system

Abstract

The system according to the embodiment aims to improve the efficiency of responses to user inquiries and to resolve resource shortages. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a response unit, a learning unit, and a switching unit. The reception unit receives user inquiries. The analysis unit analyzes the content of the inquiry received by the reception unit. The response unit provides an answer based on the content analyzed by the analysis unit. The learning unit constantly reads the answer content provided by the response unit as new data. The switching unit has a human respond to unreasonable or complex inquiries.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies may result in resource shortages and delays in responding to user inquiries.

[0005] The system according to the embodiment aims to improve the efficiency of responses to user inquiries and to resolve resource shortages. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a response unit, a learning unit, and a switching unit. The reception unit receives user inquiries. The analysis unit analyzes the content of the inquiry received by the reception unit. The response unit provides an answer based on the content analyzed by the analysis unit. The learning unit constantly reads the answer content provided by the response unit as new data. The switching unit has a human respond to unreasonable or complicated inquiries. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of responding to user inquiries and resolve resource shortages. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A sales digitalization system according to an embodiment of the present invention uses generative AI to resolve sales activities and resource shortages. This sales digitalization system accepts user inquiries and requests, and the generative AI provides appropriate answers, automating communication with the user. Furthermore, the generative AI constantly reads user inquiries as new data, enabling rapid responses to similar questions. This enables responses to user inquiries 24 hours a day, 365 days a year. For difficult or complex inquiries, a system is implemented in which humans respond during business hours. This system eliminates sales staff shortages and realizes efficient sales activities. Furthermore, smooth communication with users is expected to improve customer satisfaction. For example, a sales digitalization system includes a reception unit that accepts user inquiries. The reception unit accepts user inquiries and requests using generative AI. Next, the system includes an analysis unit that analyzes the inquiries accepted by the reception unit. The analysis unit uses generative AI to analyze the inquiries and extract information for providing appropriate answers. The system also includes an answering unit that provides appropriate answers based on the content analyzed by the analysis unit. The answering unit uses generative AI to provide appropriate answers to user questions. It is equipped with a learning unit that constantly reads the answer content provided by the answering unit as new data. The learning unit uses generation AI to learn the answer content provided, enabling it to respond quickly to future inquiries. It is equipped with a switching unit that switches impossible or complex inquiries to a human response. The switching unit uses generation AI to detect impossible or complex inquiries and switches to a human response during business hours. This allows the sales digitalization system to efficiently accept, analyze, respond to, and learn from user inquiries, and switch to a human as needed. This allows the sales digitalization system to eliminate sales staff shortages and realize efficient sales activities. In addition, smooth communication with users is expected to improve customer satisfaction.

[0029] A sales digitalization system according to an embodiment includes a reception unit, an analysis unit, a response unit, a learning unit, and a switching unit. The reception unit receives user inquiries. User inquiries include, but are not limited to, product-related questions, service requests, and technical support requests. The reception unit receives user inquiries using, for example, a generation AI. The generation AI understands the user's inquiry using natural language processing technology and responds appropriately. The analysis unit analyzes the inquiry received by the reception unit. The analysis unit analyzes the inquiry using, for example, the generation AI and extracts information for providing an appropriate answer. The generation AI analyzes the inquiry using, for example, a text generation AI (e.g., LLM). The analysis unit can also analyze multiple modalities, such as images and audio, in addition to text, using a multimodal generation AI. The response unit provides an appropriate answer based on the content analyzed by the analysis unit. The response unit provides an appropriate answer to the user's question using, for example, the generation AI. The generation AI generates an answer using, for example, a text generation AI. The answering unit can also use a generation AI to provide quick answers to user questions. The learning unit constantly reads the answer content provided by the answering unit as new data. The learning unit, for example, uses a generation AI to learn the answer content provided so that it can respond quickly to future inquiries. The generation AI, for example, learns the answer content using a text generation AI. The learning unit can also use a generation AI to constantly read the user's inquiry content as new data so that it can quickly answer similar questions. The switching unit has a human respond to unreasonable or complex inquiries. The switching unit, for example, uses a generation AI to detect unreasonable or complex inquiries and switches to a human responder during business hours. The generation AI, for example, uses a text generation AI to detect unreasonable or complex inquiries. The switching unit can also use a generation AI to detect unreasonable or complex inquiries and switch to a human responder at the appropriate time.This allows the sales digitalization system of the embodiment to efficiently accept, analyze, respond to, and learn from user inquiries, and switch to a person as needed.

[0030] The reception unit can analyze the user's past inquiry history and select a reception method. For example, the reception unit can automatically display inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest inquiry methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest an inquiry method to be used during a specific time period based on the user's past inquiry history. This makes it possible to provide an optimal reception method based on the user's past inquiry history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use data mining technology or machine learning algorithms to analyze the user's past inquiry history. This makes it possible to provide an optimal reception method based on the user's past inquiry history.

[0031] The reception unit may perform filtering based on the user's current situation and areas of interest when receiving an inquiry. For example, when the user inputs their current situation, the reception unit may preferentially display related inquiry content. The reception unit may also filter related inquiry content based on the user's areas of interest. Furthermore, the reception unit may also suggest an optimal inquiry method based on the user's current situation and areas of interest. This makes it possible to provide optimal inquiry content based on the user's current situation and areas of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may use information such as location information, device status, and time of day to identify the user's current situation. The reception unit may also use information such as past search history and social media activity to identify the user's areas of interest. This makes it possible to provide optimal inquiry content based on the user's current situation and areas of interest.

[0032] When receiving an inquiry, the reception unit can prioritize reception of inquiries that are highly relevant based on the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes reception of inquiries related to that area. The reception unit can also suggest an optimal inquiry method based on the user's geographical location information. Furthermore, if the user is moving, the reception unit can also suggest optimal inquiry content based on the user's current location. This makes it possible to provide optimal inquiry content based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use information such as GPS data or an IP address to obtain the user's geographical location information. This makes it possible to provide optimal inquiry content based on the user's geographical location information.

[0033] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. For example, the reception unit can prioritize reception of inquiries related to topics of interest from the user's social media activity. The reception unit can also analyze the user's social media activity and suggest an optimal inquiry method. Furthermore, the reception unit can filter related inquiry content based on the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can use text mining technology or machine learning algorithms to analyze the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity.

[0034] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry. For example, the analysis unit performs a detailed analysis for inquiries with high importance. The analysis unit can also perform a simplified analysis for inquiries with low importance. Furthermore, the analysis unit can set an analysis priority according to the importance. This makes it possible to provide an optimal analysis method depending on the importance of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as business impact and user position to evaluate the importance of the inquiry. This makes it possible to provide an optimal analysis method depending on the importance of the inquiry.

[0035] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the inquiry. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. The analysis unit can also apply a standard analysis algorithm to general inquiries. Furthermore, the analysis unit can also apply a specific analysis algorithm to inquiries related to customer support. This makes it possible to provide the optimal analysis algorithm depending on the category of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use text mining technology or machine learning algorithms to classify the category of the inquiry. This makes it possible to provide the optimal analysis algorithm depending on the category of the inquiry.

[0036] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the inquiry. For example, the analysis unit prioritizes analysis of recently submitted inquiries. The analysis unit can also analyze older inquiries with normal priority. Furthermore, the analysis unit can set the priority of analysis based on the time of submission. This makes it possible to provide the optimal analysis method depending on the time of submission of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as the elapsed time since submission or whether it is during or outside business hours to evaluate the time of submission of the inquiry. This makes it possible to provide the optimal analysis method depending on the time of submission of the inquiry.

[0037] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the query. For example, the analysis unit prioritizes analysis for highly relevant queries. The analysis unit can also analyze less relevant queries in a normal order. Furthermore, the analysis unit can set the order of analysis based on the relevance. This makes it possible to provide an optimal analysis method based on the relevance of the query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as similarity with past queries and related topics to evaluate the relevance of the query. This makes it possible to provide an optimal analysis method based on the relevance of the query.

[0038] When responding, the answering unit can adjust the level of detail of the answer based on the importance of the inquiry. For example, the answering unit provides a detailed answer to an inquiry of high importance. The answering unit can also provide a brief answer to an inquiry of low importance. Furthermore, the answering unit can set a priority order for the answers based on the importance. This makes it possible to provide an optimal answering method based on the importance of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as business impact and user position to evaluate the importance of the inquiry. This makes it possible to provide an optimal answering method based on the importance of the inquiry.

[0039] When responding, the answering unit can apply different answering algorithms depending on the category of the inquiry. For example, the answering unit can apply a specialized answering algorithm to technical inquiries. The answering unit can also apply a standard answering algorithm to general inquiries. Furthermore, the answering unit can apply a specific answering algorithm to inquiries regarding customer support. This makes it possible to provide the optimal answering algorithm depending on the category of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without using AI. For example, the answering unit can use text mining technology or a machine learning algorithm to classify the category of the inquiry. This makes it possible to provide the optimal answering algorithm depending on the category of the inquiry.

[0040] When responding, the answering unit can determine the priority of the answer based on the time of submission of the inquiry. For example, the answering unit can provide answers with priority to recently submitted inquiries. The answering unit can also provide answers with normal priority to older submitted inquiries. Furthermore, the answering unit can set the priority of the answer based on the time of submission. This makes it possible to provide the optimal answering method depending on the time of submission of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as the elapsed time since submission or whether it is during or outside business hours to evaluate the time of submission of the inquiry. This makes it possible to provide the optimal answering method depending on the time of submission of the inquiry.

[0041] When answering, the answering unit can adjust the order of answers based on the relevance of the inquiry. For example, the answering unit can provide answers preferentially to highly relevant inquiries. Furthermore, the answering unit can also provide answers in a normal order to less relevant inquiries. Furthermore, the answering unit can set the order of answers based on the relevance. This makes it possible to provide an optimal answering method based on the relevance of the inquiry. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as similarity to past inquiries and related topics to evaluate the relevance of the inquiry. This makes it possible to provide an optimal answering method based on the relevance of the inquiry.

[0042] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. Furthermore, the learning unit can improve learning efficiency by referring to past learning data. As a result, the learning algorithm is optimized based on past learning data, thereby improving learning efficiency. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use data mining technology or machine learning algorithms to refer to past learning data. As a result, the learning algorithm can be optimized based on past learning data.

[0043] During learning, the learning unit can apply different learning methods to different inquiry categories. For example, the learning unit can apply a specialized learning method to technical inquiries. The learning unit can also apply a standard learning method to general inquiries. Furthermore, the learning unit can also apply a specific learning method to inquiries related to customer support. This makes it possible to provide an optimal learning method depending on the inquiry category. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use text mining technology or a machine learning algorithm to classify inquiry categories. This makes it possible to provide an optimal learning method depending on the inquiry category.

[0044] During learning, the learning unit can weight the learning data based on the time of inquiry submission. For example, the learning unit sets a high weight for recent inquiry data during learning. The learning unit can also set a low weight for older inquiry data during learning. Furthermore, the learning unit can adjust the weighting of the learning data depending on the time of submission. This makes it possible to provide optimal weighting of the learning data depending on the time of inquiry submission. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use information such as the elapsed time since submission or whether the time is during or outside business hours to evaluate the time of inquiry submission. This makes it possible to provide optimal weighting of the learning data depending on the time of inquiry submission.

[0045] During learning, the learning unit can improve the accuracy of learning by referring to literature related to the query. For example, the learning unit refers to related literature to improve the accuracy of the learning data. The learning unit can also improve the learning algorithm based on the related literature. Furthermore, the learning unit can also improve the efficiency of learning by referring to related literature. As a result, the accuracy of learning is improved by referring to related literature. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use information such as academic papers and technical reports to refer to related literature. As a result, the accuracy of learning can be improved by referring to related literature.

[0046] The switching unit can adjust the level of detail of the switching based on the complexity of the inquiry when switching. For example, for a complex inquiry, the switching unit provides detailed information and switches to a human. Also, for a simple inquiry, the switching unit can continue to respond using the generation AI. Furthermore, the switching unit can adjust the level of detail of the switching based on the complexity of the inquiry. This makes it possible to provide an optimal switching method based on the complexity of the inquiry. Some or all of the above-described processing in the switching unit may be performed using AI, for example, or may be performed without using AI. For example, the switching unit can use information such as technical difficulty and the amount of information required to evaluate the complexity of the inquiry. This makes it possible to provide an optimal switching method based on the complexity of the inquiry.

[0047] The switching unit can apply different switching algorithms depending on the category of the inquiry when switching. For example, the switching unit applies a specialized switching algorithm to technical inquiries. The switching unit can also apply a standard switching algorithm to general inquiries. Furthermore, the switching unit can also apply a specific switching algorithm to inquiries related to customer support. This makes it possible to provide an optimal switching algorithm depending on the category of the inquiry. Some or all of the above-described processing in the switching unit may be performed using AI, for example, or may be performed without using AI. For example, the switching unit can use text mining technology or a machine learning algorithm to classify the category of the inquiry. This makes it possible to provide an optimal switching algorithm depending on the category of the inquiry.

[0048] At the time of switching, the switching unit can determine a switching priority based on the time when the inquiry was submitted. For example, the switching unit prioritizes switching to a person for a recently submitted inquiry. The switching unit can also switch to a normal priority for an older inquiry. Furthermore, the switching unit can set a switching priority based on the time when the inquiry was submitted. This makes it possible to provide an optimal switching priority based on the time when the inquiry was submitted. Some or all of the above-described processing in the switching unit may be performed using, for example, AI, or may be performed without using AI. For example, the switching unit can use information such as the elapsed time since submission or whether the inquiry was submitted during business hours to evaluate the time when the inquiry was submitted. This makes it possible to provide an optimal switching priority based on the time when the inquiry was submitted.

[0049] The switching unit can adjust the switching order based on the relevance of the inquiry when switching. For example, the switching unit preferentially switches to a person for a highly relevant inquiry. The switching unit can also switch in the normal order for a less relevant inquiry. Furthermore, the switching unit can set the switching order based on the relevance. This makes it possible to provide an optimal switching order based on the relevance of the inquiry. Some or all of the above-described processing in the switching unit may be performed using, for example, AI, or may be performed without using AI. For example, the switching unit can use information such as similarity with past inquiries and related topics to evaluate the relevance of the inquiry. This makes it possible to provide an optimal switching order based on the relevance of the inquiry.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The reception unit can analyze the user's past purchase history and customize the method for receiving inquiries. For example, inquiries related to products the user has previously purchased can be displayed with priority. The reception unit can also automatically provide support information for products the user has previously purchased. Furthermore, the reception unit can also suggest related products and services based on the user's purchase history. This makes it possible to provide the optimal reception method based on the user's purchase history.

[0052] The answering unit can analyze the user's past feedback and improve the quality of the answer. For example, the answering unit can improve the content of the answer based on the user's past feedback. The answering unit can also adjust the format and expression of the answer based on the user's feedback. Furthermore, the answering unit can create a template that reflects the user's feedback and provide the answer quickly. This makes it possible to provide the optimal answering method based on the user's feedback.

[0053] The switching unit can analyze the user's past inquiry history and optimize the timing of switching. For example, if the user has made a complex inquiry in the past, it can quickly switch to a human. Also, if the user has made a simple inquiry in the past, it can continue to respond using the generation AI. Furthermore, it can also provide the optimal switching timing based on the user's past inquiry history. This makes it possible to provide the optimal switching method based on the user's past inquiry history.

[0054] The analysis unit can analyze the user's past inquiry history to improve the accuracy of the analysis. For example, it can quickly analyze similar inquiries based on the content of inquiries made by the user in the past. The analysis unit can also select the optimal analysis algorithm based on the user's past inquiry history. Furthermore, it can also improve the efficiency of the analysis by referring to the user's past inquiry history. This makes it possible to provide the optimal analysis method based on the user's past inquiry history.

[0055] The learning unit can analyze the user's past feedback and optimize the learning algorithm. For example, it selects learning data based on feedback provided by the user in the past. The learning unit can also improve the learning algorithm based on the user's feedback. Furthermore, it can create a learning template that reflects the user's feedback and perform learning efficiently. This makes it possible to provide the optimal learning method based on the user's feedback.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The reception department accepts user inquiries. User inquiries include product questions, service requests, and technical support requests. The reception department uses generative AI to accept user inquiries, understands the content of the inquiry using natural language processing technology, and responds appropriately. Step 2: The analysis unit analyzes the inquiry received by the reception unit. The analysis unit uses generation AI to analyze the inquiry and extract information to provide an appropriate answer. The analysis unit can use text generation AI and multimodal generation AI to analyze multiple modalities, such as images and audio, in addition to text. Step 3: The answering unit provides an appropriate answer based on the content analyzed by the analysis unit. The answering unit uses generation AI to provide an appropriate answer to the user's question, allowing for a quick response. Step 4: The learning unit constantly reads the answers provided by the answering unit as new data. The learning unit uses the generation AI to learn the answers provided, enabling it to respond quickly to future inquiries. Step 5: The switching unit uses generative AI to detect unreasonable or complex inquiries and switches them over to a human during business hours.

[0058] (Example 2) A sales digitalization system according to an embodiment of the present invention uses generative AI to resolve sales activities and resource shortages. This sales digitalization system accepts user inquiries and requests, and the generative AI provides appropriate answers, automating communication with the user. Furthermore, the generative AI constantly reads user inquiries as new data, enabling rapid responses to similar questions. This enables responses to user inquiries 24 hours a day, 365 days a year. For difficult or complex inquiries, a system is implemented in which humans respond during business hours. This system eliminates sales staff shortages and realizes efficient sales activities. Furthermore, smooth communication with users is expected to improve customer satisfaction. For example, a sales digitalization system includes a reception unit that accepts user inquiries. The reception unit accepts user inquiries and requests using generative AI. Next, the system includes an analysis unit that analyzes the inquiries accepted by the reception unit. The analysis unit uses generative AI to analyze the inquiries and extract information for providing appropriate answers. The system also includes an answering unit that provides appropriate answers based on the content analyzed by the analysis unit. The answering unit uses generative AI to provide appropriate answers to user questions. It is equipped with a learning unit that constantly reads the answer content provided by the answering unit as new data. The learning unit uses generation AI to learn the answer content provided, enabling it to respond quickly to future inquiries. It is equipped with a switching unit that switches impossible or complex inquiries to a human response. The switching unit uses generation AI to detect impossible or complex inquiries and switches to a human response during business hours. This allows the sales digitalization system to efficiently accept, analyze, respond to, and learn from user inquiries, and switch to a human as needed. This allows the sales digitalization system to eliminate sales staff shortages and realize efficient sales activities. In addition, smooth communication with users is expected to improve customer satisfaction.

[0059] A sales digitalization system according to an embodiment includes a reception unit, an analysis unit, a response unit, a learning unit, and a switching unit. The reception unit receives user inquiries. User inquiries include, but are not limited to, product-related questions, service requests, and technical support requests. The reception unit receives user inquiries using, for example, a generation AI. The generation AI understands the user's inquiry using natural language processing technology and responds appropriately. The analysis unit analyzes the inquiry received by the reception unit. The analysis unit analyzes the inquiry using, for example, the generation AI and extracts information for providing an appropriate answer. The generation AI analyzes the inquiry using, for example, a text generation AI (e.g., LLM). The analysis unit can also analyze multiple modalities, such as images and audio, in addition to text, using a multimodal generation AI. The response unit provides an appropriate answer based on the content analyzed by the analysis unit. The response unit provides an appropriate answer to the user's question using, for example, the generation AI. The generation AI generates an answer using, for example, a text generation AI. The answering unit can also use a generation AI to provide quick answers to user questions. The learning unit constantly reads the answer content provided by the answering unit as new data. The learning unit, for example, uses a generation AI to learn the answer content provided so that it can respond quickly to future inquiries. The generation AI, for example, learns the answer content using a text generation AI. The learning unit can also use a generation AI to constantly read the user's inquiry content as new data so that it can quickly answer similar questions. The switching unit has a human respond to unreasonable or complex inquiries. The switching unit, for example, uses a generation AI to detect unreasonable or complex inquiries and switches to a human responder during business hours. The generation AI, for example, uses a text generation AI to detect unreasonable or complex inquiries. The switching unit can also use a generation AI to detect unreasonable or complex inquiries and switch to a human responder at the appropriate time.This allows the sales digitalization system of the embodiment to efficiently accept, analyze, respond to, and learn from user inquiries, and switch to a person as needed.

[0060] The reception unit can estimate the user's emotions and adjust the inquiry reception method based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept inquiries. This allows the optimal reception method to be provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without AI. For example, the reception unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This allows the optimal reception method to be provided according to the user's emotions.

[0061] The reception unit can analyze the user's past inquiry history and select a reception method. For example, the reception unit can automatically display inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest inquiry methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest an inquiry method to be used during a specific time period based on the user's past inquiry history. This makes it possible to provide an optimal reception method based on the user's past inquiry history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use data mining technology or machine learning algorithms to analyze the user's past inquiry history. This makes it possible to provide an optimal reception method based on the user's past inquiry history.

[0062] The reception unit may perform filtering based on the user's current situation and areas of interest when receiving an inquiry. For example, when the user inputs their current situation, the reception unit may preferentially display related inquiry content. The reception unit may also filter related inquiry content based on the user's areas of interest. Furthermore, the reception unit may also suggest an optimal inquiry method based on the user's current situation and areas of interest. This makes it possible to provide optimal inquiry content based on the user's current situation and areas of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may use information such as location information, device status, and time of day to identify the user's current situation. The reception unit may also use information such as past search history and social media activity to identify the user's areas of interest. This makes it possible to provide optimal inquiry content based on the user's current situation and areas of interest.

[0063] The reception unit can estimate the user's emotions and determine the priority of inquiries to be received based on the estimated user emotions. For example, if the user is nervous, the reception unit can set a high priority to respond quickly. Furthermore, if the user is relaxed, the reception unit can also respond with normal priority. Furthermore, if the user is in a hurry, the reception unit can also respond with top priority. This allows the priority of inquiries to be determined according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without AI. For example, the reception unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This makes it possible to provide an optimal reception method according to the user's emotions.

[0064] When receiving an inquiry, the reception unit can prioritize reception of inquiries that are highly relevant based on the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes reception of inquiries related to that area. The reception unit can also suggest an optimal inquiry method based on the user's geographical location information. Furthermore, if the user is moving, the reception unit can also suggest optimal inquiry content based on the user's current location. This makes it possible to provide optimal inquiry content based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use information such as GPS data or an IP address to obtain the user's geographical location information. This makes it possible to provide optimal inquiry content based on the user's geographical location information.

[0065] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. For example, the reception unit can prioritize reception of inquiries related to topics of interest from the user's social media activity. The reception unit can also analyze the user's social media activity and suggest an optimal inquiry method. Furthermore, the reception unit can filter related inquiry content based on the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can use text mining technology or machine learning algorithms to analyze the user's social media activity. This makes it possible to provide optimal inquiry content based on the user's social media activity.

[0066] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. For example, the analysis unit can apply a simple analysis method when the user is nervous. The analysis unit can also apply a detailed analysis method when the user is relaxed. Furthermore, the analysis unit can also apply a method for quickly performing analysis when the user is in a hurry. This makes it possible to provide an optimal analysis method depending on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using AI, or can be performed without AI. For example, the analysis unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This makes it possible to provide an optimal analysis method depending on the user's emotions.

[0067] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry. For example, the analysis unit performs a detailed analysis for inquiries with high importance. The analysis unit can also perform a simplified analysis for inquiries with low importance. Furthermore, the analysis unit can set an analysis priority according to the importance. This makes it possible to provide an optimal analysis method depending on the importance of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as business impact and user position to evaluate the importance of the inquiry. This makes it possible to provide an optimal analysis method depending on the importance of the inquiry.

[0068] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the inquiry. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. The analysis unit can also apply a standard analysis algorithm to general inquiries. Furthermore, the analysis unit can also apply a specific analysis algorithm to inquiries related to customer support. This makes it possible to provide the optimal analysis algorithm depending on the category of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use text mining technology or machine learning algorithms to classify the category of the inquiry. This makes it possible to provide the optimal analysis algorithm depending on the category of the inquiry.

[0069] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user's emotions. For example, if the user is nervous, the analysis unit can set a high priority to perform analysis quickly. Furthermore, if the user is relaxed, the analysis unit can perform analysis at a normal priority. Furthermore, if the user is in a hurry, the analysis unit can perform analysis with the highest priority. This allows the analysis priority to be determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This allows the optimal analysis method to be provided according to the user's emotions.

[0070] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the inquiry. For example, the analysis unit prioritizes analysis of recently submitted inquiries. The analysis unit can also analyze older inquiries with normal priority. Furthermore, the analysis unit can set the priority of analysis based on the time of submission. This makes it possible to provide the optimal analysis method depending on the time of submission of the inquiry. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as the elapsed time since submission or whether it is during or outside business hours to evaluate the time of submission of the inquiry. This makes it possible to provide the optimal analysis method depending on the time of submission of the inquiry.

[0071] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the query. For example, the analysis unit prioritizes analysis for highly relevant queries. The analysis unit can also analyze less relevant queries in a normal order. Furthermore, the analysis unit can set the order of analysis based on the relevance. This makes it possible to provide an optimal analysis method based on the relevance of the query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use information such as similarity with past queries and related topics to evaluate the relevance of the query. This makes it possible to provide an optimal analysis method based on the relevance of the query.

[0072] The answering unit can estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. For example, if the user is nervous, the answering unit can provide a simple and easy-to-understand expression. Furthermore, if the user is relaxed, the answering unit can provide an expression that includes detailed information. Furthermore, if the user is in a hurry, the answering unit can provide a quick and concise expression. This allows the optimal answering method to be provided according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answering unit can be performed using AI, or can be performed without AI. For example, the answering unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This allows the optimal answering method to be provided according to the user's emotions.

[0073] When responding, the answering unit can adjust the level of detail of the answer based on the importance of the inquiry. For example, the answering unit provides a detailed answer to an inquiry of high importance. The answering unit can also provide a brief answer to an inquiry of low importance. Furthermore, the answering unit can set a priority order for the answers based on the importance. This makes it possible to provide an optimal answering method based on the importance of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as business impact and user position to evaluate the importance of the inquiry. This makes it possible to provide an optimal answering method based on the importance of the inquiry.

[0074] When responding, the answering unit can apply different answering algorithms depending on the category of the inquiry. For example, the answering unit can apply a specialized answering algorithm to technical inquiries. The answering unit can also apply a standard answering algorithm to general inquiries. Furthermore, the answering unit can apply a specific answering algorithm to inquiries regarding customer support. This makes it possible to provide the optimal answering algorithm depending on the category of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without using AI. For example, the answering unit can use text mining technology or a machine learning algorithm to classify the category of the inquiry. This makes it possible to provide the optimal answering algorithm depending on the category of the inquiry.

[0075] The answering unit can estimate the user's emotions and adjust the length of the answer based on the estimated user's emotions. For example, if the user is nervous, the answering unit can provide a short, to-the-point answer. Furthermore, if the user is relaxed, the answering unit can provide a longer answer with detailed explanations. Furthermore, if the user is in a hurry, the answering unit can provide a quick, concise answer. This allows the optimal length of the answer to be provided depending on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answering unit can be performed using, for example, AI, or without AI. For example, the answering unit can use technologies such as text analysis, speech analysis, and facial expression recognition to estimate the user's emotions. This allows the optimal answering method to be provided depending on the user's emotions.

[0076] When responding, the answering unit can determine the priority of the answer based on the time of submission of the inquiry. For example, the answering unit can provide answers with priority to recently submitted inquiries. The answering unit can also provide answers with normal priority to older submitted inquiries. Furthermore, the answering unit can set the priority of the answer based on the time of submission. This makes it possible to provide the optimal answering method depending on the time of submission of the inquiry. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as the elapsed time since submission or whether it is during or outside business hours to evaluate the time of submission of the inquiry. This makes it possible to provide the optimal answering method depending on the time of submission of the inquiry.

[0077] When answering, the answering unit can adjust the order of answers based on the relevance of the inquiry. For example, the answering unit can provide answers preferentially to highly relevant inquiries. Furthermore, the answering unit can also provide answers in a normal order to less relevant inquiries. Furthermore, the answering unit can set the order of answers based on the relevance. This makes it possible to provide an optimal answering method based on the relevance of the inquiry. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can use information such as similarity to past inquiries and related topics to evaluate the relevance of the inquiry. This makes it possible to provide an optimal answering method based on the relevance of the inquiry.

[0078] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is nervous, the learning unit prioritizes learning simple, easy-to-understand data. The learning unit can also learn detailed data if the user is relaxed. Furthermore, if the user is in a hurry, the learning unit can select data that can be quickly learned. This allows optimal training data to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can use technologies such as text analysis, speech analysis, and facial expression recognition to estimate the user's emotions. This allows optimal training data to be selected according to the user's emotions.

[0079] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. Furthermore, the learning unit can improve learning efficiency by referring to past learning data. As a result, the learning algorithm is optimized based on past learning data, thereby improving learning efficiency. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use data mining technology or machine learning algorithms to refer to past learning data. As a result, the learning algorithm can be optimized based on past learning data.

[0080] During learning, the learning unit can apply different learning methods to different inquiry categories. For example, the learning unit can apply a specialized learning method to technical inquiries. The learning unit can also apply a standard learning method to general inquiries. Furthermore, the learning unit can also apply a specific learning method to inquiries related to customer support. This makes it possible to provide an optimal learning method depending on the inquiry category. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use text mining technology or a machine learning algorithm to classify inquiry categories. This makes it possible to provide an optimal learning method depending on the inquiry category.

[0081] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated user emotions. For example, if the user is nervous, the learning unit can set the learning frequency low to reduce the burden. Furthermore, if the user is relaxed, the learning unit can set the learning frequency high to learn detailed data. Furthermore, if the user is in a hurry, the learning unit can adjust the frequency to allow for quick learning. This allows for an optimal learning frequency to be provided according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can use technologies such as text analysis, speech analysis, and facial expression recognition to estimate the user's emotions. This allows for an optimal learning frequency to be provided according to the user's emotions.

[0082] During learning, the learning unit can weight the learning data based on the time of inquiry submission. For example, the learning unit sets a high weight for recent inquiry data during learning. The learning unit can also set a low weight for older inquiry data during learning. Furthermore, the learning unit can adjust the weighting of the learning data depending on the time of submission. This makes it possible to provide optimal weighting of the learning data depending on the time of inquiry submission. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use information such as the elapsed time since submission or whether the time is during or outside business hours to evaluate the time of inquiry submission. This makes it possible to provide optimal weighting of the learning data depending on the time of inquiry submission.

[0083] During learning, the learning unit can improve the accuracy of learning by referring to literature related to the query. For example, the learning unit refers to related literature to improve the accuracy of the learning data. The learning unit can also improve the learning algorithm based on the related literature. Furthermore, the learning unit can also improve the efficiency of learning by referring to related literature. As a result, the accuracy of learning is improved by referring to related literature. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can use information such as academic papers and technical reports to refer to related literature. As a result, the accuracy of learning can be improved by referring to related literature.

[0084] The switching unit can estimate the user's emotions and adjust the timing of switching based on the estimated user emotions. For example, if the user is nervous, the switching unit can quickly switch to a human. Furthermore, if the user is relaxed, the switching unit can continue to use the generation AI. Furthermore, if the user is in a hurry, the switching unit can instantly switch to a human. This allows optimal switching timing to be provided according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the switching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the switching unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This allows optimal switching timing to be provided according to the user's emotions.

[0085] The switching unit can adjust the level of detail of the switching based on the complexity of the inquiry when switching. For example, for a complex inquiry, the switching unit provides detailed information and switches to a human. Also, for a simple inquiry, the switching unit can continue to respond using the generation AI. Furthermore, the switching unit can adjust the level of detail of the switching based on the complexity of the inquiry. This makes it possible to provide an optimal switching method based on the complexity of the inquiry. Some or all of the above-described processing in the switching unit may be performed using AI, for example, or may be performed without using AI. For example, the switching unit can use information such as technical difficulty and the amount of information required to evaluate the complexity of the inquiry. This makes it possible to provide an optimal switching method based on the complexity of the inquiry.

[0086] The switching unit can apply different switching algorithms depending on the category of the inquiry when switching. For example, the switching unit applies a specialized switching algorithm to technical inquiries. The switching unit can also apply a standard switching algorithm to general inquiries. Furthermore, the switching unit can also apply a specific switching algorithm to inquiries related to customer support. This makes it possible to provide an optimal switching algorithm depending on the category of the inquiry. Some or all of the above-described processing in the switching unit may be performed using AI, for example, or may be performed without using AI. For example, the switching unit can use text mining technology or a machine learning algorithm to classify the category of the inquiry. This makes it possible to provide an optimal switching algorithm depending on the category of the inquiry.

[0087] The switching unit can estimate the user's emotions and determine a switching priority based on the estimated user's emotions. For example, if the user is nervous, the switching unit sets a high priority to quickly switch to a person. The switching unit can also switch at a normal priority when the user is relaxed. Furthermore, if the user is in a hurry, the switching unit can also switch to a person with the highest priority. This makes it possible to provide an optimal switching priority according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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-described processing in the switching unit can be performed using AI, or can be performed without AI. For example, the switching unit can use technologies such as text analysis, voice analysis, and facial expression recognition to estimate the user's emotions. This makes it possible to provide an optimal switching priority according to the user's emotions.

[0088] At the time of switching, the switching unit can determine a switching priority based on the time when the inquiry was submitted. For example, the switching unit prioritizes switching to a person for a recently submitted inquiry. The switching unit can also switch to a normal priority for an older inquiry. Furthermore, the switching unit can set a switching priority based on the time when the inquiry was submitted. This makes it possible to provide an optimal switching priority based on the time when the inquiry was submitted. Some or all of the above-described processing in the switching unit may be performed using, for example, AI, or may be performed without using AI. For example, the switching unit can use information such as the elapsed time since submission or whether the inquiry was submitted during business hours to evaluate the time when the inquiry was submitted. This makes it possible to provide an optimal switching priority based on the time when the inquiry was submitted.

[0089] The switching unit can adjust the switching order based on the relevance of the inquiry when switching. For example, the switching unit preferentially switches to a person for a highly relevant inquiry. The switching unit can also switch in the normal order for a less relevant inquiry. Furthermore, the switching unit can set the switching order based on the relevance. This makes it possible to provide an optimal switching order based on the relevance of the inquiry. Some or all of the above-described processing in the switching unit may be performed using, for example, AI, or may be performed without using AI. For example, the switching unit can use information such as similarity with past inquiries and related topics to evaluate the relevance of the inquiry. This makes it possible to provide an optimal switching order based on the relevance of the inquiry. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, response unit, learning unit, and switching unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives inquiries from a user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the inquiry. The response unit is realized by the specific processing unit 290 of the data processing device 12 and provides an appropriate answer. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the content of the provided answer. The switching unit is realized by the control unit 46A of the smart device 14 and detects unreasonable or complex inquiries and switches to a human. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, analysis unit, response unit, learning unit, and switching unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives an inquiry from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the content of the inquiry. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides an appropriate answer. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the content of the provided answer. The switching unit is realized, for example, by the control unit 46A of the smart glasses 214 and detects unreasonable or complex inquiries and switches to a person. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, response unit, learning unit, and switching unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives an inquiry from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the content of the inquiry. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides an appropriate answer. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the content of the provided answer. The switching unit is realized, for example, by the control unit 46A of the headset type terminal 314 and detects unreasonable or complex inquiries and switches to a person. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, response unit, learning unit, and switching unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives an inquiry from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the content of the inquiry. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides an appropriate answer. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the content of the provided answer. The switching unit is realized, for example, by the control unit 46A of the robot 414 and detects unreasonable or complex inquiries and switches to a human.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The reception unit can analyze the user's past purchase history and customize the method for receiving inquiries. For example, inquiries related to products the user has previously purchased can be displayed with priority. The reception unit can also automatically provide support information for products the user has previously purchased. Furthermore, the reception unit can also suggest related products and services based on the user's purchase history. This makes it possible to provide the optimal reception method based on the user's purchase history.

[0092] The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated user emotions. For example, if the user feels anxious, a detailed analysis can be performed to provide a sense of security. If the user feels relaxed, a concise analysis can be performed. Furthermore, if the user is in a hurry, a method for performing a quick analysis can be applied. This makes it possible to provide the optimal analysis method according to the user's emotions.

[0093] The answering unit can analyze the user's past feedback and improve the quality of the answer. For example, the answering unit can improve the content of the answer based on the user's past feedback. The answering unit can also adjust the format and expression of the answer based on the user's feedback. Furthermore, the answering unit can create a template that reflects the user's feedback and provide the answer quickly. This makes it possible to provide the optimal answering method based on the user's feedback.

[0094] The learning unit can estimate the user's emotions and prioritize learning data based on the estimated user emotions. For example, if the user is nervous, simple and easy-to-understand data can be prioritized for learning. If the user is relaxed, detailed data can be learned. Furthermore, if the user is in a hurry, data that can be learned quickly can be selected. This makes it possible to select optimal learning data according to the user's emotions.

[0095] The switching unit can analyze the user's past inquiry history and optimize the timing of switching. For example, if the user has made a complex inquiry in the past, it can quickly switch to a human. Also, if the user has made a simple inquiry in the past, it can continue to respond using the generation AI. Furthermore, it can also provide the optimal switching timing based on the user's past inquiry history. This makes it possible to provide the optimal switching method based on the user's past inquiry history.

[0096] The reception unit can estimate the user's emotions and determine the priority of inquiries to be received based on the estimated user's emotions. For example, if the user is nervous, the priority can be set high to respond quickly. If the user is relaxed, the inquiry can be responded with normal priority. Furthermore, if the user is in a hurry, the inquiry can be responded with top priority. In this way, the priority of inquiries can be determined according to the user's emotions.

[0097] The analysis unit can analyze the user's past inquiry history to improve the accuracy of the analysis. For example, it can quickly analyze similar inquiries based on the content of inquiries made by the user in the past. The analysis unit can also select the optimal analysis algorithm based on the user's past inquiry history. Furthermore, it can also improve the efficiency of the analysis by referring to the user's past inquiry history. This makes it possible to provide the optimal analysis method based on the user's past inquiry history.

[0098] The answering unit can estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. For example, if the user is nervous, a simple and easy-to-understand expression can be provided. If the user is relaxed, an expression including detailed information can be provided. Furthermore, if the user is in a hurry, a quick and concise expression can be provided. This makes it possible to provide the optimal answering method according to the user's emotions.

[0099] The learning unit can analyze the user's past feedback and optimize the learning algorithm. For example, it selects learning data based on feedback provided by the user in the past. The learning unit can also improve the learning algorithm based on the user's feedback. Furthermore, it can create a learning template that reflects the user's feedback and perform learning efficiently. This makes it possible to provide the optimal learning method based on the user's feedback.

[0100] The switching unit can estimate the user's emotions and determine the priority of switching based on the estimated user's emotions. For example, if the user is nervous, the priority can be set high to quickly switch to a person. If the user is relaxed, the switching can be performed with normal priority. Furthermore, if the user is in a hurry, the switching can be performed with the highest priority. This makes it possible to provide optimal switching priority according to the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The reception department accepts user inquiries. User inquiries include product questions, service requests, and technical support requests. The reception department uses generative AI to accept user inquiries, understands the content of the inquiry using natural language processing technology, and responds appropriately. Step 2: The analysis unit analyzes the inquiry received by the reception unit. The analysis unit uses generation AI to analyze the inquiry and extract information to provide an appropriate answer. The analysis unit can use text generation AI and multimodal generation AI to analyze multiple modalities, such as images and audio, in addition to text. Step 3: The answering unit provides an appropriate answer based on the content analyzed by the analysis unit. The answering unit uses generation AI to provide an appropriate answer to the user's question, allowing for a quick response. Step 4: The learning unit constantly reads the answers provided by the answering unit as new data. The learning unit uses the generation AI to learn the answers provided, enabling it to respond quickly to future inquiries. Step 5: The switching unit uses generative AI to detect unreasonable or complex inquiries and switches them over to a human during business hours.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

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

[0142] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0146] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0147] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0157] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0158] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0159] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0160] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0161] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0162] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0163] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0164] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0165] 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.

[0166] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0167] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0168] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0169] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0170] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0171] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0172] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0173] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives user inquiries; an analysis unit that analyzes the inquiry content received by the reception unit; a response unit that provides a response based on the content analyzed by the analysis unit; a learning unit that constantly reads the answer content provided by the answering unit as new data; A switching unit that allows a person to respond to unreasonable or complicated inquiries. A system characterized by:

2. The reception unit Estimate user emotions and adjust the way inquiries are received based on the estimated user emotions The system of claim 1 .

3. The reception unit Analyze the user's past inquiry history and select the reception method The system of claim 1 .

4. The reception unit Filtering inquiries based on the user's current situation and interests The system of claim 1 .

5. The reception unit Estimate the user's emotions and prioritize inquiries based on the estimated user emotions. The system of claim 1 .

6. The reception unit When accepting inquiries, prioritize relevant inquiries based on the user's geographic location. The system of claim 1 .

7. The reception unit When receiving an inquiry, analyze the user's social media activity and receive related inquiries The system of claim 1 .

8. The analysis unit Estimate the user's emotions and adjust the analysis method based on the estimated user emotions. The system of claim 1 .

Images