 also has a data generation model and emotion identification model similar to data generation model 58 and emotion identification model 59, and can use these models to perform processing similar to that of identification processing unit 290.

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 processing results (such as prediction results) using the data generation model 58. The data processing device 12 may also be a server device, or a terminal device owned by a user (for example, a mobile phone, robot, home appliance, etc.).

The specific processing unit 290 transmits the results 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 results of the specific processing. The microphone 238 acquires audio indicating the user input regarding the results 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.

The data generation model 58 is what is known as generative AI. An example of a data generation model 58 is generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 that outputs inference results from prompts that do not include instructions. In this case, the data generation model 58 can output inference results from prompts that do not include instructions. The data processing device 12 or the like includes multiple types of data generation models 58, and the data generation model 58 includes AI other than the generation AI. Examples of AI other than the generation AI include 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, and can perform various processes, but are 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 AI, the processing may be performed in part or in whole by AI, but is not limited to these examples. In addition, processing performed by AI, including generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generation AI.

The data processing system 410 according to the fourth embodiment performs processing similar to that of the data processing system 10 according to the first embodiment. 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.

For example, the acquisition unit photographs the instruction manual using the camera 42 of the robot 414 and acquires the image data. The acquisition unit can also directly acquire the digital instruction manual using the specific processing unit 290 of the data processing device 12. For example, the summarization unit summarizes the contents of the instruction manual acquired by the acquisition unit using generated AI by the specific processing unit 290 of the data processing device 12. The repair unit operates the robot to repair the product based on the contents summarized by the control unit 46A of the robot 414, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

The emotion identification model 59, which serves 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 Figure 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.

Figure 9 shows an emotion map 400 on which multiple emotions are mapped. In emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both emotions and mental states. Emotions that are generally generated from reactions that occur in the brain are arranged on the left side of the concentric circles. Emotions that are generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions that are generally generated from reactions that occur in the brain and are 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, emotion map 400 maps multiple emotions based on the structure by which emotions are generated, with emotions that tend to occur simultaneously being mapped close together.

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

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 out you go on emotion map 400, the more visible (expressed in behavior) the emotion becomes.

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

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

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 close to each other have similar values, as in the emotion map 900 shown in Figure 10. Figure 10 shows an example in which multiple emotions, such as "relieved," "calm," and "reassuring," have similar emotion values.

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

In the above embodiment, an example was described in which the specific processing program 56 is stored in the storage 32, 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.

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.

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

The following types of processors can be used as hardware resources for executing specific processes. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource for executing specific processes by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which are processors with a circuit configuration designed specifically for executing specific processes. All processors have built-in or connected memory, and all use the memory to execute specific processes.

The hardware resource that executes the specific processing may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). The hardware resource that executes the specific processing may also be a single processor.

As an example of a configuration using a single processor, first, there is a configuration in which one processor is configured using a combination of one or more CPUs and software, and this processor functions as a hardware resource that executes specific processing. Second, there is a configuration in which a processor is used to realize the functions of an entire system, including multiple hardware resources that execute specific processing, on a single IC chip, as typified by SoC (System-on-a-chip). In this way, specific processing is realized using one or more of the various processors listed above as hardware resources.

More specifically, the hardware structure of these various processors can be an electrical circuit that combines circuit elements such as semiconductor devices. Furthermore, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps can be added, or the processing order can be rearranged, all within the scope of the spirit of the invention.

Furthermore, in the above examples, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. Furthermore, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are only examples, and they may be combined, or other devices may be used. Furthermore, in the above examples, the first and second embodiments have been described separately, but these may also be combined.

The above-described written content 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 explanation 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 substitutions may be made to the above-described written content and illustrations, as long as they do not deviate from the spirit 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 written content 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.

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

(Appendix 1)
an acquisition unit that acquires the contents of the product instruction manual;
a unit that summarizes the contents of the instruction manual acquired by the acquisition unit using a generation AI;
A unit that uses a generative AI to operate a robot to repair the product based on the content summarized by the summarization unit.
(Appendix 2)
The repair department
2. The system of claim 1, wherein the robotic hand is actuated to repair the product.
(Appendix 3)
a receiving unit that receives input of information indicating a symptom of a malfunction of the product from a user;
The repair department
The system according to claim 1, wherein the robot is operated based on the summarized content and the information input by the reception unit.
(Appendix 4)
The acquisition unit
The system according to claim 1, characterized in that it estimates the user's emotions and adjusts the timing of obtaining the instruction manual based on the emotions.
(Appendix 5)
The acquisition unit
The system according to claim 1, wherein when obtaining an instruction manual, the system analyzes the user's past repair history and selects a method of obtaining the instruction manual.
(Appendix 6)
The acquisition unit
The system described in Appendix 1, wherein when obtaining an instruction manual, filtering is performed based on the user's repair skill level.
(Appendix 7)
The acquisition unit
The system according to claim 1, characterized in that it estimates the user's emotions and determines the priority of the instruction manuals to be acquired based on the emotions.
(Appendix 8)
The acquisition unit
The system according to claim 1, wherein when obtaining an instruction manual, the system prioritizes obtaining highly relevant instruction manuals based on the user's geographical location information.
(Appendix 9)
The acquisition unit
The system described in Appendix 1, characterized in that when obtaining an instruction manual, related instruction manuals are obtained based on the user's social media activity.
(Appendix 10)
The summary section
The system according to claim 1, wherein the system estimates a user's emotion and adjusts the presentation of the summary based on the emotion.
(Appendix 11)
The summary section
The system of claim 1, wherein when generating a summary, the level of detail of the summary is adjusted based on the importance of the instruction manual.
(Appendix 12)
The summary section
The system of claim 1, wherein different summarization algorithms are applied based on the category of the instruction manual when generating the summary.
(Appendix 13)
The summary section
2. The system of claim 1, wherein the system estimates a user's emotion and adjusts the length of the summary based on the emotion.
(Appendix 14)
The summary section
When generating a summary, after-claim is based on the publication date of the instruction manual.
(Appendix 15)
The summary section
2. The system of claim 1, wherein when generating summaries, the system adjusts the order of the summaries based on the relevance of the instruction manual.
(Appendix 16)
The repair department
2. The system of claim 1, wherein the system estimates a user's emotions and adjusts repair methods based on the emotions.
(Appendix 17)
The repair department
The system according to claim 1, wherein, at the time of repair, the system analyzes the user's past repair history and selects a repair method.
(Appendix 18)
The repair department
2. The system of claim 1, wherein, at the time of repair, the repair procedure is customized based on the user's repair skill level.
(Appendix 19)
The repair department
2. The system of claim 1, further comprising: estimating a user's emotions and prioritizing repairs based on the emotions.
(Appendix 20)
The repair department
The system according to claim 1, wherein, at the time of repair, a repair method is selected based on the user's geographical location information.
(Appendix 21)
The repair department
The system described in Appendix 1 is characterized in that, at the time of repair, repair procedures are suggested based on the user's social media activity.
(Appendix 22)
The reception unit
The system according to claim 1, wherein the system estimates a user's emotion and adjusts a method for inputting fault information based on the emotion.
(Appendix 23)
The reception unit
The system according to claim 1, wherein when inputting failure information, an input method is selected based on the user's past failure history.
(Appendix 24)
The reception unit
The system according to claim 1, characterized in that it estimates a user's emotions and determines the priority of fault information based on the emotions.
(Appendix 25)
The reception unit
The system according to claim 1, wherein when inputting failure information, an input method is selected based on the user's device information.

10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims (5)

a reception unit that receives input of information indicating a symptom of a malfunction of a product from a user;
an acquisition unit that acquires the contents of the product instruction manual;
a summarization unit that generates a prompt for summarizing the contents of the instruction manual acquired by the acquisition unit, inputs the prompt to a generation AI, and acquires data indicating the summarized contents ;
a repair unit that generates a prompt for generating an operating procedure for a robot to repair the product based on data indicating the summarized content obtained by the summarization unit and information indicating the symptoms of the failure received by the reception unit , inputs the prompt into a generation AI to obtain data indicating the operating procedure, and operates the robot based on the data to repair the product. The repair department
The system of claim 1 , further comprising: actuating the robotic hand to repair the item. 2. The system according to claim 1, wherein the reception unit receives input of information including at least one of text, image, and voice from the user as information indicating the symptom of the malfunction of the product. The acquisition unit
The system described in claim 1, characterized in that the user's emotions are estimated based on image data obtained by photographing the user's facial expression with a camera , and the timing of obtaining the instruction manual is adjusted based on the emotion so that if the estimated emotion is a stressful state, the timing of obtaining the instruction manual is adjusted based on the emotion so that the timing of obtaining the instruction manual is immediately started. The acquisition unit
The system described in claim 1, characterized in that when obtaining the instruction manual, the user's geographical location information is obtained from GPS data, and if the user is in a specific area, instruction manuals for products sold in that area are obtained preferentially .