System

Abstract

The system provided by the embodiment of the invention aims to improve the service maintenance and handling efficiency of the base station. A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a delegation unit. The collecting part is used for collecting data such as alarm information, technical specifications and past coping resumes. The analysis unit analyzes the data collected by the collection unit. The generation unit generates a coping method based on a result of the analysis by the analysis unit. The delegation unit performs delegation on the basis of the coping method generated by the generation unit.

Description

Technical Field

[0001] The technology disclosed herein relates to a system. Background Technology

[0002] Patent Document 1 discloses a personalized chatbot control method executed by at least one processor, the method comprising: receiving user speech; adding the user speech to a prompt containing instructions related to a chatbot role; encoding the prompt; and inputting the encoded prompt into a language model to generate chatbot speech in response to the user speech.

[0003] Patent document 1: Japanese Patent Application Publication No. 2022-180282. Summary of the Invention

[0004] In existing technologies, base station maintenance requires manual handling to respond to business needs, which is inefficient.

[0005] The system involved in this technical solution aims to improve the efficiency of base station maintenance in responding to business needs.

[0006] The system involved in this technical solution includes a collection department, an analysis department, a generation department, and a delegation department. The collection department collects data such as alarm information, technical specifications, and past response records. The analysis department analyzes the data collected by the collection department. The generation department generates response methods based on the analysis results. The delegation department delegates tasks based on the response methods generated by the generation department.

[0007] The system involved in this technical solution can improve the efficiency of base station maintenance in responding to services. Attached Figure Description

[0008] Figure 1 This is a conceptual diagram illustrating an example of the configuration of a data processing system according to the first embodiment.

[0009] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0010] Figure 3 This is a conceptual diagram illustrating an example of the data processing system configuration in the second embodiment.

[0011] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0012] Figure 5 This is a conceptual diagram illustrating an example of the data processing system configuration in the third embodiment.

[0013] Figure 6This is a conceptual diagram illustrating an example of the main functions of the data processing device and head-mounted terminal according to the third embodiment.

[0014] Figure 7 This is a conceptual diagram illustrating an example of the data processing system configuration in the fourth embodiment.

[0015] Figure 8 This is a conceptual diagram illustrating an example of the functions of the main parts of the data processing device and robot according to the fourth embodiment.

[0016] Figure 9 It represents an emotion graph that maps multiple emotions.

[0017] Figure 10 It represents an emotion graph that maps multiple emotions.

[0018] Explanation of reference numerals in the attached figures

[0019] Data processing systems 10, 210, 310, and 410

[0020] 12 Data processing devices

[0021] 14 Smart devices

[0022] 214 Smart Glasses

[0023] 314 Head-mounted terminal

[0024] 414 Robot. Detailed Implementation

[0025] Hereinafter, an example of an implementation of the system involved in this disclosure will be described with reference to the accompanying drawings.

[0026] First, let's explain the terms used in the following description.

[0027] In the following embodiments, the processor (hereinafter referred to as "processor"), as indicated by the reference numerals, can be a single computing device or a combination of multiple computing devices. Furthermore, a processor can be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit), etc.

[0028] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory for temporary information storage that is used by the processor as working memory.

[0029] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices used to store various programs and parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes, etc.

[0030] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface including a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. Examples of communication standards applicable 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).

[0031] In the following implementation, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects more than three items, the same approach as "A and / or B" applies.

[0032] First Implementation Method

[0033] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0034] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. An example of the data processing device 12 is a server.

[0035] 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 memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a receiver 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiver 38, output device 40, and camera 42 are also connected to the bus 52.

[0037] The receiving device 38 includes a touchscreen 38A and a microphone 38B, etc., for receiving user input. The touchscreen 38A receives user input generated by contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input generated by sound by detecting the user's voice. The control unit 46A sends data representing user input received via the touchscreen 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, a specific processing unit 290 (see reference...) Figure 2 Get the data that represents the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, etc., and presents data to the user by outputting data in a user-perceptible form (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0040] Figure 2 An example of the main functions of the data processing device 12 and the smart device 14 is shown.

[0041] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0042] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0043] In the smart device 14, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The specific processing program 60 is used in conjunction with the data processing system 10. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart device 14 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0044] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing performed by the data processing system 10 of the first embodiment will be described.

[0045] Implementation Method 1

[0046] The maintenance response system described in this invention utilizes generative AI to replace traditional base station maintenance response tasks. Currently, maintenance response systems rely on manual methods developed based on alarm information, technical specifications, and past response experience, which are then outsourced to external providers. By entrusting these tasks to generative AI, the time required for base station maintenance can be significantly reduced, enabling fault response that is impossible for humans. For example, the maintenance response system collects data such as alarm information, technical specifications, and past response experience. Subsequently, the system uses generative AI to analyze this data and generate the optimal response method. Based on the generated response method, the system outsources the task to external providers. This mechanism not only improves the efficiency of base station maintenance but also enables fault response that is impossible for humans. For instance, when a base station alarms, the system uses generative AI to analyze the alarm information, refers to past response experience and technical specifications, and generates the optimal response method. Based on this method, the system outsources the task to external providers, achieving rapid response. This system not only significantly reduces the time required for base station maintenance but also enables fault response that is impossible for humans. For example, even in the event of complex faults, the maintenance response system can quickly generate and implement the optimal response method through generative AI. This ensures the stable operation of the base station and is expected to improve service quality. Therefore, the maintenance response system can significantly reduce the man-hours required for base station maintenance and enable fault response that is impossible for humans.

[0047] The maintenance response system described in this embodiment includes a collection unit, an analysis unit, a generation unit, and a delegation unit. The collection unit collects data such as alarm information, technical specifications, and past response history. For example, the collection unit can collect alarm information in real time. The collection unit can also collect technical specifications in digital form. Furthermore, the collection unit can retrieve past response history from a database. For example, the collection unit can directly obtain alarm information from sensors and save it to the database in real time. Technical specifications are collected and saved to the database in PDF or text format. Past response history is retrieved from the database through queries and provided to the analysis unit. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit uses generative AI to analyze the data and generate the optimal response method. The analysis unit can also use data mining techniques to analyze data patterns or use statistical analysis techniques to analyze data trends. For example, the analysis unit inputs alarm information, technical specifications, and past response history into a generative AI to generate the optimal response method. Data mining techniques can extract useful patterns from the data, which helps in generating response methods. Statistical analysis techniques can analyze data trends and improve the accuracy of response methods. The generation unit generates response methods based on the results analyzed by the analysis unit. For example, the generation unit may utilize generative AI to generate response methods. The generation unit may also generate response methods based on operation manuals or guidelines. Furthermore, the generation unit may refer to past response experience to generate response methods. For example, the generation unit inputs the analysis results into the generative AI to generate the optimal response method. Operation manuals or guidelines serve as a reference in response method generation. Past response experience can provide response methods for similar faults. The delegation unit delegates tasks based on the response methods generated by the generation unit. For example, the delegation unit issues a task to an external operator. The delegation unit may also automatically generate a task request and send it to the external operator. Furthermore, the delegation unit can confirm the task content and make corrections as necessary. For example, the delegation unit automatically generates a task request based on the generated response method and sends it to the external operator. The task request details the response method, providing specific instructions to the external operator. The task content is confirmed by the delegation unit and corrected as necessary. Therefore, the maintenance response system according to this embodiment can significantly reduce the working hours of base station maintenance services and achieve fault response that is impossible for humans to complete.

[0048] The data collection department gathers alarm information, technical specifications, and past response records. Specifically, alarm information is acquired in real-time by sensors and immediately saved to the database. This ensures the system always has the latest alarm information, enabling rapid response. Technical specifications are digitized in PDF or text format and saved to the database. This allows technicians to quickly retrieve and access the information they need. Past response records are retrieved from the database through queries and provided to the analysis department. Analysis based on these records can then be used to generate more accurate response methods. The collection department manages this data centrally and can collaborate with other systems or departments as needed. For example, collected data can be stored on a cloud server for access by the analysis and generation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses can be implemented based on specific situations or conditions. This allows the collection department to collect data efficiently and effectively, improving overall system performance. In addition, the collection department incorporates verification processes to ensure data consistency and reliability, maintaining data quality. For example, by detecting duplicate or missing data and utilizing automatic correction algorithms, data accuracy is improved. This ensures the collection department provides highly reliable data, enhancing the overall reliability of the system.

[0049] The analysis department is used to analyze the data collected by the collection department. For example, the analysis department utilizes generative AI to analyze the data and generate optimal response methods. Specifically, alarm information, technical specifications, and past response history are input into the generative AI to generate optimal response methods. The generative AI uses natural language processing technology to analyze the technical specifications and past response history, proposing response methods based on the alarm information. Data mining technology can extract useful patterns from the data, contributing to the generation of response methods. For example, common patterns can be discovered from past response history to determine the optimal response method for similar faults. Statistical analysis technology can analyze data trends to improve the accuracy of response methods. For example, based on the frequency of alarm information and the content of technical specifications, the probability of a specific fault can be predicted, allowing for proactive countermeasures. Furthermore, the analysis department can also use historical data and statistical information for long-term risk assessment and trend analysis. For example, based on past fault data, risk changes in a specific region or time period can be predicted to formulate future countermeasures. The analysis department can also use anomaly detection algorithms to detect abnormal patterns or abnormal data and issue early warnings. Therefore, the analysis department can not only grasp the situation in real time, but also perform long-term risk management and anomaly detection, thereby improving the overall reliability and security of the system.

[0050] The generation department generates response methods based on the results analyzed by the analysis department. For example, the generation department utilizes generative AI to generate response methods. Specifically, the analysis results are input into the generative AI to generate the optimal response method. The generative AI references past response experience and technical specifications to propose optimal response steps. Operation manuals or guidelines serve as references in response method generation. For example, a specific response method can be customized based on standard response steps for a particular fault. Past response experience can provide response methods for similar faults. For example, referencing response methods for similar faults in the past, the optimal response steps are generated. The generation department integrates this information to quickly generate the optimal response method. Furthermore, the generation department can evaluate the accuracy and effectiveness of the generated response methods and make corrections when necessary. For example, the generated response methods are simulated to confirm their applicability to real-world situations. The generation department can also collect user feedback to improve response methods. Thus, the generation department can always provide highly accurate response methods based on the latest information, supporting rapid and appropriate responses. In addition, the generation department can automatically document the generated response methods and share them with other departments or systems. This ensures the consistency and transparency of response methods and improves the overall efficiency of the system.

[0051] The delegation department delegates tasks based on the response methods generated by the generation department. Specifically, it issues delegation requests to external clients. The delegation department can also automatically generate and send delegation documents to external clients. For example, it can automatically generate and send delegation documents based on the generated response methods. The delegation documents detail the response methods, providing specific instructions to external clients. The delegation department confirms the delegation content and makes corrections as necessary. For example, it confirms the content of the delegation documents and corrects any errors or ambiguities. The delegation department can also monitor the progress of delegations and follow up as needed. For example, it receives reports from external clients and confirms the progress of responses. Furthermore, the delegation department can record delegation content and progress in a database for future reference. This allows the delegation department to delegate tasks efficiently and effectively, improving the overall reliability and efficiency of the system. In addition, the delegation department can share delegation content and progress with other departments or systems to strengthen overall collaboration. For example, it can notify other departments of the delegation content and request necessary support. The delegation department can also evaluate the delegation results for future improvements. Thus, the delegation department can always provide optimal responses, improving the overall performance of the system.

[0052] The data collection department can gather alarm information, technical specifications, and past response records. For example, it can collect alarm information in real time. It can also collect technical specifications in digital form. Furthermore, it can retrieve past response records from a database. For instance, the department can directly obtain alarm information from sensors and save it to the database in real time. Technical specifications are collected and saved to the database in PDF or text format. Past response records are retrieved from the database through queries and provided to the analysis department. This allows for efficient collection of the required data.

[0053] The analysis unit is capable of analyzing collected data and generating optimal response methods. For example, it can utilize generative AI to analyze data and generate optimal response methods. The analysis unit can also use data mining techniques to analyze data patterns or statistical analysis techniques to analyze data trends. For instance, the analysis unit can input alarm information, technical specifications, and past response history into generative AI to generate optimal response methods. Data mining techniques can extract useful patterns from data, which helps in the generation of response methods. Statistical analysis techniques can analyze data trends, improving the accuracy of response methods. Thus, it is possible to analyze collected data and generate optimal response methods.

[0054] The generation department can outsource solutions to external vendors based on the generated response methods. For example, the generation department can utilize generative AI to generate response methods. It can also generate response methods based on operation manuals or guidelines. Furthermore, it can refer to past response experience when generating response methods. For instance, the generation department inputs the parsed results into the generative AI to generate the optimal response method. Operation manuals or guidelines serve as a reference in response method generation. Past response experience can provide solutions for similar failures. Therefore, it is possible to outsource solutions to external vendors based on the generated response methods.

[0055] The delegation department can delegate tasks based on the generated response methods. For example, the delegation department may issue a task to an external contractor. The delegation department can also automatically generate a task request and send it to the external contractor. The delegation department can also verify the content of the task and make corrections as necessary. For instance, the delegation department automatically generates a task request based on the generated response methods and sends it to the external contractor. The task request details the response methods and provides specific instructions to the external contractor. The content of the task is verified by the delegation department and corrected as necessary. Thus, delegation can be based on the generated response methods.

[0056] The data collection department can analyze past data collection history to select the optimal collection method. For example, it can identify the most effective collection methods from past data collection history and apply them to future data collection. The department can also select the optimal collection method for specific time periods or conditions based on past data collection history. Furthermore, the department can analyze past data collection history, identify areas for improvement in specific collection methods, and optimize them. For instance, the department can retrieve past data collection history from a database and analyze it using data mining techniques. The department can select data collection methods for specific time periods or conditions to achieve efficient data collection. By identifying and optimizing specific collection methods, the department can improve the accuracy and efficiency of data collection. Thus, it is possible to analyze past data collection history and select the optimal collection method.

[0057] The data collection unit can filter data based on the current operating status of the base station and environmental conditions during data collection. For example, the collection unit can monitor the base station's operating status in real time and collect data only when an anomaly occurs. The collection unit can also consider environmental conditions (such as weather and temperature) and prioritize data collection under specific conditions. Furthermore, the collection unit can adjust the type and quantity of data collected based on the base station's operating status and environmental conditions. Thus, data collection can be filtered based on the base station's operating status and environmental conditions.

[0058] The data collection unit can consider the geographical location information of the base station during data collection, prioritizing the collection of highly relevant data. For example, the collection unit can prioritize collecting surrounding environmental data based on the geographical location information of the base station. The collection unit can also consider the geographical location information of the base station and prioritize collecting data in specific areas. Furthermore, the collection unit can filter and collect highly relevant data based on the geographical location information of the base station. For example, the collection unit can prioritize collecting surrounding environmental data based on the geographical location information of the base station. The collection unit considers the geographical location information of the base station and prioritizes collecting data in specific areas. The collection unit filters and collects highly relevant data based on the geographical location information of the base station. Therefore, it is possible to consider the geographical location information of the base station and prioritize the collection of highly relevant data.

[0059] The data collection unit can analyze the social media activity of base stations and collect relevant data during data collection. For example, the collection unit can monitor the social media activity of base stations and collect relevant data. The collection unit can also analyze trends on social media and prioritize the collection of data related to base stations. The collection unit can also collect data related to base stations based on user feedback on social media. For example, the collection unit can monitor the social media activity of base stations and collect relevant data. The collection unit can analyze trends on social media and prioritize the collection of data related to base stations. The collection unit can collect data related to base stations based on user feedback on social media. Thus, it is possible to analyze the social media activity of base stations and collect relevant data.

[0060] The parsing unit can adjust the level of detail in the parsing based on the importance of the data. For example, it can perform detailed parsing on highly important data, or simplified parsing on less important data. Furthermore, it can determine the parsing priority based on the importance of the data. For instance, the parsing unit assesses the importance of the data and performs detailed parsing on highly important data, while simplifying parsing on less important data. The parsing unit determines the parsing priority based on the importance of the data. Therefore, the level of detail in the parsing can be adjusted based on the importance of the data.

[0061] The parsing unit can apply different parsing algorithms based on the data category during parsing. For example, it can apply a specific parsing algorithm to data based on technical specifications. It can also apply different parsing algorithms to data based on alarm information. Furthermore, it can apply additional parsing algorithms to data based on past response history. Thus, it is possible to apply different parsing algorithms based on the data category.

[0062] The parsing unit can determine the parsing priority based on the timing of data collection. For example, it may prioritize parsing the most recent data. It may also prioritize parsing data from a specific time period based on historical data. Furthermore, the parsing unit can adjust the parsing order according to the timing of data collection. Thus, it is possible to determine the parsing priority based on the timing of data collection.

[0063] The parsing unit can adjust the parsing order based on the relevance of the data during parsing. For example, the parsing unit may prioritize parsing data with high relevance. It may also postpone processing data with low relevance. Furthermore, the parsing unit can dynamically adjust the parsing order based on the relevance of the data. For instance, the parsing unit may prioritize parsing data with high relevance and postpone processing data with low relevance. The parsing unit can dynamically adjust the parsing order based on the relevance of the data. Therefore, the parsing order can be adjusted based on the relevance of the data.

[0064] The generation unit can adjust the level of detail generated based on the importance of the data when generating response methods. For example, the generation unit can generate detailed response methods based on data with high importance, or simplified response methods based on data with low importance. The generation unit can also determine the priority of the generated response methods based on the importance of the data. For example, the generation unit can generate detailed response methods based on data with high importance, or simplified response methods based on data with low importance. The generation unit determines the priority of the generated response methods based on the importance of the data. Therefore, the level of detail generated can be adjusted based on the importance of the data.

[0065] The generation department can apply different generation algorithms based on the data category when generating response methods. For example, the generation department can apply a specific generation algorithm to response methods based on technical specifications. It can also apply different generation algorithms to response methods based on alarm information. Furthermore, it can apply additional generation algorithms to response methods based on past response history. Thus, different generation algorithms can be applied according to the data category.

[0066] The generation unit can determine the generation priority based on the timing of data collection when generating response methods. For example, the generation unit may prioritize generating response methods based on the latest data. It may also postpone processing response methods based on past data. Furthermore, the generation unit can adjust the order in which the generated response methods are processed based on the timing of data collection. Thus, the generation priority can be determined based on the timing of data collection.

[0067] The generation unit can adjust the generation order based on data relevance during response method generation. For example, the generation unit may prioritize generating response methods based on highly relevant data. It may also postpone processing response methods based on low-relevance data. Furthermore, the generation unit can dynamically adjust the order of generated response methods based on data relevance. For instance, the generation unit may prioritize generating response methods based on highly relevant data. It may postpone processing response methods based on low-relevance data. The generation unit can dynamically adjust the order of generated response methods based on data relevance. Thus, the generation order can be adjusted based on data relevance.

[0068] The delegation department can adjust the level of detail in delegation based on the importance of the response methods. For example, the delegation department may process delegations based on high-importance response methods in detail, while simplifying delegations based on low-importance response methods. The delegation department can also determine the priority of delegations based on the importance of the response methods. For example, the delegation department may process delegations based on high-importance response methods in detail, while simplifying delegations based on low-importance response methods. The delegation department determines the priority of delegations based on the importance of the response methods. Therefore, the level of detail in delegation can be adjusted based on the importance of the response methods.

[0069] The delegation department can apply different delegation algorithms based on the type of response method when delegation. For example, the delegation department can apply a specific delegation algorithm to response methods based on technical specifications. The delegation department can also apply different delegation algorithms to response methods based on alarm information. The delegation department can also apply additional delegation algorithms to response methods based on past response history. For example, the delegation department applies a specific delegation algorithm to response methods based on technical specifications. The delegation department applies different delegation algorithms to response methods based on alarm information. The delegation department applies additional delegation algorithms to response methods based on past response history. Thus, different delegation algorithms can be applied according to the type of response method.

[0070] The delegation department can determine the priority of delegations based on the timing of response method generation. For example, the delegation department may prioritize delegations based on the latest response method. It may also postpone delegations based on past response methods. Furthermore, the delegation department can adjust the order of delegations based on the timing of response method generation. For instance, the delegation department may prioritize delegations based on the latest response method and postpone delegations based on past response methods. The delegation department can adjust the order of delegations based on the timing of response method generation. Thus, the priority of delegations can be determined based on the timing of response method generation.

[0071] The delegation department can adjust the order of delegation based on the relevance of response methods when delegation is made. For example, the delegation department may prioritize delegations based on highly relevant response methods. The delegation department may also postpone delegations based on less relevant response methods. The delegation department can also dynamically adjust the order of delegation based on the relevance of response methods. For example, the delegation department may prioritize delegations based on highly relevant response methods. The delegation department may postpone delegations based on less relevant response methods. The delegation department dynamically adjusts the order of delegation based on the relevance of response methods. Therefore, the order of delegation can be adjusted based on the relevance of response methods.

[0072] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as follows.

[0073] The maintenance response system may also include a prediction unit. This unit can predict future failures based on collected data. For example, it analyzes past failure patterns to predict the likelihood of future failures. It can also use machine learning algorithms to learn data trends and predict future failures. Furthermore, it can analyze data in real time to detect signs of failure. Thus, the maintenance response system can take preventative measures before failures occur, further ensuring the stable operation of the base station.

[0074] The maintenance response system may also include a notification department. This department can communicate generated response methods or predicted fault information to relevant personnel. For example, the notification department can send notifications via email or SMS. It can also send notifications in real time via a dedicated application. Furthermore, the notification department can customize notification content to provide relevant personnel with information appropriate to their roles. This allows relevant personnel to quickly grasp the response methods or fault information and take appropriate action.

[0075] The maintenance response system may also include an evaluation department. This department can assess the effectiveness of the generated response methods and identify areas for improvement. For example, the evaluation department collects results after the implementation of the response methods and evaluates their effectiveness. The evaluation department can also use data analysis techniques to quantitatively evaluate the effectiveness of the response methods. Furthermore, the evaluation department can collect feedback from relevant personnel and identify areas for improvement in the response methods. Thus, the maintenance response system can continuously improve response methods and increase the efficiency of base station maintenance services.

[0076] The maintenance response system may also include a learning unit. This unit can learn from collected data and evaluation results to improve the generative AI. For example, it can use past response experiences and evaluation results to refine the generative AI's algorithm. The learning unit can also utilize machine learning techniques to enhance the accuracy of the generative AI. Furthermore, it can regularly update the data to keep the generative AI up-to-date. Thus, the maintenance response system can consistently generate optimal response methods, improving the efficiency of base station maintenance operations.

[0077] The maintenance response system can also include a reporting department. This department can compile the generated response methods and implementation results into reports. For example, the reporting department can automatically compile detailed information about the response methods and implementation results into a report. The reporting department can also generate reports in PDF or text format and provide them to relevant personnel. Furthermore, the reporting department can customize the report content to provide relevant personnel with information tailored to their needs. This allows relevant personnel to gain a detailed understanding of the response methods and implementation results, providing a reference for future responses.

[0078] The following is a brief description of the processing flow of Implementation Method 1.

[0079] Step 1: The data collection department gathers alarm information, technical specifications, and past response records. For example, the collection department can directly acquire alarm information from sensors in real time and save it to the database. Technical specifications are collected in PDF or text format and saved to the database. Past response records are retrieved from the database through queries.

[0080] Step 2: The analysis department analyzes the data collected by the collection department. For example, the analysis department uses generative AI to analyze the data and generate the optimal response method. It can also use data mining techniques to analyze data patterns and statistical analysis techniques to analyze data trends.

[0081] Step 3: The generation department generates response methods based on the results analyzed by the parsing department. For example, the generation department can use generative AI to generate response methods, or it can generate response methods based on operation manuals or guidelines. It can also refer to past response experience to generate response methods.

[0082] Step 4: The outsourcing department outsources tasks based on the response methods generated by the generation department. For example, the outsourcing department issues a task to an external service provider, automatically generates a task assignment form, and sends it to the external service provider. It can also confirm the content of the task and make corrections if necessary.

[0083] Implementation Method 2

[0084] The maintenance response system described in this invention utilizes generative AI to replace traditional base station maintenance response tasks. Currently, maintenance response systems rely on manual methods developed based on alarm information, technical specifications, and past response experience, which are then outsourced to external providers. By entrusting these tasks to generative AI, the time required for base station maintenance can be significantly reduced, enabling fault response that is impossible for humans. For example, the maintenance response system collects data such as alarm information, technical specifications, and past response experience. Subsequently, the system uses generative AI to analyze this data and generate the optimal response method. Based on the generated response method, the system outsources the task to external providers. This mechanism not only improves the efficiency of base station maintenance but also enables fault response that is impossible for humans. For instance, when a base station alarms, the system uses generative AI to analyze the alarm information, refers to past response experience and technical specifications, and generates the optimal response method. Based on this method, the system outsources the task to external providers, achieving rapid response. This system not only significantly reduces the time required for base station maintenance but also enables fault response that is impossible for humans. For example, even in the event of complex faults, the maintenance response system can quickly generate and implement the optimal response method through generative AI. This ensures the stable operation of the base station and is expected to improve service quality. Therefore, the maintenance response system can significantly reduce the man-hours required for base station maintenance and enable fault response that is impossible for humans.

[0085] The maintenance response system described in this embodiment includes a collection unit, an analysis unit, a generation unit, and a delegation unit. The collection unit collects data such as alarm information, technical specifications, and past response history. For example, the collection unit can collect alarm information in real time. The collection unit can also collect technical specifications in digital form. Furthermore, the collection unit can retrieve past response history from a database. For example, the collection unit can directly obtain alarm information from sensors and save it to the database in real time. Technical specifications are collected and saved to the database in PDF or text format. Past response history is retrieved from the database through queries and provided to the analysis unit. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit uses generative AI to analyze the data and generate the optimal response method. The analysis unit can also use data mining techniques to analyze data patterns or use statistical analysis techniques to analyze data trends. For example, the analysis unit inputs alarm information, technical specifications, and past response history into a generative AI to generate the optimal response method. Data mining techniques can extract useful patterns from the data, which helps in generating response methods. Statistical analysis techniques can analyze data trends and improve the accuracy of response methods. The generation unit generates response methods based on the results analyzed by the analysis unit. For example, the generation unit may utilize generative AI to generate response methods. The generation unit may also generate response methods based on operation manuals or guidelines. Furthermore, the generation unit may refer to past response experience to generate response methods. For example, the generation unit inputs the analysis results into the generative AI to generate the optimal response method. Operation manuals or guidelines serve as a reference in response method generation. Past response experience can provide response methods for similar faults. The delegation unit delegates tasks based on the response methods generated by the generation unit. For example, the delegation unit issues a task to an external operator. The delegation unit may also automatically generate a task request and send it to the external operator. Furthermore, the delegation unit can confirm the task content and make corrections as necessary. For example, the delegation unit automatically generates a task request based on the generated response method and sends it to the external operator. The task request details the response method, providing specific instructions to the external operator. The task content is confirmed by the delegation unit and corrected as necessary. Therefore, the maintenance response system according to this embodiment can significantly reduce the working hours of base station maintenance services and achieve fault response that is impossible for humans to complete.

[0086] The data collection department gathers alarm information, technical specifications, and past response records. Specifically, alarm information is acquired in real-time by sensors and immediately saved to the database. This ensures the system always has the latest alarm information, enabling rapid response. Technical specifications are digitized in PDF or text format and saved to the database. This allows technicians to quickly retrieve and access the information they need. Past response records are retrieved from the database through queries and provided to the analysis department. Analysis based on these records can then be used to generate more accurate response methods. The collection department manages this data centrally and can collaborate with other systems or departments as needed. For example, collected data can be stored on a cloud server for access by the analysis and generation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses can be implemented based on specific situations or conditions. This allows the collection department to collect data efficiently and effectively, improving overall system performance. In addition, the collection department incorporates verification processes to ensure data consistency and reliability, maintaining data quality. For example, by detecting duplicate or missing data and utilizing automatic correction algorithms, data accuracy is improved. This ensures the collection department provides highly reliable data, enhancing the overall reliability of the system.

[0087] The analysis department is used to analyze the data collected by the collection department. For example, the analysis department utilizes generative AI to analyze the data and generate optimal response methods. Specifically, alarm information, technical specifications, and past response history are input into the generative AI to generate optimal response methods. The generative AI uses natural language processing technology to analyze the technical specifications and past response history, proposing response methods based on the alarm information. Data mining technology can extract useful patterns from the data, contributing to the generation of response methods. For example, common patterns can be discovered from past response history to determine the optimal response method for similar faults. Statistical analysis technology can analyze data trends to improve the accuracy of response methods. For example, based on the frequency of alarm information and the content of technical specifications, the probability of a specific fault can be predicted, allowing for proactive countermeasures. Furthermore, the analysis department can also use historical data and statistical information for long-term risk assessment and trend analysis. For example, based on past fault data, risk changes in a specific region or time period can be predicted to formulate future countermeasures. The analysis department can also use anomaly detection algorithms to detect abnormal patterns or abnormal data and issue early warnings. Therefore, the analysis department can not only grasp the situation in real time, but also perform long-term risk management and anomaly detection, thereby improving the overall reliability and security of the system.

[0088] The generation department generates response methods based on the results analyzed by the analysis department. For example, the generation department utilizes generative AI to generate response methods. Specifically, the analysis results are input into the generative AI to generate the optimal response method. The generative AI references past response experience and technical specifications to propose optimal response steps. Operation manuals or guidelines serve as references in response method generation. For example, a specific response method can be customized based on standard response steps for a particular fault. Past response experience can provide response methods for similar faults. For example, referencing response methods for similar faults in the past, the optimal response steps are generated. The generation department integrates this information to quickly generate the optimal response method. Furthermore, the generation department can evaluate the accuracy and effectiveness of the generated response methods and make corrections when necessary. For example, the generated response methods are simulated to confirm their applicability to real-world situations. The generation department can also collect user feedback to improve response methods. Thus, the generation department can always provide highly accurate response methods based on the latest information, supporting rapid and appropriate responses. In addition, the generation department can automatically document the generated response methods and share them with other departments or systems. This ensures the consistency and transparency of response methods and improves the overall efficiency of the system.

[0089] The delegation department delegates tasks based on the response methods generated by the generation department. Specifically, it issues delegation requests to external clients. The delegation department can also automatically generate and send delegation documents to external clients. For example, it can automatically generate and send delegation documents based on the generated response methods. The delegation documents detail the response methods, providing specific instructions to external clients. The delegation department confirms the delegation content and makes corrections as necessary. For example, it confirms the content of the delegation documents and corrects any errors or ambiguities. The delegation department can also monitor the progress of delegations and follow up as needed. For example, it receives reports from external clients and confirms the progress of responses. Furthermore, the delegation department can record delegation content and progress in a database for future reference. This allows the delegation department to delegate tasks efficiently and effectively, improving the overall reliability and efficiency of the system. In addition, the delegation department can share delegation content and progress with other departments or systems to strengthen overall collaboration. For example, it can notify other departments of the delegation content and request necessary support. The delegation department can also evaluate the delegation results for future improvements. Thus, the delegation department can always provide optimal responses, improving the overall performance of the system.

[0090] The data collection department can gather alarm information, technical specifications, and past response records. For example, it can collect alarm information in real time. It can also collect technical specifications in digital form. Furthermore, it can retrieve past response records from a database. For instance, the department can directly obtain alarm information from sensors and save it to the database in real time. Technical specifications are collected and saved to the database in PDF or text format. Past response records are retrieved from the database through queries and provided to the analysis department. This allows for efficient collection of the required data.

[0091] The analysis unit is capable of analyzing collected data and generating optimal response methods. For example, it can utilize generative AI to analyze data and generate optimal response methods. The analysis unit can also use data mining techniques to analyze data patterns or statistical analysis techniques to analyze data trends. For instance, the analysis unit can input alarm information, technical specifications, and past response history into generative AI to generate optimal response methods. Data mining techniques can extract useful patterns from data, which helps in the generation of response methods. Statistical analysis techniques can analyze data trends, improving the accuracy of response methods. Thus, it is possible to analyze collected data and generate optimal response methods.

[0092] The generation department can outsource solutions to external vendors based on the generated response methods. For example, the generation department can utilize generative AI to generate response methods. It can also generate response methods based on operation manuals or guidelines. Furthermore, it can refer to past response experience when generating response methods. For instance, the generation department inputs the parsed results into the generative AI to generate the optimal response method. Operation manuals or guidelines serve as a reference in response method generation. Past response experience can provide solutions for similar failures. Therefore, it is possible to outsource solutions to external vendors based on the generated response methods.

[0093] The delegation department can delegate tasks based on the generated response methods. For example, the delegation department may issue a task to an external contractor. The delegation department can also automatically generate a task request and send it to the external contractor. The delegation department can also verify the content of the task and make corrections as necessary. For instance, the delegation department automatically generates a task request based on the generated response methods and sends it to the external contractor. The task request details the response methods and provides specific instructions to the external contractor. The content of the task is verified by the delegation department and corrected as necessary. Thus, delegation can be based on the generated response methods.

[0094] The data collection unit can infer a user's emotions and adjust the timing of data collection based on these inferred emotions. For example, when a user is stressed, the collection unit can reduce the frequency of data collection to lessen the user's burden. When a user is relaxed, the collection unit can increase the frequency of data collection to gather more detailed data. When a user is anxious, the collection unit can also quickly collect the necessary data immediately. For example, the collection unit can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. The collection unit can also record the user's voice and use voice analysis technology to infer emotions. The collection unit can also collect the user's physiological data (heart rate, skin conductance) through sensors and use emotion inference algorithms to infer emotions. For example, the collection unit can calculate an emotion score based on heart rate changes. Thus, the timing of data collection can be adjusted according to the user's emotions. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these.

[0095] The data collection department can analyze past data collection history to select the optimal collection method. For example, it can identify the most effective collection methods from past data collection history and apply them to future data collection. The department can also select the optimal collection method for specific time periods or conditions based on past data collection history. Furthermore, the department can analyze past data collection history, identify areas for improvement in specific collection methods, and optimize them. For instance, the department can retrieve past data collection history from a database and analyze it using data mining techniques. The department can select data collection methods for specific time periods or conditions to achieve efficient data collection. By identifying and optimizing specific collection methods, the department can improve the accuracy and efficiency of data collection. Thus, it is possible to analyze past data collection history and select the optimal collection method.

[0096] The data collection unit can filter data based on the current operating status of the base station and environmental conditions during data collection. For example, the collection unit can monitor the base station's operating status in real time and collect data only when an anomaly occurs. The collection unit can also consider environmental conditions (such as weather and temperature) and prioritize data collection under specific conditions. Furthermore, the collection unit can adjust the type and quantity of data collected based on the base station's operating status and environmental conditions. Thus, data collection can be filtered based on the base station's operating status and environmental conditions.

[0097] The data collection unit can infer a user's emotions and prioritize the collected data based on these inferred emotions. For example, when a user is stressed, the unit prioritizes collecting data of high importance. When a user is relaxed, the unit can prioritize collecting detailed data. When a user is anxious, the unit can prioritize collecting data that can be collected quickly. For instance, the unit can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. The unit can also record the user's voice and use voice analysis technology to infer emotions. Furthermore, the unit can collect the user's physiological data (heart rate, skin conductance) using sensors and use emotion inference algorithms to infer emotions. For example, the unit can calculate an emotion score based on heart rate changes. Thus, the unit can prioritize the collected data based on the user's emotions. Emotion inference can be achieved, for example, through emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these.

[0098] The data collection unit can consider the geographical location information of the base station during data collection, prioritizing the collection of highly relevant data. For example, the collection unit can prioritize collecting surrounding environmental data based on the geographical location information of the base station. The collection unit can also consider the geographical location information of the base station and prioritize collecting data in specific areas. Furthermore, the collection unit can filter and collect highly relevant data based on the geographical location information of the base station. For example, the collection unit can prioritize collecting surrounding environmental data based on the geographical location information of the base station. The collection unit considers the geographical location information of the base station and prioritizes collecting data in specific areas. The collection unit filters and collects highly relevant data based on the geographical location information of the base station. Therefore, it is possible to consider the geographical location information of the base station and prioritize the collection of highly relevant data.

[0099] The data collection unit can analyze the social media activity of base stations and collect relevant data during data collection. For example, the collection unit can monitor the social media activity of base stations and collect relevant data. The collection unit can also analyze trends on social media and prioritize the collection of data related to base stations. The collection unit can also collect data related to base stations based on user feedback on social media. For example, the collection unit can monitor the social media activity of base stations and collect relevant data. The collection unit can analyze trends on social media and prioritize the collection of data related to base stations. The collection unit can collect data related to base stations based on user feedback on social media. Thus, it is possible to analyze the social media activity of base stations and collect relevant data.

[0100] The analysis unit can infer a user's emotions and adjust its analysis presentation based on the inferred emotions. For example, it can provide concise and easily identifiable analysis results when the user is tense, detailed results when the user is relaxed, and concise, key-point results when the user is anxious. For instance, the analysis unit can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. It can also record the user's voice and use voice analysis technology to infer emotions. Furthermore, it can collect the user's physiological data (heart rate, skin conductance) using sensors and use emotion inference algorithms to infer emotions. For example, it can calculate an emotion score based on heart rate changes. Thus, the analysis presentation can be adjusted according to the user's emotions. Emotion inference can be achieved, for example, through emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these.

[0101] The parsing unit can adjust the level of detail in the parsing based on the importance of the data. For example, it can perform detailed parsing on highly important data, or simplified parsing on less important data. Furthermore, it can determine the parsing priority based on the importance of the data. For instance, the parsing unit assesses the importance of the data and performs detailed parsing on highly important data, while simplifying parsing on less important data. The parsing unit determines the parsing priority based on the importance of the data. Therefore, the level of detail in the parsing can be adjusted based on the importance of the data.

[0102] The parsing unit can apply different parsing algorithms based on the data category during parsing. For example, it can apply a specific parsing algorithm to data based on technical specifications. It can also apply different parsing algorithms to data based on alarm information. Furthermore, it can apply additional parsing algorithms to data based on past response history. Thus, it is possible to apply different parsing algorithms based on the data category.

[0103] The analysis unit can infer a user's emotions and adjust the length of the analysis based on the inferred emotions. For example, when a user is anxious, the analysis unit provides a concise and to-the-point analysis. When a user is relaxed, the analysis unit can provide a detailed analysis. When a user is excited, the analysis unit can provide a more visually stimulating analysis. For example, the analysis unit can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. The analysis unit can also record the user's voice and use voice analysis technology to infer emotions. The analysis unit can also collect the user's physiological data (heart rate, skin conductance) through sensors and use emotion inference algorithms to infer emotions. For example, the analysis unit can calculate an emotion score based on heart rate changes. Thus, the length of the analysis can be adjusted according to the user's emotions. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these.

[0104] The parsing unit can determine the parsing priority based on the timing of data collection. For example, it may prioritize parsing the most recent data. It may also prioritize parsing data from a specific time period based on historical data. Furthermore, the parsing unit can adjust the parsing order according to the timing of data collection. Thus, it is possible to determine the parsing priority based on the timing of data collection.

[0105] The parsing unit can adjust the parsing order based on the relevance of the data during parsing. For example, the parsing unit may prioritize parsing data with high relevance. It may also postpone processing data with low relevance. Furthermore, the parsing unit can dynamically adjust the parsing order based on the relevance of the data. For instance, the parsing unit may prioritize parsing data with high relevance and postpone processing data with low relevance. The parsing unit can dynamically adjust the parsing order based on the relevance of the data. Therefore, the parsing order can be adjusted based on the relevance of the data.

[0106] The generation unit can infer the user's emotions and adjust the expression of the generated coping methods based on the inferred user emotions. For example, when the user is nervous, the generation unit generates concise and easily recognizable coping methods. When the user is relaxed, the generation unit can also generate detailed coping methods. When the user is anxious, the generation unit can also generate coping methods that grasp the key points. For example, the generation unit can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. The generation unit can also record the user's voice and use voice analysis technology to infer emotions. The generation unit can also collect the user's physiological data (heart rate, skin conductance) through sensors and use emotion inference algorithms to infer emotions. For example, the generation unit can calculate an emotion score based on heart rate changes. Thus, the expression of the generated coping methods can be adjusted according to the user's emotions. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these.

[0107] The generation unit can adjust the level of detail generated based on the importance of the data when generating response methods. For example, the generation unit can generate detailed response methods based on data with high importance, or simplified response methods based on data with low importance. The generation unit can also determine the priority of the generated response methods based on the importance of the data. For example, the generation unit can generate detailed response methods based on data with high importance, or simplified response methods based on data with low importance. The generation unit determines the priority of the generated response methods based on the importance of the data. Therefore, the level of detail generated can be adjusted based on the importance of the data.

[0108] The generation department can apply different generation algorithms based on the data category when generating response methods. For example, the generation department can apply a specific generation algorithm to response methods based on technical specifications. It can also apply different generation algorithms to response methods based on alarm information. Furthermore, it can apply additional generation algorithms to response methods based on past response history. Thus, different generation algorithms can be applied according to the data category.

[0109] The generation unit can infer the user's emotions and prioritize the generated coping methods based on these inferred emotions. For example, when the user is nervous, the generation unit prioritizes generating high-importance coping methods. When the user is relaxed, it can also prioritize generating detailed coping methods. When the user is anxious, it can also prioritize generating coping methods that can be generated quickly. For example, the generation unit can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. The generation unit can also record the user's voice and use voice analysis technology to infer emotions. The generation unit can also collect the user's physiological data (heart rate, skin conductance) through sensors and use emotion inference algorithms to infer emotions. For example, the generation unit can calculate an emotion score based on heart rate changes. Thus, the priority of the generated coping methods can be determined according to the user's emotions. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these.

[0110] The generation unit can determine the generation priority based on the timing of data collection when generating response methods. For example, the generation unit may prioritize generating response methods based on the latest data. It may also postpone processing response methods based on past data. Furthermore, the generation unit can adjust the order in which the generated response methods are processed based on the timing of data collection. Thus, the generation priority can be determined based on the timing of data collection.

[0111] The generation unit can adjust the generation order based on data relevance during response method generation. For example, the generation unit may prioritize generating response methods based on highly relevant data. It may also postpone processing response methods based on low-relevance data. Furthermore, the generation unit can dynamically adjust the order of generated response methods based on data relevance. For instance, the generation unit may prioritize generating response methods based on highly relevant data. It may postpone processing response methods based on low-relevance data. The generation unit can dynamically adjust the order of generated response methods based on data relevance. Thus, the generation order can be adjusted based on data relevance.

[0112] The delegation department can infer a user's emotions and adjust the delivery method based on the inferred emotions. For example, when a user is nervous, the delegation department can provide a concise and easily identifiable delegation method. When a user is relaxed, the delegation department can also provide a detailed delegation method. When a user is anxious, the delegation department can also provide a concise and to-the-point delegation method. For example, the delegation department can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. The delegation department can also record the user's voice and use voice analysis technology to infer emotions. The delegation department can also collect the user's physiological data (heart rate, skin conductance) through sensors and use emotion inference algorithms to infer emotions. For example, the delegation department can calculate an emotion score based on heart rate changes. Thus, the delivery method can be adjusted according to the user's emotions. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these.

[0113] The delegation department can adjust the level of detail in delegation based on the importance of the response methods. For example, the delegation department may process delegations based on high-importance response methods in detail, while simplifying delegations based on low-importance response methods. The delegation department can also determine the priority of delegations based on the importance of the response methods. For example, the delegation department may process delegations based on high-importance response methods in detail, while simplifying delegations based on low-importance response methods. The delegation department determines the priority of delegations based on the importance of the response methods. Therefore, the level of detail in delegation can be adjusted based on the importance of the response methods.

[0114] The delegation department can apply different delegation algorithms based on the type of response method when delegation. For example, the delegation department can apply a specific delegation algorithm to response methods based on technical specifications. The delegation department can also apply different delegation algorithms to response methods based on alarm information. The delegation department can also apply additional delegation algorithms to response methods based on past response history. For example, the delegation department applies a specific delegation algorithm to response methods based on technical specifications. The delegation department applies different delegation algorithms to response methods based on alarm information. The delegation department applies additional delegation algorithms to response methods based on past response history. Thus, different delegation algorithms can be applied according to the type of response method.

[0115] The delegation department can infer a user's emotions and prioritize delegations based on these inferred emotions. For example, when a user is nervous, the department prioritizes high-importance delegations. When a user is relaxed, it can prioritize detailed delegations. When a user is anxious, it can prioritize methods that can be delegated quickly. For instance, the department can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. It can also record the user's voice and use voice analysis technology to infer emotions. Furthermore, the department can collect the user's physiological data (heart rate, skin conductance) using sensors and use emotion inference algorithms to infer emotions. For example, the department can calculate an emotion score based on heart rate changes. Thus, the department can prioritize delegations based on the user's emotions. Emotion inference can be achieved, for example, through emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these.

[0116] The delegation department can determine the priority of delegations based on the timing of response method generation. For example, the delegation department may prioritize delegations based on the latest response method. It may also postpone delegations based on past response methods. Furthermore, the delegation department can adjust the order of delegations based on the timing of response method generation. For instance, the delegation department may prioritize delegations based on the latest response method and postpone delegations based on past response methods. The delegation department can adjust the order of delegations based on the timing of response method generation. Thus, the priority of delegations can be determined based on the timing of response method generation.

[0117] The delegation department can adjust the order of delegation based on the relevance of response methods when delegation is made. For example, the delegation department may prioritize delegations based on highly relevant response methods. The delegation department may also postpone delegations based on less relevant response methods. The delegation department can also dynamically adjust the order of delegation based on the relevance of response methods. For example, the delegation department may prioritize delegations based on highly relevant response methods. The delegation department may postpone delegations based on less relevant response methods. The delegation department dynamically adjusts the order of delegation based on the relevance of response methods. Therefore, the order of delegation can be adjusted based on the relevance of response methods.

[0118] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as follows.

[0119] The maintenance response system may also include a prediction unit. This unit can predict future failures based on collected data. For example, it analyzes past failure patterns to predict the likelihood of future failures. It can also use machine learning algorithms to learn data trends and predict future failures. Furthermore, it can analyze data in real time to detect signs of failure. Thus, the maintenance response system can take preventative measures before failures occur, further ensuring the stable operation of the base station.

[0120] The maintenance response system may also include a notification department. This department can communicate generated response methods or predicted fault information to relevant personnel. For example, the notification department can send notifications via email or SMS. It can also send notifications in real time via a dedicated application. Furthermore, the notification department can customize notification content to provide relevant personnel with information appropriate to their roles. This allows relevant personnel to quickly grasp the response methods or fault information and take appropriate action.

[0121] The maintenance response system may also include an evaluation department. This department can assess the effectiveness of the generated response methods and identify areas for improvement. For example, the evaluation department collects results after the implementation of the response methods and evaluates their effectiveness. The evaluation department can also use data analysis techniques to quantitatively evaluate the effectiveness of the response methods. Furthermore, the evaluation department can collect feedback from relevant personnel and identify areas for improvement in the response methods. Thus, the maintenance response system can continuously improve response methods and increase the efficiency of base station maintenance services.

[0122] The maintenance response system may also include a learning unit. This unit can learn from collected data and evaluation results to improve the generative AI. For example, it can use past response experiences and evaluation results to refine the generative AI's algorithm. The learning unit can also utilize machine learning techniques to enhance the accuracy of the generative AI. Furthermore, it can regularly update the data to keep the generative AI up-to-date. Thus, the maintenance response system can consistently generate optimal response methods, improving the efficiency of base station maintenance operations.

[0123] The maintenance response system can also include a reporting department. This department can compile the generated response methods and implementation results into reports. For example, the reporting department can automatically compile detailed information about the response methods and implementation results into a report. The reporting department can also generate reports in PDF or text format and provide them to relevant personnel. Furthermore, the reporting department can customize the report content to provide relevant personnel with information tailored to their needs. This allows relevant personnel to gain a detailed understanding of the response methods and implementation results, providing a reference for future responses.

[0124] The maintenance response system can infer a user's emotions and adjust notification content based on these inferences. For example, when a user is stressed, the notification content can be simplified, providing only essential information. When a user is relaxed, detailed notifications can still be provided. When a user is anxious, information requiring immediate attention can be prioritized. Thus, the system can adjust notification content according to the user's emotions, providing appropriate information.

[0125] The maintenance response system can infer a user's emotions and adjust the presentation of evaluation results based on these inferred emotions. For example, when a user is nervous, it provides concise and easily identifiable evaluation results. When a user is relaxed, it can provide detailed evaluation results. When a user is anxious, it can provide evaluation results that capture the key points. Thus, it can adjust the presentation of evaluation results according to the user's emotions, providing appropriate information.

[0126] The maintenance response system can infer a user's emotions and select learning data based on these inferred emotions. For example, when a user is stressed, the amount of learning data can be reduced to lighten the burden. When a user is relaxed, detailed learning data can be selected. When a user is anxious, data that allows for rapid learning can be chosen. Thus, learning data can be selected based on the user's emotions, achieving efficient learning.

[0127] The maintenance response system can infer a user's emotions and adjust report content accordingly. For example, it can provide a concise and easily identifiable report when the user is stressed, a detailed report when the user is relaxed, and a report that highlights the key points when the user is anxious. Thus, it can adjust report content based on the user's emotions to provide appropriate information.

[0128] The maintenance response system can infer the user's emotions and adjust the presentation of predictions based on these inferred emotions. For example, it can provide concise and easily identifiable predictions when the user is anxious, detailed predictions when the user is relaxed, and key-point predictions when the user is anxious. Thus, it can adjust the presentation of predictions according to the user's emotions, providing appropriate information.

[0129] The following is a brief description of the processing flow of Implementation Method 2.

[0130] Step 1: The data collection department gathers alarm information, technical specifications, and past response records. For example, the collection department can directly acquire alarm information from sensors in real time and save it to the database. Technical specifications are collected in PDF or text format and saved to the database. Past response records are retrieved from the database through queries.

[0131] Step 2: The analysis department analyzes the data collected by the collection department. For example, the analysis department uses generative AI to analyze the data and generate the optimal response method. It can also use data mining techniques to analyze data patterns and statistical analysis techniques to analyze data trends.

[0132] Step 3: The generation department generates response methods based on the results analyzed by the parsing department. For example, the generation department can use generative AI to generate response methods, or it can generate response methods based on operation manuals or guidelines. It can also refer to past response experience to generate response methods.

[0133] Step 4: The outsourcing department outsources tasks based on the response methods generated by the generation department. For example, the outsourcing department issues a task to an external service provider, automatically generates a task assignment form, and sends it to the external service provider. It can also confirm the content of the task and make corrections if necessary.

[0134] The specific processing unit 290 sends the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires voice representing the user's input to the result of the specific processing. The control unit 46A sends the voice data representing the user's 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 voice data.

[0135] Data generation model 58 is what is known as generative AI (Artificial Intelligence). An example of data generation model 58 includes ChatGPT (registered trademark) (Internet search).<URL:https: / / openai.com / blog / chatgpt> Generative AI, such as data generation model 58, is obtained by deep learning through a neural network. The data generation model 58 is input with a prompt containing instructions, and with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the input inference data according to the instructions shown in the prompt, and outputs the inference result in one or more data forms such as speech 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 specific processing unit 290 performs the above-described specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, the data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes multiple data generation models 58, including AI other than generative AI. AI other than generative AI includes, but is not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes. Furthermore, AI can also act as an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to this example. Moreover, processing performed by AI, including generative AI, can be replaced by rule-based processing, and vice versa.

[0136] Furthermore, the processing performed by the aforementioned data processing system 10 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 it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0137] Each of the elements described above, including the collection unit, analysis unit, generation unit, and delegation unit, can be implemented, for example, in at least one of the smart device 14 and the data processing device 12. For instance, the collection unit uses the camera 42 and sensors of the smart device 14 to collect alarm information in real time, and retrieves technical specifications and past response history from the database 24 via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, uses generative AI to analyze the data via the specific processing unit 290 of the data processing device 12 to generate the optimal response method. The generation unit, for example, generates a response method based on the analysis results via the specific processing unit 290 of the data processing device 12. The delegation unit, for example, delegates the response to an external company via the control unit 46A of the smart device 14 based on the generated response method. The correspondence between the various units and the device or control unit is not limited to the above examples and can be modified in various ways.

[0138] Second Implementation Method

[0139] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0140] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. One example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0142] 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 memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0143] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system such as 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, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

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

[0146] Figure 4 An example of the main functions of the data processing device 12 and the smart glasses 214 is shown. Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0148] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0149] In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart glasses 214 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 sends the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires voice input representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0153] The data processing system 210 of the second embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed 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 it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0154] Each of the elements described above, including the collection unit, analysis unit, generation unit, and delegation unit, can be implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For instance, the collection unit uses the camera 42 and sensors of the smart glasses 214 to collect alarm information in real time, and retrieves technical specifications and past response history from the database 24 via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, uses generative AI to analyze the data via the specific processing unit 290 of the data processing device 12 to generate the optimal response method. The generation unit, for example, generates a response method based on the analysis results via the specific processing unit 290 of the data processing device 12. The delegation unit, for example, delegates the response to external businesses via the control unit 46A of the smart glasses 214 based on the generated response method. The correspondence between the various units and the device or control unit is not limited to the above examples and can be modified in various ways.

[0155] Third Implementation Method

[0156] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0157] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. An example of the data processing device 12 is a server.

[0158] 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 memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0159] The head-mounted 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 memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0160] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system such as 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, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0162] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0163] Figure 6 An example of the main functions of the data processing device 12 and the head-mounted terminal 314 is shown. Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0164] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0165] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0166] In the head-mounted terminal 314, specific processing is performed by the processor 46. A specific program 60 is stored in the memory 50. The processor 46 reads the specific program 60 from the memory 50 and executes the read specific program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific program 60 executed on the RAM 48. Furthermore, the head-mounted terminal 314 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0168] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires voice representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0169] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0170] The data processing system 310 of the third embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed 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 head-mounted terminal 314, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0171] Each of the elements described above, including the collection unit, analysis unit, generation unit, and delegation unit, can be implemented, for example, in at least one of the head-mounted terminal 314 and the data processing device 12. For example, the collection unit uses the camera 42 and sensors of the head-mounted terminal 314 to collect alarm information in real time, and retrieves technical specifications and past response history from the database 24 via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, uses generative AI to analyze the data via the specific processing unit 290 of the data processing device 12 to generate the optimal response method. The generation unit, for example, generates a response method based on the analysis results via the specific processing unit 290 of the data processing device 12. The delegation unit, for example, delegates the response to external businesses via the control unit 46A of the head-mounted terminal 314 based on the generated response method. The correspondence between the various units and the device or control unit is not limited to the above examples and can be modified in various ways.

[0172] Fourth Implementation Method

[0173] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0174] like Figure 7 As shown, 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.

[0175] 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 memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0176] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control object 443. Computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and control object 443 are also connected to the bus 52.

[0177] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0178] The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, used to photograph the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0179] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0180] The controlled object 443 includes a display device, LEDs for the eyes, and motors for driving the arms, hands, and feet. The posture and movements of the robot 414 are controlled by controlling the motors for the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, facial expressions of the robot 414 can also be expressed by controlling the illumination state of the LEDs for the robot 414's eyes.

[0181] Figure 8 An example of the main functions of the data processing device 12 and the robot 414 is shown. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0182] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0183] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in memory 50. Processor 46 reads the specific program 60 from memory 50 and executes the read specific program 60 on RAM 48. Specific processing is achieved by processor 46 acting as control unit 46A based on the specific program 60 executed on RAM 48. Furthermore, robot 414 may also have the same data generation model and emotion-specific model as data generation model 58 and emotion-specific model 59, and use these models to perform the same processing as specific processing unit 290.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0186] The specific processing unit 290 sends the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires voice representing the user's input regarding the result of the specific processing. The control unit 46A sends the voice data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0188] The data processing system 410 of the fourth embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed 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 it can also be executed jointly 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 external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0189] Each of the elements, including the aforementioned collection unit, analysis unit, generation unit, and delegation unit, can be implemented, for example, in at least one of the robot 414 and the data processing device 12. For instance, the collection unit uses the robot 414's camera 42 and sensors to collect alarm information in real time, and retrieves technical specifications and past response history from the database 24 via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, uses generative AI to analyze the data via the specific processing unit 290 of the data processing device 12 to generate the optimal response method. The generation unit, for example, generates a response method based on the analysis results via the specific processing unit 290 of the data processing device 12. The delegation unit, for example, delegates the response to external businesses via the robot 414's control unit 46A based on the generated response method. The correspondence between the various units and the device or control unit is not limited to the above examples and can be modified in various ways.

[0190] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine the user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine the user's emotion based on an emotion graph that serves as a specific mapping (see...). Figure 9 The robot's emotions can be determined by the emotion-specific model 59. In addition, the emotion-specific model 59 can also determine the robot's emotions in the same way, and the specific processing unit 290 can also perform specific processing using the robot's emotions.

[0191] Figure 9 This is a diagram representing an emotion map 400 that maps various emotions. In the emotion map 400, emotions are arranged radially from the center in concentric circles. The closer to the center of the concentric circles, the more primitive the emotion is. Further out on the concentric circles, emotions are arranged representing states or actions arising from mood. Emotion is a concept that includes both feelings and mental states. To the left of the concentric circles, emotions generated by reactions occurring in the brain are arranged roughly. To the right of the concentric circles, emotions guided by situational judgments are arranged roughly. Above and below the concentric circles, emotions generated by reactions occurring in the brain and guided by situational judgments are arranged roughly. Furthermore, the emotion of "pleasure" is arranged above the concentric circles, and the emotion of "unpleasantness" is arranged below. Thus, in the emotion map 400, various emotions are mapped according to the structure of emotion generation, while easily generated emotions are mapped nearby.

[0192] These emotions are distributed at the 3 o'clock position on the Emotion Chart 400, and usually fluctuate between peace and unease. In the right half of the Emotion Chart 400, because situational awareness is more dominant than internal feelings, it gives a sense of calm.

[0193] The inner side of the emotion diagram 400 represents the mind, and the outer side of the emotion diagram 400 represents actions. Therefore, the further you go to the outer side of the emotion diagram 400, the more the emotion can be seen (manifested in actions).

[0194] Here, human emotions are based on a balance of various factors such as posture and blood sugar levels. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. In robots, cars, and motorcycles, emotions can also be created based on a balance of factors such as posture and remaining battery power. When these balances deviate from the ideal, it indicates unhappiness; 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 Brain Physiological Signal Analysis Systems for Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the "Reaction" domain, where sensation is dominant, are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the "Situation" domain, where situational cognition is dominant, are arranged.

[0195] The emotion map defines two types of emotions that promote learning. One is a negative emotion located near the middle of "repentance" or "reflection" on the situation side. That is, when the robot experiences negative emotions such as "I never want to feel this way again" or "I never want to be scolded again." The other is a positive emotion located near "desire" on the response side. That is, when the robot experiences positive feelings such as "wanting more" or "wanting to know more."

[0196] The emotion-specific model 59 feeds user input into a pre-learned neural network to obtain emotion values ​​representing each emotion shown in the emotion graph 400, and determines the user's emotion. This neural network is pre-learned based on multiple learning data sets that combine user input with emotion values ​​representing each emotion shown in the emotion graph 400. Furthermore, this neural network is learned to... Figure 10 As shown in sentiment graph 900, nearby sentiment values ​​are similar to each other. Figure 10 Examples show how emotions such as "peace of mind," "stability," and "reassurance" can be associated with similar emotional values.

[0197] In the above embodiments, a specific processing is described by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing by multiple computers, including computer 22, is also possible.

[0198] In the above embodiments, an example of storing a specific processing program 56 in memory 32 is illustrated, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also 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 into the computer 22 of the data processing device 12. The processor 28 performs specific processing according to the specific processing program 56.

[0199] Alternatively, the specific processing program 56 can be stored in a storage device such as a server connected to the data processing device 12 via a network 54, and the specific processing program 56 can be downloaded and installed into the computer 22 upon request from the data processing device 12.

[0200] Furthermore, it is not necessary to store the entire specific process 56 in a storage device such as a server connected to the data processing device 12 via the network 54, nor is it necessary to store the entire specific process 56 in the memory 32; a portion of the specific process 56 may also be stored.

[0201] As a hardware resource for performing specific processing, various processors can be used. For example, a CPU is a general-purpose processor that functions as a hardware resource for performing specific processing by executing software, i.e., programs. Additionally, a dedicated circuit can be listed as a processor; it is a processor with a circuit structure specifically designed for performing specific processing, such as a FPGA (Field-Programmable Gate Array), PLD (Programmable Logic Device), or ASIC (Application Specific Integrated Circuit). Every processor has built-in or connected memory, and every processor executes specific processing by using that memory.

[0202] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware resources for performing a specific process can also be a single processor.

[0203] As an example of a single processor, the first type consists of a combination of one or more CPUs and software, which functions as a hardware resource to perform specific processing. The second type uses a processor, such as a System-on-a-chip (SoC), which implements the entire system functionality, including multiple hardware resources for performing specific processing, using a single IC chip. In this case, the specific processing is implemented using one or more of the aforementioned processors that serve as hardware resources.

[0204] Furthermore, as the hardware architecture of these various processors, more specifically, circuits combining semiconductor elements and other circuit components can be used. Moreover, the specific process described above is merely an example. Therefore, it goes without saying that, without departing from the main point, unnecessary steps can be removed, new steps can be added, or the processing order can be changed.

[0205] Furthermore, although the above examples have been described in terms of first to fourth embodiments, some or all of these embodiments can be combined. Additionally, the smart device 14, smart glasses 214, head-mounted terminal 314, and robot 414 are just examples and can be combined separately, or other devices may be used. Furthermore, although the above examples have been described in terms of morphological example 1 and morphological example 2, these can also be combined.

[0206] The foregoing descriptions and illustrations are detailed explanations of the parts covered by this disclosure and are merely one example of this disclosure. For instance, the descriptions of the above-described structure, function, role, and effect are just one example of the structure, function, role, and effect of the parts covered by this disclosure. Therefore, it goes without saying that, without departing from the spirit of this disclosure, unnecessary parts can be deleted, new elements can be added, or replacements can be made to the foregoing descriptions and illustrations. Furthermore, to avoid confusion and facilitate understanding of the parts covered by this disclosure, explanations of technical common sense that does not require special explanation for implementing this disclosure have been omitted from the foregoing descriptions and illustrations.

[0207] All documents, patent applications and technical standards described in this specification are incorporated herein by reference as if they were specifically and individually described as incorporated by reference.

[0208] [Postscript 1]

[0209] This includes: a data collection department, used to collect alarm information, technical specifications, past response records, and other data;

[0210] The parsing unit is used to parse the data collected by the collecting unit;

[0211] The generation unit is used to generate a response method based on the result parsed by the parsing unit;

[0212] The delegation department is used to delegate tasks based on the response method generated by the generation department.

[0213] [Postscript 2]

[0214] The system as described in Appendix 1 is characterized in that,

[0215] The collection unit is used to collect data such as alarm information, technical specifications, and past response history.

[0216] [Postscript 3]

[0217] The system as described in Appendix 1 is characterized in that,

[0218] The parsing unit is used to analyze the collected data and generate the optimal response method.

[0219] [Postscript 4]

[0220] The system as described in Appendix 1 is characterized in that,

[0221] The generation department outsources its solutions to external businesses based on the generated solutions.

[0222] [Postscript 5]

[0223] The system as described in Appendix 1 is characterized in that,

[0224] The delegation department delegates tasks based on the generated response method.

[0225] [Postscript 6]

[0226] The system as described in Appendix 1 is characterized in that,

[0227] The data collection unit is used to infer the user's emotions and adjust the timing of data collection based on the inferred user emotions.

[0228] [Postscript 7]

[0229] The system as described in Appendix 1 is characterized in that,

[0230] The data collection department analyzes past data collection history and selects the optimal collection method.

[0231] [Postscript 8]

[0232] The system as described in Appendix 1 is characterized in that,

[0233] The data collection unit filters data based on the current operating status of the base station and environmental conditions during data collection.

[0234] [Postscript 9]

[0235] The system as described in Appendix 1 is characterized in that,

[0236] The collection unit is used to infer the user's emotions and determine the priority of the collected data based on the inferred user emotions.

[0237] [Postscript 10]

[0238] The system as described in Appendix 1 is characterized in that,

[0239] When collecting data, the collection unit takes into account the geographical location information of the base station and prioritizes collecting data with high relevance.

[0240] [Postscript 11]

[0241] The system as described in Appendix 1 is characterized in that,

[0242] The collection unit analyzes the social media activities of the base station and collects relevant data during data collection.

[0243] [Postscript 12]

[0244] The system as described in Appendix 1 is characterized in that,

[0245] The parsing unit is used to infer the user's emotions and adjust the parsing presentation based on the inferred user emotions.

[0246] [Postscript 13]

[0247] The system as described in Appendix 1 is characterized in that,

[0248] During the parsing process, the parsing unit adjusts the level of detail based on the importance of the data.

[0249] [Postscript 14]

[0250] The system as described in Appendix 1 is characterized in that,

[0251] During the parsing process, the parsing unit applies different parsing algorithms based on the category of the data.

[0252] [Postscript 15]

[0253] The system as described in Appendix 1 is characterized in that,

[0254] The parsing unit is used to infer the user's emotions and adjust the length of the parsing based on the inferred user emotions.

[0255] [Postscript 16]

[0256] The system as described in Appendix 1 is characterized in that,

[0257] During the parsing process, the parsing unit determines the parsing priority based on the timing of data collection.

[0258] [Postscript 17]

[0259] The system as described in Appendix 1 is characterized in that,

[0260] During the parsing process, the parsing unit adjusts the parsing order based on the correlation of the data.

[0261] [Postscript 18]

[0262] The system as described in Appendix 1 is characterized in that,

[0263] The generation unit is used to infer the user's emotions and adjust the performance of the generated response method based on the inferred user emotions.

[0264] [Postscript 19]

[0265] The system as described in Appendix 1 is characterized in that,

[0266] When generating a response method, the generation unit adjusts the level of detail based on the importance of the data.

[0267] [Postscript 20]

[0268] The system as described in Appendix 1 is characterized in that,

[0269] When generating data, the generation unit applies different generation algorithms based on the data category.

[0270] [Postscript 21]

[0271] The system as described in Appendix 1 is characterized in that,

[0272] The generation unit is used to estimate the user's emotions and determine the priority of the generated response methods based on the estimated user emotions.

[0273] [Postscript 22]

[0274] The system as described in Appendix 1 is characterized in that,

[0275] When generating a response method, the generation unit determines the generation priority based on the timing of data collection.

[0276] [Postscript 23]

[0277] The system as described in Appendix 1 is characterized in that,

[0278] When generating a response method, the generation unit adjusts the generation order based on the relevance of the data.

[0279] [Postscript 24]

[0280] The system as described in Appendix 1 is characterized in that,

[0281] The delegation department is used to infer the user's emotions and adjust the delegation's presentation based on the inferred user emotions.

[0282] [Postscript 25]

[0283] The system as described in Appendix 1 is characterized in that,

[0284] When making a request, the department that makes the request adjusts the level of detail based on the importance of the response method.

[0285] [Postscript 26]

[0286] The system as described in Appendix 1 is characterized in that,

[0287] When delegating, the delegation department applies different delegation algorithms based on the type of response method.

[0288] [Postscript 27]

[0289] The system as described in Appendix 1 is characterized in that,

[0290] The delegation department is used to infer the user's emotions and determine the priority of delegation based on the inferred user emotions.

[0291] [Postscript 28]

[0292] The system as described in Appendix 1 is characterized in that,

[0293] When entrusting a task, the entrusting department determines the priority of the entrustment based on the timing of the generation of the response method.

[0294] [Postscript 29]

[0295] The system as described in Appendix 1 is characterized in that,

[0296] When entrusting tasks, the entrusting department adjusts the order of entrustment based on the relevance of the response methods.

Claims

1. A system, characterized in that, include: The data collection department is responsible for collecting alarm information, technical specifications, past response records, and other data. The parsing unit is used to parse the data collected by the collecting unit; The generation unit is used to generate a response method based on the result parsed by the parsing unit; The delegation department is used to delegate tasks based on the response method generated by the generation department.

2. The system as described in claim 1, characterized in that, The collection unit is used to collect data such as alarm information, technical specifications, and past response history.

3. The system as described in claim 1, characterized in that, The parsing unit is used to analyze the collected data and generate the optimal response method.

4. The system as described in claim 1, characterized in that, The generation department outsources its solutions to external businesses based on the generated solutions.

5. The system as described in claim 1, characterized in that, The delegation department delegates tasks based on the generated response method.

6. The system as described in claim 1, characterized in that, The data collection unit is used to infer the user's emotions and adjust the timing of data collection based on the inferred user emotions.

7. The system as described in claim 1, characterized in that, The data collection department analyzes past data collection history and selects the optimal collection method.

8. The system as described in claim 1, characterized in that, The data collection unit filters data based on the current operating status of the base station and environmental conditions during data collection.

Images