system

Abstract

The system according to this embodiment aims to understand customer inquiries and provide the most appropriate answers in real time. [Solution] The system according to the embodiment comprises an understanding unit, a generation unit, and an improvement unit. The understanding unit understands and classifies the customer's inquiry. The generation unit generates the optimal answer based on the inquiry classified by the understanding unit. The improvement unit improves the accuracy of the answer generated by the generation unit by learning from past response data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to provide an optimal answer to a customer's inquiry in real time, and there is a problem that the efficiency of customer support is low.

[0005] The system according to the embodiment aims to understand the content of a customer's inquiry and provide an optimal answer in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an understanding unit, a generation unit, and an improvement unit. The understanding unit understands and classifies the content of customer inquiries. The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. The improvement unit improves the accuracy of the answer generated by the generation unit by learning from past response data. [Effects of the Invention]

[0007] The system according to this embodiment can understand customer inquiries and provide the most appropriate answers in real time. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The chatbot system according to an embodiment of the present invention is a system that significantly improves the efficiency of customer support by learning patterns of customer inquiries and providing optimal answers in real time. This chatbot system understands and classifies customer inquiries using natural language processing (NLP). Next, it generates the optimal answer using machine learning. Furthermore, it learns from past interaction data to improve the accuracy of the answers. This mechanism can significantly reduce the time and cost of customer support, reduce variability in responses, and improve customer satisfaction. For example, the chatbot system understands and classifies customer inquiries using natural language processing (NLP). At this time, it identifies what kind of question the customer is asking and which category it belongs to. For example, if a customer asks, "How do I return a product?", NLP is used to classify this inquiry as "return". Next, the chatbot system generates the optimal answer using machine learning. The machine learning model generates the optimal answer to the customer inquiry based on past interaction data. For example, in response to the inquiry, "How do I return a product?", it generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." Furthermore, the chatbot system learns from past interaction data to improve the accuracy of the answers. Machine learning models continuously learn from past interaction data to improve the accuracy of their responses. For example, they can learn what kind of answers satisfied customers with past inquiries such as "How do I return this product?" and incorporate that knowledge into future responses. This mechanism can significantly reduce the time and cost of customer support. By providing fast and consistent answers, AI can reduce the burden on human customer support staff and improve customer satisfaction. It can also improve the quality of the customer experience by reducing variability in responses. Target customers include customer support departments of large corporations to small and medium-sized enterprises, online shops, and technology service providers. These target groups face challenges such as high time and cost in customer support, low customer satisfaction due to variability in responses, and delays due to staff shortages.By implementing this chatbot system, AI can provide fast and consistent answers, reducing the burden on human customer support staff while improving customer satisfaction. Furthermore, by understanding and classifying inquiries using natural language processing (NLP), generating optimal answers through machine learning, and learning from and improving based on past response data, the efficiency of customer support can be significantly improved. In this way, the chatbot system can improve the efficiency of customer support by understanding customer inquiries, generating optimal answers, and improving the accuracy of responses.

[0029] The chatbot system according to this embodiment comprises an understanding unit, a generation unit, and an improvement unit. The understanding unit understands and classifies the content of customer inquiries. The understanding unit analyzes the content of customer inquiries using, for example, natural language processing (NLP) to identify what kind of question is being asked and which category it belongs to. For example, if a customer asks, "How do I return this product?", the understanding unit uses NLP to classify this inquiry as "return". The understanding unit can accurately understand and classify the content of customer inquiries using natural language processing technology. The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. The generation unit generates the optimal answer to customer inquiries based on past response data using, for example, machine learning. For example, in response to the inquiry, "How do I return this product?", the generation unit generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to customer inquiries using a machine learning model. The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. The improvement unit, for example, continuously learns from past interaction data to improve the accuracy of its responses. For instance, the improvement unit learns what kind of answers satisfied customers with past inquiries such as "How do I return this product?" and incorporates this into future responses. By learning from past interaction data, the improvement unit can improve the accuracy of its responses. As a result, the chatbot system according to this embodiment can improve the efficiency of customer support by understanding customer inquiries, generating optimal answers, and improving the accuracy of responses.

[0030] The understanding unit understands and classifies customer inquiries. For example, it uses natural language processing (NLP) to analyze customer inquiries and identify what kind of question is being asked and which category it belongs to. Specifically, it uses NLP techniques to perform morphological analysis on customer inquiries, analyzing the structure and meaning of the sentences. For example, if a customer asks, "How do I return a product?", the understanding unit analyzes this sentence, extracts the keyword "return," and classifies the inquiry under "return." Furthermore, the understanding unit can perform more accurate classifications by considering the context and the customer's past inquiry history. For example, even if the same keyword "return" is included, it may be classified into a different category such as "exchange" or "refund" depending on the context. The understanding unit takes this contextual information into account to perform accurate classifications. In addition, the understanding unit can analyze customer inquiries in real time and generate classification results quickly. This allows the understanding unit to accurately and quickly understand customer inquiries and classify them into the appropriate category. Furthermore, the understanding unit can continuously learn and improve its classification accuracy. For example, if new inquiry patterns or keywords emerge, the understanding unit learns from them and incorporates them into subsequent classifications. This allows the understanding unit to always perform highly accurate classifications based on the latest information.

[0031] The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. For example, the generation unit uses machine learning to generate the optimal answer to a customer inquiry based on past response data. Specifically, the generation unit learns from past inquiries and their answer data to build a model for generating appropriate answers to similar inquiries. For example, in response to the inquiry, "How do I return this product?", the generation unit refers to past data and generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to a customer inquiry using a machine learning model. Furthermore, the generation unit can evaluate the quality of the generated answer and make corrections as needed. For example, if the generated answer is inappropriate, the generation unit generates other candidate answers and selects the best one. The generation unit can also collect customer feedback and continuously improve the quality of the answers. For example, it evaluates whether the customer was satisfied with the generated answer and learns answer patterns that yield high satisfaction. This allows the generation unit to quickly provide high-quality answers to customer inquiries. Furthermore, the generation unit can generate multiple answer candidates and present the customer with choices. This allows customers to choose the answer that best suits them, leading to increased satisfaction.

[0032] The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. For example, the improvement unit continuously learns from past response data to improve the accuracy of answers. Specifically, the improvement unit analyzes past inquiries and their answer data to learn what kind of answers satisfied customers. For example, it analyzes what kind of answers satisfied customers to the inquiry, "How do I return a product?", and reflects this in future answers. By learning from past response data, the improvement unit can improve the accuracy of answers. Furthermore, the improvement unit can evaluate the quality of the answers generated by the generation unit and make corrections as needed. For example, if a generated answer is inappropriate, the improvement unit generates other candidate answers and selects the best one. The improvement unit can also collect customer feedback and continuously improve the quality of answers. For example, it evaluates whether customers were satisfied with the generated answers and learns answer patterns that yield high satisfaction. This allows the improvement unit to quickly provide high-quality answers to customer inquiries. Furthermore, the improvement unit can work in conjunction with the generation unit to optimize the answer generation process. For example, a process can be established in which the improvement unit evaluates the candidate answers generated by the generation unit and selects the optimal answer. This allows the improvement unit to work with the generation unit to provide the best possible answers to customer inquiries.

[0033] The understanding unit can understand and classify customer inquiries using natural language processing. For example, the understanding unit uses natural language processing techniques to analyze customer inquiries and identify what kind of question is being asked and which category it belongs to. For example, if a customer asks, "How do I return a product?", the understanding unit uses NLP to classify this inquiry as "return". The understanding unit can accurately understand and classify customer inquiries using natural language processing techniques. This means that by using natural language processing, customer inquiries can be accurately understood and classified. Natural language processing includes, but is not limited to, techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the processing described above in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can analyze customer inquiries using natural language processing techniques, input the results into AI, and the AI ​​can classify the inquiries.

[0034] The generation unit can generate the optimal answer using machine learning. For example, the generation unit uses a machine learning model to generate the optimal answer to a customer inquiry based on past response data. For example, in response to the inquiry, "How do I return this product?", the generation unit generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to a customer inquiry using a machine learning model. Thus, by using machine learning, the optimal answer to a customer inquiry can be generated. Machine learning includes, but is not limited to, algorithms such as neural networks and support vector machines. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the customer inquiry into a machine learning model, and the AI ​​can generate the optimal answer.

[0035] The improvement unit can learn from past response data and improve the accuracy of its answers. For example, the improvement unit can continuously learn from past response data to improve the accuracy of its answers. For example, the improvement unit can learn what kind of answers satisfied customers in the past to inquiries such as "How do I return a product?" and reflect that in future answers. The improvement unit can improve the accuracy of its answers by learning from past response data. This means that by learning from past response data, the accuracy of its answers can be improved. Past response data includes, but is not limited to, customer inquiry history and response results. Some or all of the above processing in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input past response data into AI, and the AI ​​can learn to improve the accuracy of its answers.

[0036] The understanding unit can analyze a customer's past inquiry history and select the optimal understanding method. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. For example, the understanding unit can find specific patterns in a customer's past inquiry history and understand based on those patterns. For example, the understanding unit can analyze trends in the content of past inquiries the customer has made and understand based on those trends. This allows for the selection of the optimal understanding method and a quick response by analyzing past inquiry history. Past inquiry history includes, but is not limited to, pattern analysis of inquiry content and methods for storing historical data. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input a customer's past inquiry history into AI, which can then select the optimal understanding method.

[0037] The understanding unit can filter inquiries based on the customer's current situation and areas of interest. For example, if the customer is in a hurry, the understanding unit will prioritize understanding important information. For example, if the customer's areas of interest are focused on a specific product, the understanding unit will prioritize understanding information related to that product. For example, if the customer is facing a specific problem, the understanding unit will prioritize understanding information related to that problem. This allows for a more appropriate response by filtering based on the customer's current situation and areas of interest. The customer's current situation includes, but is not limited to, how real-time data is obtained and the criteria for classifying the situation. Areas of interest include, but are not limited to, the customer's past behavioral history and survey results. Some or all of the processing described above in the understanding unit may be performed using, for example, AI, or not using AI. For example, the understanding unit can input the customer's current situation and areas of interest into the AI, which can then perform the filtering.

[0038] The understanding unit can prioritize understanding highly relevant information when understanding an inquiry, taking into account the customer's geographical location. For example, if the customer is in a specific region, the understanding unit will prioritize understanding information related to that region. For example, if the customer is traveling, the understanding unit will prioritize understanding information related to their travel destination. For example, if the customer is in a specific store, the understanding unit will prioritize understanding information related to that store. This allows for the understanding of more relevant information and appropriate responses by considering the customer's geographical location. Geographical location information includes, but is not limited to, methods for acquiring GPS data and methods for analyzing location information. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the customer's geographical location information into AI, which can then prioritize understanding highly relevant information.

[0039] The understanding unit can analyze the customer's social media activity and understand relevant content when understanding an inquiry. For example, if the customer mentions a specific product on social media, the understanding unit will prioritize understanding information related to that product. For example, if the customer mentions a specific issue on social media, the understanding unit will prioritize understanding information related to that issue. For example, if the customer mentions a specific event on social media, the understanding unit will prioritize understanding information related to that event. This allows for a more relevant understanding and appropriate response by analyzing the customer's social media activity. Social media activity includes, but is not limited to, methods for analyzing post content and criteria for evaluating relevance. Some or all of the processing described above in the understanding unit may be performed using AI, for example, or not using AI. For example, the understanding unit can input the customer's social media activity into AI, which can then understand the relevant content.

[0040] The generation unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the generation unit generates a detailed response for important inquiries. For example, the generation unit generates a standard response for general inquiries. For example, the generation unit generates a concise response for simple inquiries. By adjusting the level of detail in the response based on the importance of the inquiry, more appropriate responses become possible. The level of detail in the response includes, but is not limited to, the comprehensiveness of the information and the need for detailed explanations. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance of the inquiry into the AI, and the AI ​​can adjust the level of detail in the response.

[0041] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating an answer. For example, the generation unit applies a technical generation algorithm to a technical inquiry. For example, the generation unit applies a general generation algorithm to a general inquiry. For example, the generation unit applies a customer service generation algorithm to a customer service inquiry. By applying different generation algorithms depending on the category of the inquiry, more appropriate answers can be provided. The generation algorithms include, but are not limited to, differences in algorithms for each category and application conditions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the category of the inquiry into the AI, and the AI ​​can apply an appropriate generation algorithm.

[0042] The generation unit can determine the priority of responses based on when the inquiry was submitted. For example, the generation unit can generate responses with the highest priority for urgent inquiries. For example, the generation unit can generate responses with a standard priority for regular inquiries. For example, the generation unit can generate responses with a lower priority for past inquiries. This allows for a faster response by determining the priority of responses based on when the inquiry was submitted. The priority of responses includes, but is not limited to, the submission date and urgency of the inquiry. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the priority of responses.

[0043] The generation unit can adjust the order of responses based on the relevance of the inquiries when generating answers. For example, the generation unit may generate answers first for important inquiries. For example, the generation unit may generate answers in a standard order for general inquiries. For example, the generation unit may generate answers last for simple inquiries. By adjusting the order of responses based on the relevance of the inquiries, more appropriate answers can be provided. The order of responses may include, but is not limited to, the relevance and importance of the inquiries. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the relevance of the inquiries into the AI, and the AI ​​can adjust the order of responses.

[0044] The improvement unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the improvement unit optimizes the learning algorithm based on past learning data. For example, the improvement unit finds a specific pattern from past learning data and optimizes the learning algorithm based on that pattern. For example, the improvement unit analyzes past learning data and selects the optimal learning algorithm. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved. Optimization of the learning algorithm includes, but is not limited to, methods for using past learning data and methods for adjusting the algorithm. Some or all of the above processes in the improvement unit may be performed using AI, for example, or without using AI. For example, the improvement unit can input past learning data into AI, and the AI ​​can optimize the learning algorithm.

[0045] The improvement unit can improve the accuracy of learning by considering customer attribute information during the learning process. For example, the improvement unit can improve the accuracy of learning by considering the customer's age and gender. For example, the improvement unit can improve the accuracy of learning by considering the customer's region and language. For example, the improvement unit can improve the accuracy of learning by considering the customer's purchase history. In this way, the accuracy of learning can be improved by considering customer attribute information. Customer attribute information includes, but is not limited to, age, gender, and purchase history. Some or all of the above processing in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input customer attribute information into AI, and the AI ​​can improve the accuracy of learning.

[0046] The improvement unit can weight the training data during training based on when the inquiry content was submitted. For example, the improvement unit might give a higher weight to recent inquiries, a lower weight to past inquiries, or adjust the weight of the training data for inquiries related to seasons or events. This allows for more appropriate training by weighting the training data based on when the inquiry content was submitted. The weighting of the training data includes, but is not limited to, a weighting method based on the submission date of the inquiry content and the importance of the data. Some or all of the above processing in the improvement unit may be performed using AI, for example, or without AI. For example, the improvement unit can input the submission date of the inquiry content into the AI, and the AI ​​can weight the training data.

[0047] The improvement unit can improve the accuracy of its learning by referring to customer feedback during the learning process. For example, the improvement unit adjusts the learning algorithm based on customer feedback. For example, the improvement unit identifies specific problems from customer feedback and learns to solve those problems. For example, the improvement unit analyzes customer feedback to improve the accuracy of its learning. In this way, the accuracy of learning can be improved by referring to customer feedback. Customer feedback includes, but is not limited to, methods for collecting feedback and methods for analyzing feedback. Some or all of the above processes in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input customer feedback into AI, which can then improve the accuracy of its learning.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] A chatbot system can be further equipped with a "context analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The context analysis unit analyzes the customer's past inquiry history and current situation to improve the accuracy of understanding the inquiry. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. The generation unit can generate highly relevant answers based on the customer's current situation. The improvement unit can learn from the customer's past inquiry history and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's context.

[0050] A chatbot system can be further equipped with a "geographic information analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The geographic information analysis unit takes into account the customer's geographic location information to prioritize understanding highly relevant content and generate answers. For example, if the customer is in a specific region, the understanding unit can prioritize understanding information related to that region. If the customer is traveling, the generation unit can prioritize providing answers related to their travel destination. The improvement unit can learn the customer's geographic location information and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's geographic information.

[0051] The chatbot system can also be equipped with a "social media analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The social media analysis unit analyzes the customer's social media activity, understands relevant content, and generates responses. For example, if the understanding unit sees a customer mentioning a specific product on social media, it can prioritize understanding information related to that product. If the customer sees a specific issue on social media, it can prioritize providing information related to that issue. The improvement unit can learn from the customer's social media activity and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's social media activity.

[0052] A chatbot system can be further equipped with an "attribute analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of those answers. The attribute analysis unit improves the accuracy of learning by considering customer attribute information. For example, the understanding unit can understand the inquiry by considering the customer's age and gender. The generation unit can generate optimal answers by considering the customer's region and language. The improvement unit can improve the accuracy of learning by considering the customer's purchase history. This allows for more appropriate responses by adjusting the operation of the entire system based on customer attribute information.

[0053] A chatbot system can be further equipped with a "context estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The context estimation unit analyzes the customer's past inquiry history and current situation to improve the accuracy of understanding the inquiry. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. The generation unit can generate highly relevant answers based on the customer's current situation. The improvement unit can learn from the customer's past inquiry history and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's context.

[0054] A chatbot system can be further equipped with a "geographic information estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The geographic information estimation unit takes into account the customer's geographic location information to prioritize understanding highly relevant content and generate answers. For example, if the customer is in a specific region, the understanding unit can prioritize understanding information related to that region. If the customer is traveling, the generation unit can prioritize providing information related to their travel destination. The improvement unit can learn the customer's geographic location information and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's geographic information.

[0055] The chatbot system can also be equipped with a "social media estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The social media estimation unit analyzes the customer's social media activity, understands relevant content, and generates responses. For example, if the understanding unit mentions a specific product on social media, it can prioritize understanding information related to that product. If the generation unit mentions a specific issue on social media, it can prioritize providing information related to that issue. The improvement unit can learn from the customer's social media activity and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's social media activity.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The understanding unit understands and classifies the customer's inquiry. The understanding unit uses natural language processing (NLP) to analyze the customer's inquiry and identify what kind of question it is and which category it belongs to. For example, if a customer asks, "How do I return a product?", NLP is used to classify this inquiry as "return". Step 2: The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. The generation unit uses machine learning to generate the optimal answer to customer inquiries based on past response data. For example, in response to the inquiry, "How do I return this product?", it generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." Step 3: The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. The improvement unit continuously learns from past response data to improve the accuracy of the answers. For example, it learns what kind of answers satisfied customers in the past to inquiries such as "How do I return a product?" and reflects this in future answers.

[0058] (Example of form 2) The chatbot system according to an embodiment of the present invention is a system that significantly improves the efficiency of customer support by learning patterns of customer inquiries and providing optimal answers in real time. This chatbot system understands and classifies customer inquiries using natural language processing (NLP). Next, it generates the optimal answer using machine learning. Furthermore, it learns from past interaction data to improve the accuracy of the answers. This mechanism can significantly reduce the time and cost of customer support, reduce variability in responses, and improve customer satisfaction. For example, the chatbot system understands and classifies customer inquiries using natural language processing (NLP). At this time, it identifies what kind of question the customer is asking and which category it belongs to. For example, if a customer asks, "How do I return a product?", NLP is used to classify this inquiry as "return". Next, the chatbot system generates the optimal answer using machine learning. The machine learning model generates the optimal answer to the customer inquiry based on past interaction data. For example, in response to the inquiry, "How do I return a product?", it generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." Furthermore, the chatbot system learns from past interaction data to improve the accuracy of the answers. Machine learning models continuously learn from past interaction data to improve the accuracy of their responses. For example, they can learn what kind of answers satisfied customers with past inquiries such as "How do I return this product?" and incorporate that knowledge into future responses. This mechanism can significantly reduce the time and cost of customer support. By providing fast and consistent answers, AI can reduce the burden on human customer support staff and improve customer satisfaction. It can also improve the quality of the customer experience by reducing variability in responses. Target customers include customer support departments of large corporations to small and medium-sized enterprises, online shops, and technology service providers. These target groups face challenges such as high time and cost in customer support, low customer satisfaction due to variability in responses, and delays due to staff shortages.By implementing this chatbot system, AI can provide fast and consistent answers, reducing the burden on human customer support staff while improving customer satisfaction. Furthermore, by understanding and classifying inquiries using natural language processing (NLP), generating optimal answers through machine learning, and learning from and improving based on past response data, the efficiency of customer support can be significantly improved. In this way, the chatbot system can improve the efficiency of customer support by understanding customer inquiries, generating optimal answers, and improving the accuracy of responses.

[0059] The chatbot system according to this embodiment comprises an understanding unit, a generation unit, and an improvement unit. The understanding unit understands and classifies the content of customer inquiries. The understanding unit analyzes the content of customer inquiries using, for example, natural language processing (NLP) to identify what kind of question is being asked and which category it belongs to. For example, if a customer asks, "How do I return this product?", the understanding unit uses NLP to classify this inquiry as "return". The understanding unit can accurately understand and classify the content of customer inquiries using natural language processing technology. The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. The generation unit generates the optimal answer to customer inquiries based on past response data using, for example, machine learning. For example, in response to the inquiry, "How do I return this product?", the generation unit generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to customer inquiries using a machine learning model. The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. The improvement unit, for example, continuously learns from past interaction data to improve the accuracy of its responses. For instance, the improvement unit learns what kind of answers satisfied customers with past inquiries such as "How do I return this product?" and incorporates this into future responses. By learning from past interaction data, the improvement unit can improve the accuracy of its responses. As a result, the chatbot system according to this embodiment can improve the efficiency of customer support by understanding customer inquiries, generating optimal answers, and improving the accuracy of responses.

[0060] The understanding unit understands and classifies customer inquiries. For example, it uses natural language processing (NLP) to analyze customer inquiries and identify what kind of question is being asked and which category it belongs to. Specifically, it uses NLP techniques to perform morphological analysis on customer inquiries, analyzing the structure and meaning of the sentences. For example, if a customer asks, "How do I return a product?", the understanding unit analyzes this sentence, extracts the keyword "return," and classifies the inquiry under "return." Furthermore, the understanding unit can perform more accurate classifications by considering the context and the customer's past inquiry history. For example, even if the same keyword "return" is included, it may be classified into a different category such as "exchange" or "refund" depending on the context. The understanding unit takes this contextual information into account to perform accurate classifications. In addition, the understanding unit can analyze customer inquiries in real time and generate classification results quickly. This allows the understanding unit to accurately and quickly understand customer inquiries and classify them into the appropriate category. Furthermore, the understanding unit can continuously learn and improve its classification accuracy. For example, if new inquiry patterns or keywords emerge, the understanding unit learns from them and incorporates them into subsequent classifications. This allows the understanding unit to always perform highly accurate classifications based on the latest information.

[0061] The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. For example, the generation unit uses machine learning to generate the optimal answer to a customer inquiry based on past response data. Specifically, the generation unit learns from past inquiries and their answer data to build a model for generating appropriate answers to similar inquiries. For example, in response to the inquiry, "How do I return this product?", the generation unit refers to past data and generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to a customer inquiry using a machine learning model. Furthermore, the generation unit can evaluate the quality of the generated answer and make corrections as needed. For example, if the generated answer is inappropriate, the generation unit generates other candidate answers and selects the best one. The generation unit can also collect customer feedback and continuously improve the quality of the answers. For example, it evaluates whether the customer was satisfied with the generated answer and learns answer patterns that yield high satisfaction. This allows the generation unit to quickly provide high-quality answers to customer inquiries. Furthermore, the generation unit can generate multiple answer candidates and present the customer with choices. This allows customers to choose the answer that best suits them, leading to increased satisfaction.

[0062] The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. For example, the improvement unit continuously learns from past response data to improve the accuracy of answers. Specifically, the improvement unit analyzes past inquiries and their answer data to learn what kind of answers satisfied customers. For example, it analyzes what kind of answers satisfied customers to the inquiry, "How do I return a product?", and reflects this in future answers. By learning from past response data, the improvement unit can improve the accuracy of answers. Furthermore, the improvement unit can evaluate the quality of the answers generated by the generation unit and make corrections as needed. For example, if a generated answer is inappropriate, the improvement unit generates other candidate answers and selects the best one. The improvement unit can also collect customer feedback and continuously improve the quality of answers. For example, it evaluates whether customers were satisfied with the generated answers and learns answer patterns that yield high satisfaction. This allows the improvement unit to quickly provide high-quality answers to customer inquiries. Furthermore, the improvement unit can work in conjunction with the generation unit to optimize the answer generation process. For example, a process can be established in which the improvement unit evaluates the candidate answers generated by the generation unit and selects the optimal answer. This allows the improvement unit to work with the generation unit to provide the best possible answers to customer inquiries.

[0063] The understanding unit can understand and classify customer inquiries using natural language processing. For example, the understanding unit uses natural language processing techniques to analyze customer inquiries and identify what kind of question is being asked and which category it belongs to. For example, if a customer asks, "How do I return a product?", the understanding unit uses NLP to classify this inquiry as "return". The understanding unit can accurately understand and classify customer inquiries using natural language processing techniques. This means that by using natural language processing, customer inquiries can be accurately understood and classified. Natural language processing includes, but is not limited to, techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the processing described above in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can analyze customer inquiries using natural language processing techniques, input the results into AI, and the AI ​​can classify the inquiries.

[0064] The generation unit can generate the optimal answer using machine learning. For example, the generation unit uses a machine learning model to generate the optimal answer to a customer inquiry based on past response data. For example, in response to the inquiry, "How do I return this product?", the generation unit generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." The generation unit can generate the optimal answer to a customer inquiry using a machine learning model. Thus, by using machine learning, the optimal answer to a customer inquiry can be generated. Machine learning includes, but is not limited to, algorithms such as neural networks and support vector machines. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the customer inquiry into a machine learning model, and the AI ​​can generate the optimal answer.

[0065] The improvement unit can learn from past response data and improve the accuracy of its answers. For example, the improvement unit can continuously learn from past response data to improve the accuracy of its answers. For example, the improvement unit can learn what kind of answers satisfied customers in the past to inquiries such as "How do I return a product?" and reflect that in future answers. The improvement unit can improve the accuracy of its answers by learning from past response data. This means that by learning from past response data, the accuracy of its answers can be improved. Past response data includes, but is not limited to, customer inquiry history and response results. Some or all of the above processing in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input past response data into AI, and the AI ​​can learn to improve the accuracy of its answers.

[0066] The understanding unit can estimate the customer's emotions and adjust the accuracy of its understanding of the inquiry based on the estimated emotions. For example, if the customer is angry, the understanding unit will analyze the inquiry more carefully and perform a detailed understanding to avoid misunderstandings. For example, if the customer is confused, the understanding unit will understand the inquiry concisely and respond quickly. For example, if the customer is relaxed, the understanding unit will understand the inquiry with normal accuracy and provide a standard response. This allows for a more appropriate response by adjusting the accuracy of understanding based on the customer's emotions. The estimation of customer emotions is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using AI or not using AI. For example, the understanding unit can input the customer's inquiry into an emotion engine to estimate the customer's emotions, and the emotion engine can estimate the customer's emotions.

[0067] The understanding unit can analyze a customer's past inquiry history and select the optimal understanding method. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. For example, the understanding unit can find specific patterns in a customer's past inquiry history and understand based on those patterns. For example, the understanding unit can analyze trends in the content of past inquiries the customer has made and understand based on those trends. This allows for the selection of the optimal understanding method and a quick response by analyzing past inquiry history. Past inquiry history includes, but is not limited to, pattern analysis of inquiry content and methods for storing historical data. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input a customer's past inquiry history into AI, which can then select the optimal understanding method.

[0068] The understanding unit can filter inquiries based on the customer's current situation and areas of interest. For example, if the customer is in a hurry, the understanding unit will prioritize understanding important information. For example, if the customer's areas of interest are focused on a specific product, the understanding unit will prioritize understanding information related to that product. For example, if the customer is facing a specific problem, the understanding unit will prioritize understanding information related to that problem. This allows for a more appropriate response by filtering based on the customer's current situation and areas of interest. The customer's current situation includes, but is not limited to, how real-time data is obtained and the criteria for classifying the situation. Areas of interest include, but are not limited to, the customer's past behavioral history and survey results. Some or all of the processing described above in the understanding unit may be performed using, for example, AI, or not using AI. For example, the understanding unit can input the customer's current situation and areas of interest into the AI, which can then perform the filtering.

[0069] The understanding unit can estimate the customer's emotions and determine the priority of inquiries to understand based on the estimated emotions. For example, if the customer is angry, the understanding unit will prioritize understanding that inquiry. For example, if the customer is confused, the understanding unit will quickly understand that inquiry. For example, if the customer is relaxed, the understanding unit will understand that inquiry with normal priority. This allows for a faster response by prioritizing based on the customer's emotions. The estimation of customer emotions is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using AI or not using AI. For example, the understanding unit can input the customer's inquiry into an emotion engine to estimate the customer's emotions, and the emotion engine can estimate the customer's emotions.

[0070] The understanding unit can prioritize understanding highly relevant information when understanding an inquiry, taking into account the customer's geographical location. For example, if the customer is in a specific region, the understanding unit will prioritize understanding information related to that region. For example, if the customer is traveling, the understanding unit will prioritize understanding information related to their travel destination. For example, if the customer is in a specific store, the understanding unit will prioritize understanding information related to that store. This allows for the understanding of more relevant information and appropriate responses by considering the customer's geographical location. Geographical location information includes, but is not limited to, methods for acquiring GPS data and methods for analyzing location information. Some or all of the above processing in the understanding unit may be performed using AI, for example, or without AI. For example, the understanding unit can input the customer's geographical location information into AI, which can then prioritize understanding highly relevant information.

[0071] The understanding unit can analyze the customer's social media activity and understand relevant content when understanding an inquiry. For example, if the customer mentions a specific product on social media, the understanding unit will prioritize understanding information related to that product. For example, if the customer mentions a specific issue on social media, the understanding unit will prioritize understanding information related to that issue. For example, if the customer mentions a specific event on social media, the understanding unit will prioritize understanding information related to that event. This allows for a more relevant understanding and appropriate response by analyzing the customer's social media activity. Social media activity includes, but is not limited to, methods for analyzing post content and criteria for evaluating relevance. Some or all of the processing described above in the understanding unit may be performed using AI, for example, or not using AI. For example, the understanding unit can input the customer's social media activity into AI, which can then understand the relevant content.

[0072] The generation unit can estimate the customer's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the customer is angry, the generation unit will use a polite and calm expression. If the customer is confused, the generation unit will use a concise and easy-to-understand expression. If the customer is relaxed, the generation unit will use a normal expression. By adjusting the way the response is expressed based on the customer's emotions, a more appropriate response becomes possible. The estimation of the customer's emotions is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, in order to estimate the customer's emotions, the generation unit can input the customer's inquiry into an emotion engine, and the emotion engine can estimate the customer's emotions.

[0073] The generation unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the generation unit generates a detailed response for important inquiries. For example, the generation unit generates a standard response for general inquiries. For example, the generation unit generates a concise response for simple inquiries. By adjusting the level of detail in the response based on the importance of the inquiry, more appropriate responses become possible. The level of detail in the response includes, but is not limited to, the comprehensiveness of the information and the need for detailed explanations. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance of the inquiry into the AI, and the AI ​​can adjust the level of detail in the response.

[0074] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating an answer. For example, the generation unit applies a technical generation algorithm to a technical inquiry. For example, the generation unit applies a general generation algorithm to a general inquiry. For example, the generation unit applies a customer service generation algorithm to a customer service inquiry. By applying different generation algorithms depending on the category of the inquiry, more appropriate answers can be provided. The generation algorithms include, but are not limited to, differences in algorithms for each category and application conditions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the category of the inquiry into the AI, and the AI ​​can apply an appropriate generation algorithm.

[0075] The generation unit can estimate the customer's emotions and adjust the length of the response based on the estimated emotions. For example, if the customer is angry, the generation unit will generate a concise and to-the-point response. If the customer is confused, the generation unit will generate a detailed and easy-to-understand response. If the customer is relaxed, the generation unit will generate a response of normal length. By adjusting the length of the response based on the customer's emotions, a more appropriate response can be provided. The estimation of customer emotions is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, or not using AI. For example, the generation unit can input the customer's inquiry into an emotion engine to estimate the customer's emotions, and the emotion engine can estimate the customer's emotions.

[0076] The generation unit can determine the priority of responses based on when the inquiry was submitted. For example, the generation unit can generate responses with the highest priority for urgent inquiries. For example, the generation unit can generate responses with a standard priority for regular inquiries. For example, the generation unit can generate responses with a lower priority for past inquiries. This allows for a faster response by determining the priority of responses based on when the inquiry was submitted. The priority of responses includes, but is not limited to, the submission date and urgency of the inquiry. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the priority of responses.

[0077] The generation unit can adjust the order of responses based on the relevance of the inquiries when generating answers. For example, the generation unit may generate answers first for important inquiries. For example, the generation unit may generate answers in a standard order for general inquiries. For example, the generation unit may generate answers last for simple inquiries. By adjusting the order of responses based on the relevance of the inquiries, more appropriate answers can be provided. The order of responses may include, but is not limited to, the relevance and importance of the inquiries. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the relevance of the inquiries into the AI, and the AI ​​can adjust the order of responses.

[0078] The improvement unit can estimate the customer's emotions and select training data based on the estimated customer emotions. For example, if the customer is angry, the improvement unit will select training data related to anger. For example, if the customer is confused, the improvement unit will select training data related to confusion. For example, if the customer is relaxed, the improvement unit will select training data related to relaxation. By selecting training data based on the customer's emotions, more appropriate learning becomes possible. The estimation of customer emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the improvement unit may be performed using AI, for example, or without AI. For example, in order to estimate the customer's emotions, the improvement unit can input the customer's inquiry into an emotion engine, and the emotion engine can estimate the customer's emotions.

[0079] The improvement unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the improvement unit optimizes the learning algorithm based on past learning data. For example, the improvement unit finds a specific pattern from past learning data and optimizes the learning algorithm based on that pattern. For example, the improvement unit analyzes past learning data and selects the optimal learning algorithm. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved. Optimization of the learning algorithm includes, but is not limited to, methods for using past learning data and methods for adjusting the algorithm. Some or all of the above processes in the improvement unit may be performed using AI, for example, or without using AI. For example, the improvement unit can input past learning data into AI, and the AI ​​can optimize the learning algorithm.

[0080] The improvement unit can improve the accuracy of learning by considering customer attribute information during the learning process. For example, the improvement unit can improve the accuracy of learning by considering the customer's age and gender. For example, the improvement unit can improve the accuracy of learning by considering the customer's region and language. For example, the improvement unit can improve the accuracy of learning by considering the customer's purchase history. In this way, the accuracy of learning can be improved by considering customer attribute information. Customer attribute information includes, but is not limited to, age, gender, and purchase history. Some or all of the above processing in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input customer attribute information into AI, and the AI ​​can improve the accuracy of learning.

[0081] The improvement unit can estimate the customer's emotions and adjust the learning frequency based on the estimated emotions. For example, if the customer is angry, the improvement unit increases the learning frequency. For example, if the customer is confused, the improvement unit adjusts the learning frequency. For example, if the customer is relaxed, the improvement unit returns the learning frequency to normal. This allows for more appropriate learning by adjusting the learning frequency based on the customer's emotions. The estimation of customer emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the improvement unit may be performed using AI or not using AI. For example, in order to estimate the customer's emotions, the improvement unit can input the customer's inquiry into an emotion engine, and the emotion engine can estimate the customer's emotions.

[0082] The improvement unit can weight the training data during training based on when the inquiry content was submitted. For example, the improvement unit might give a higher weight to recent inquiries, a lower weight to past inquiries, or adjust the weight of the training data for inquiries related to seasons or events. This allows for more appropriate training by weighting the training data based on when the inquiry content was submitted. The weighting of the training data includes, but is not limited to, a weighting method based on the submission date of the inquiry content and the importance of the data. Some or all of the above processing in the improvement unit may be performed using AI, for example, or without AI. For example, the improvement unit can input the submission date of the inquiry content into the AI, and the AI ​​can weight the training data.

[0083] The improvement unit can improve the accuracy of its learning by referring to customer feedback during the learning process. For example, the improvement unit adjusts the learning algorithm based on customer feedback. For example, the improvement unit identifies specific problems from customer feedback and learns to solve those problems. For example, the improvement unit analyzes customer feedback to improve the accuracy of its learning. In this way, the accuracy of learning can be improved by referring to customer feedback. Customer feedback includes, but is not limited to, methods for collecting feedback and methods for analyzing feedback. Some or all of the above processes in the improvement unit may be performed using, for example, AI, or not using AI. For example, the improvement unit can input customer feedback into AI, which can then improve the accuracy of its learning.

[0084] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0085] A chatbot system can be further equipped with a "sentiment analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The sentiment analysis unit estimates the customer's emotions from the content of the inquiry and adjusts the operation of other elements based on those emotions. For example, if the customer is angry, the understanding unit can analyze the inquiry more carefully and perform a detailed understanding to avoid misunderstandings. If the customer is confused, the generation unit can generate a concise and easy-to-understand answer. If the customer is relaxed, the improvement unit can learn at a normal learning frequency. This allows for a more appropriate response by adjusting the operation of the entire system based on the customer's emotions.

[0086] A chatbot system can be further equipped with a "context analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The context analysis unit analyzes the customer's past inquiry history and current situation to improve the accuracy of understanding the inquiry. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. The generation unit can generate highly relevant answers based on the customer's current situation. The improvement unit can learn from the customer's past inquiry history and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's context.

[0087] A chatbot system can be further equipped with a "geographic information analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The geographic information analysis unit takes into account the customer's geographic location information to prioritize understanding highly relevant content and generate answers. For example, if the customer is in a specific region, the understanding unit can prioritize understanding information related to that region. If the customer is traveling, the generation unit can prioritize providing answers related to their travel destination. The improvement unit can learn the customer's geographic location information and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's geographic information.

[0088] The chatbot system can also be equipped with a "social media analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The social media analysis unit analyzes the customer's social media activity, understands relevant content, and generates responses. For example, if the understanding unit sees a customer mentioning a specific product on social media, it can prioritize understanding information related to that product. If the customer sees a specific issue on social media, it can prioritize providing information related to that issue. The improvement unit can learn from the customer's social media activity and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's social media activity.

[0089] A chatbot system can be further equipped with an "attribute analysis unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of those answers. The attribute analysis unit improves the accuracy of learning by considering customer attribute information. For example, the understanding unit can understand the inquiry by considering the customer's age and gender. The generation unit can generate optimal answers by considering the customer's region and language. The improvement unit can improve the accuracy of learning by considering the customer's purchase history. This allows for more appropriate responses by adjusting the operation of the entire system based on customer attribute information.

[0090] A chatbot system can be further equipped with an "emotion estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The emotion estimation unit estimates the customer's emotions and adjusts the operation of other elements based on those emotions. For example, if the customer is angry, the understanding unit can analyze the inquiry more carefully and perform a detailed understanding to avoid misunderstandings. If the customer is confused, the generation unit can generate a concise and easy-to-understand answer. If the customer is relaxed, the improvement unit can learn at a normal learning frequency. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's emotions.

[0091] A chatbot system can be further equipped with a "context estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The context estimation unit analyzes the customer's past inquiry history and current situation to improve the accuracy of understanding the inquiry. For example, the understanding unit can quickly understand similar inquiries based on the content of inquiries the customer has frequently made in the past. The generation unit can generate highly relevant answers based on the customer's current situation. The improvement unit can learn from the customer's past inquiry history and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's context.

[0092] A chatbot system can be further equipped with a "geographic information estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The geographic information estimation unit takes into account the customer's geographic location information to prioritize understanding highly relevant content and generate answers. For example, if the customer is in a specific region, the understanding unit can prioritize understanding information related to that region. If the customer is traveling, the generation unit can prioritize providing information related to their travel destination. The improvement unit can learn the customer's geographic location information and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's geographic information.

[0093] The chatbot system can also be equipped with a "social media estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The social media estimation unit analyzes the customer's social media activity, understands relevant content, and generates responses. For example, if the understanding unit mentions a specific product on social media, it can prioritize understanding information related to that product. If the generation unit mentions a specific issue on social media, it can prioritize providing information related to that issue. The improvement unit can learn from the customer's social media activity and improve the accuracy of responses. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's social media activity.

[0094] A chatbot system can be further equipped with an "emotion estimation unit" to understand customer inquiries, generate optimal answers, and improve the accuracy of responses. The emotion estimation unit estimates the customer's emotions and adjusts the operation of other elements based on those emotions. For example, if the customer is angry, the understanding unit can analyze the inquiry more carefully and perform a detailed understanding to avoid misunderstandings. If the customer is confused, the generation unit can generate a concise and easy-to-understand answer. If the customer is relaxed, the improvement unit can learn at a normal learning frequency. This allows for more appropriate responses by adjusting the operation of the entire system based on the customer's emotions.

[0095] The following briefly describes the processing flow for example form 2.

[0096] Step 1: The understanding unit understands and classifies the customer's inquiry. The understanding unit uses natural language processing (NLP) to analyze the customer's inquiry and identify what kind of question it is and which category it belongs to. For example, if a customer asks, "How do I return a product?", NLP is used to classify this inquiry as "return". Step 2: The generation unit generates the optimal answer based on the inquiry content classified by the understanding unit. The generation unit uses machine learning to generate the optimal answer to customer inquiries based on past response data. For example, in response to the inquiry, "How do I return this product?", it generates an answer such as, "To return the product, pack it in its original condition and return it using the enclosed return label." Step 3: The improvement unit improves the accuracy of the answers generated by the generation unit by learning from past response data. The improvement unit continuously learns from past response data to improve the accuracy of the answers. For example, it learns what kind of answers satisfied customers in the past to inquiries such as "How do I return a product?" and reflects this in future answers.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio 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 specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0099] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0100] Each of the multiple elements described above, including the understanding unit, generation unit, and improvement unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the understanding unit is implemented by the processor 46 of the smart device 14, which analyzes and classifies customer inquiries using natural language processing (NLP). The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates the optimal answer using machine learning. The improvement unit is implemented by the identification processing unit 290 of the data processing unit 12, which improves the accuracy of the answer by learning from past correspondence data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0101] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0102] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0107] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0108] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0109] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0110] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0111] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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 specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the understanding unit, generation unit, and improvement unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the understanding unit is implemented by the processor 46 of the smart glasses 214, which analyzes and classifies customer inquiries using natural language processing (NLP). The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates the optimal answer using machine learning. The improvement unit is implemented by the identification processing unit 290 of the data processing unit 12, which improves the accuracy of the answer by learning past correspondence data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0117] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0118] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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 specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the understanding unit, generation unit, and improvement unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the understanding unit is implemented by the processor 46 of the headset terminal 314, which analyzes and classifies customer inquiries using natural language processing (NLP). The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates the optimal answer using machine learning. The improvement unit is implemented by the identification processing unit 290 of the data processing unit 12, which improves the accuracy of the answer by learning past correspondence data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0133] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0134] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0141] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0144] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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 specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the understanding unit, generation unit, and improvement unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the understanding unit is implemented by the processor 46 of the robot 414, which analyzes and classifies customer inquiries using natural language processing (NLP). The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates the optimal answer using machine learning. The improvement unit is implemented by the identification processing unit 290 of the data processing unit 12, which improves the accuracy of the answer by learning from past correspondence data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0150] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0152] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0153] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0154] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0158] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0159] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0160] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0161] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0162] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0163] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0165] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0166] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0167] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0168] (Note 1) An understanding unit that understands and classifies customer inquiries, A generation unit that generates the optimal answer based on the inquiry content classified by the understanding unit, The system includes an improvement unit that improves the accuracy of the answers generated by the generation unit by learning from past corresponding data. A system characterized by the following features. (Note 2) The aforementioned understanding unit is, Use natural language processing to understand and classify customer inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Using machine learning to generate the optimal answer The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned improvement unit is, Learn from past response data to improve the accuracy of responses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned understanding unit is, It estimates customer emotions and adjusts the accuracy of understanding the inquiry based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned understanding unit is, Analyze the customer's past inquiry history and select the most appropriate method of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned understanding unit is, When understanding inquiries, filtering is performed based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned understanding unit is, Estimate customer emotions and prioritize inquiries that require understanding based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned understanding unit is, When understanding customer inquiries, we prioritize understanding the most relevant information by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned understanding unit is, When understanding customer inquiries, we analyze their social media activity to identify relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is We estimate the customer's emotions and adjust the way we express our responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is When generating an answer, adjust the level of detail in the answer based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating responses, different generation algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is The system estimates customer emotions and adjusts the length of responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating responses, the priority of responses is determined based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating responses, the order of responses is adjusted based on the relevance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned improvement unit is, The system estimates customer emotions and selects training data based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned improvement unit is, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned improvement unit is, During training, consider customer attribute information to improve the accuracy of the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned improvement unit is, It estimates customer emotions and adjusts the learning frequency based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned improvement unit is, During training, the training data is weighted based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned improvement unit is, During the learning process, we refer to customer feedback to improve the accuracy of the learning. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An understanding unit that understands and classifies customer inquiries, A generation unit that generates the optimal answer based on the inquiry content classified by the understanding unit, The system includes an improvement unit that improves the accuracy of the answers generated by the generation unit by learning from past corresponding data. A system characterized by the following features.

2. The aforementioned understanding unit is, Use natural language processing to understand and classify customer inquiries. The system according to feature 1.

3. The generating unit is Using machine learning to generate the optimal answer The system according to feature 1.

4. The aforementioned improvement unit is, Learn from past response data to improve the accuracy of responses. The system according to feature 1.

5. The aforementioned understanding unit is, It estimates customer emotions and adjusts the accuracy of understanding the inquiry based on the estimated customer emotions. The system according to feature 1.

6. The aforementioned understanding unit is, Analyze the customer's past inquiry history and select the most appropriate method of understanding. The system according to feature 1.

7. The aforementioned understanding unit is, When understanding inquiries, filtering is performed based on the customer's current situation and areas of interest. The system according to feature 1.

8. The aforementioned understanding unit is, Estimate customer emotions and prioritize inquiries that require understanding based on those estimated emotions. The system according to feature 1.

9. The aforementioned understanding unit is, When understanding customer inquiries, we prioritize understanding the most relevant information by considering the customer's geographical location. The system according to feature 1.

10. The aforementioned understanding unit is, When understanding customer inquiries, we analyze their social media activity to identify relevant content. The system according to feature 1.

Images