System

Abstract

To provide a system that improves efficiency of handling inquiry emails.SOLUTION: A system according to an embodiment comprises: a reception unit; a generation unit; and a return unit. The reception unit receives inquiry emails. The generation unit analyzes the inquiry emails received by the reception unit and generates responses on the basis of past inquiry-response histories and the latest information. The return unit returns the responses generated by the generation unit to sales representatives.SELECTED DRAWING: Figure 1

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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, responding to inquiry emails required a lot of man-hours, making it difficult to respond efficiently.

[0005] The system according to the embodiment aims to improve the efficiency of responding to inquiry emails. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, and a return unit. The reception unit receives an inquiry email. The generation unit analyzes the inquiry email received by the reception unit and generates a response based on past inquiry response history and the latest information. The return unit returns the response generated by the generation unit to the sales representative. Effect of the Invention

[0007] The system according to the embodiment can improve the efficiency of responses to inquiry emails. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The inquiry response system according to the embodiment of the present invention is a system that uses a generation AI with past inquiry response history as source data for closed use within a company. This inquiry response system first transfers an inquiry email from a customer to the system. Next, the generation AI generates an appropriate response based on the past inquiry response history. This response is automatically returned to the sales representative. This mechanism significantly reduces the man-hours required for sales inquiry response work. For example, an inquiry email such as "Please tell me the inventory status of the product" is transferred. This email is input to the generation AI. Next, the generation AI analyzes the input inquiry email. The generation AI generates an appropriate response based on the past inquiry response history. For example, a response such as "Currently, the product is in stock. We look forward to your order" is generated. The generated response is automatically returned to the sales representative. This eliminates the need for the sales representative to manually create a response, improving work efficiency. This mechanism significantly reduces the man-hours required for sales inquiry response work. The sales representative can focus on more important tasks. In addition, quick responses are possible, and customer satisfaction is improved. This enables the inquiry response system to significantly reduce the amount of work required for sales inquiries.

[0029] The inquiry response system according to the embodiment includes a reception unit, a generation unit, and a return unit. The reception unit receives an inquiry email. The inquiry email may be in text format or may have an attachment, but is not limited to such examples. The reception unit may receive the inquiry email through a mail server, for example. The reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. The generation unit may use a generation AI to analyze the inquiry email received by the reception unit and generate an answer based on past inquiry answer history and the latest information. The generation AI may be implemented using, for example, a machine learning algorithm or training data. The generation unit may use the generation AI to analyze past inquiry answer history and generate an appropriate answer. For example, the generation AI may generate an optimal answer to the inquiry content based on past inquiry answer history. The generation unit may also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. The return unit returns the answer generated by the generation unit to the sales representative. The reply unit can automatically reply the generated reply by using, for example, the settings of a mail server or an automatic reply system. As a result, the inquiry response system according to the embodiment automates the process from receipt of an inquiry email to generating and returning a reply, thereby reducing the man-hours required for sales inquiry response work.

[0030] The reception unit receives an inquiry email. The inquiry email may be in text format, have an attachment, or the like, but is not limited to such examples. The reception unit may receive the inquiry email through, for example, a mail server. Specifically, the mail server receives the inquiry email from the user using a protocol such as IMAP or POP3, and stores the email in a database. Furthermore, the reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. Natural language processing technology is used to understand the context of the email body and extract important information. For example, morphological analysis is used to divide the email body into words and identify the part of speech of each word. Keyword extraction technology extracts important keywords related to the inquiry content and uses them for subsequent processing. This allows the reception unit to efficiently analyze the content of the inquiry email and appropriately format it as input data to the generation unit. Furthermore, the reception unit may use spam filtering technology to exclude unnecessary emails and improve the efficiency of the system. For example, Bayesian filtering or a blacklist is used to automatically detect spam emails and exclude them from processing. This enables the reception unit to quickly and accurately carry out the process from reception of an inquiry email to content analysis, thereby improving the efficiency of the entire system.

[0031] The generation unit uses the generation AI to analyze the inquiry email received by the reception unit, and generates an answer based on the past inquiry response history and the latest information. The generation AI is implemented, for example, using a machine learning algorithm and training data. Specifically, the generation AI makes full use of natural language processing technology to understand the contents of the inquiry email and generate an appropriate answer. For example, the generation AI uses a transformer model to analyze the context of the email body and generate an optimal answer. The past inquiry response history is stored in a database, and the generation AI refers to this history to generate a new answer based on past answers to similar inquiries. Furthermore, the generation unit can also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. This allows the generation unit to quickly generate an optimal answer to the inquiry content and improve user satisfaction. In addition, the generation unit can regularly update the learning data of the generation AI and reflect the latest information, thereby always providing a highly accurate answer. For example, new product information and the latest FAQs are added to the training data to improve the accuracy of the generation AI. This enables the generation unit to always provide highly accurate answers based on the latest information, improving the efficiency and quality of inquiry responses.

[0032] The return unit returns the answer generated by the generation unit to the sales representative. The return unit can automatically return the generated answer, for example, by using the settings of a mail server or an automatic reply system. Specifically, the return unit sends the generated answer email using the SMTP protocol and delivers it to the mailbox of the sales representative. The automatic reply system sends the answer email at an appropriate time based on pre-set rules. For example, it can be set to send the answer email within a certain time after the inquiry email is received. Furthermore, the return unit can monitor the delivery status of the sent email and perform a resend process if a delivery error occurs. This allows the return unit to reliably deliver the generated answer to the sales representative. In addition, the return unit saves a log of the sent email so that it can be referenced later. This allows the history of the inquiry response to be managed and the past response content to be confirmed as necessary. Furthermore, the return unit can collect feedback from the sales representative and use it to improve the accuracy of the response of the generation unit. For example, the sales representative evaluates the content of the answer, and the evaluation result is reflected in the training data of the generation AI. This enables the reply section to promptly and reliably reply to the generated reply, thereby improving the efficiency and quality of inquiries handled.

[0033] The generation unit can analyze the past inquiry response history using the generation AI and generate an answer. The generation unit, for example, uses the generation AI to analyze the past inquiry response history. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can generate an appropriate answer based on the past inquiry response history using the generation AI. For example, the generation AI generates an optimal answer to the inquiry content based on the past inquiry response history. In this way, an appropriate answer can be generated by analyzing the past inquiry response history.

[0034] The generation unit can obtain the stock status using the generation AI and reflect it in the answer. The generation unit can obtain the latest stock status using, for example, the generation AI. The generation AI can obtain stock information in real time, for example, and reflect it in the answer. The generation unit can generate an appropriate answer based on the stock status using the generation AI. For example, the generation AI reflects in the answer whether there is stock based on the latest stock status. In this way, accurate information can be provided by obtaining the latest stock status and reflecting it in the answer.

[0035] The return unit can return the generated answer to the sales representative. The return unit, for example, automatically returns the generated answer. The return unit can return the generated answer to the sales representative, for example, by using a mail server setting or an automatic reply system. In this way, by automatically returning the generated answer, manual work by the sales representative can be reduced.

[0036] The reception unit can analyze past inquiry histories and group similar inquiries. The reception unit can use, for example, keyword matching or clustering algorithms to analyze the past inquiry histories. For example, the reception unit can automatically group inquiries about the same product. The reception unit can also automatically group inquiries about the same problem. Furthermore, the reception unit can automatically group inquiries from the same customer. This allows for efficient handling by grouping similar inquiries.

[0037] The reception unit can classify the inquiry email into categories based on the content of the inquiry email. The reception unit can use, for example, natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. For example, the reception unit classifies inquiries about products into a product category. The reception unit can also classify inquiries about services into a service category. Furthermore, the reception unit can classify inquiries about technical issues into a technical support category. This makes it possible to respond quickly by classifying the inquiry email into an appropriate category.

[0038] The reception unit can analyze sender information of the inquiry email and give priority to receiving emails with high reliability. The reception unit can use, for example, an IP address or an email address domain to analyze the sender information. For example, the reception unit gives priority to receiving inquiry emails from existing customers. The reception unit can also give priority to receiving emails from customers who have made highly reliable inquiries in the past. Furthermore, the reception unit can also give priority to receiving inquiry emails from corporate domains. As a result, important inquiries can be quickly processed by giving priority to receiving highly reliable emails.

[0039] The reception unit can translate the contents of the inquiry email into multiple languages ​​and can also handle international inquiries. The reception unit can use a translation algorithm, for example, to translate the contents of the inquiry email into multiple languages. For example, the reception unit automatically translates an inquiry email sent in English into Japanese. The reception unit can also automatically translate an inquiry email sent in Chinese into Japanese. Furthermore, the reception unit can also automatically translate an inquiry email sent in Spanish into Japanese. This makes it possible to handle global inquiries through multilingual support.

[0040] The generation unit can analyze the past inquiry response history and select an answer pattern. The generation unit can analyze the past inquiry response history using, for example, a generation AI. The generation AI is implemented using, for example, a machine learning algorithm and training data. The generation unit can use the generation AI to select the most appropriate answer pattern based on the past inquiry response history. For example, the generation AI can generate an optimal answer based on past answers about the same product. The generation AI can also generate an optimal answer based on past answers about the same problem. Furthermore, the generation AI can generate an optimal answer based on past answers from the same customer. This improves the accuracy of answers by generating an optimal answer based on past answer history.

[0041] The generation unit can acquire inventory status and product information in real time and reflect them in the answer. The generation unit acquires the latest inventory status and product information in real time, for example, using a generation AI. The generation AI is implemented, for example, using API integration and the update frequency of the database. The generation unit can generate an appropriate answer based on the inventory status and product information, using the generation AI. For example, the generation AI reflects in the answer whether there is inventory based on the latest inventory status. The generation AI can also reflect product details in the answer based on the latest product information. Furthermore, the generation AI can reflect the price in the answer based on the latest price information. This makes it possible to provide an accurate answer by reflecting the latest information.

[0042] The generation unit can attach related FAQs and support documents based on the inquiry content. The generation unit can analyze the inquiry content using, for example, a generation AI. The generation AI is implemented using, for example, keyword matching and relevance scores. The generation unit can automatically attach related FAQs and support documents based on the inquiry content using the generation AI. For example, the generation AI automatically attaches related FAQs to an inquiry about a product. The generation AI can also automatically attach related support documents to an inquiry about a service. Furthermore, the generation AI can automatically attach related manuals to an inquiry about a technical problem. This makes it possible to quickly resolve a user's questions by automatically attaching related documents.

[0043] The generation unit can evaluate the reliability of the answer based on the past inquiry response history and generate highly reliable answers preferentially. The generation unit, for example, uses a generation AI to analyze the past inquiry response history. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can evaluate the reliability of the answer based on the past inquiry response history and generate highly reliable answers preferentially using the generation AI. For example, the generation AI preferentially generates answer patterns that have been highly evaluated in the past. The generation AI can also preferentially generate answer patterns that have not caused any problems in the past. Furthermore, the generation AI can also preferentially generate answer patterns that have solved a similar problem in the past. This increases user satisfaction by preferentially generating highly reliable answers.

[0044] The return unit can evaluate the generated answer and make corrections as necessary. The return unit can automatically evaluate the quality of the generated answer using, for example, a generation AI. The generation AI can, for example, check grammar and spelling mistakes, evaluate the appropriateness of the content, and evaluate the appropriateness of the tone and expression. The return unit can evaluate the quality of the generated answer using the generation AI and make corrections as necessary. For example, the generation AI automatically checks the grammar and spelling mistakes of the answer and corrects them. The generation AI can also automatically evaluate whether the content of the answer is appropriate and correct them as necessary. Furthermore, the generation AI can automatically evaluate whether the tone and expression of the answer are appropriate and correct them as necessary. In this way, an accurate answer can be provided by automatically evaluating the quality of the answer and correcting it.

[0045] When returning the response, the return unit can transmit the response at the optimal timing, taking into account the schedule of the sales representative. For example, the return unit can perform adjustments based on calendar integration or priority in order to take into account the schedule of the sales representative. For example, the return unit transmits the response avoiding the time period when the sales representative is busy. The return unit can also transmit the response during the time period when the sales representative is available. Furthermore, the return unit can transmit the response at the optimal timing, in accordance with the schedule of the sales representative. This allows for efficient response by taking into account the schedule of the sales representative.

[0046] When returning the answer, the return unit can refer to the sales representative's past response history and transmit the answer in the optimal format. The return unit can use a database or a log file, for example, to refer to the sales representative's past response history. For example, the return unit can transmit the answer in the optimal format based on a format that the sales representative has used in the past. The return unit can also transmit the answer in the optimal format based on a format that the sales representative has received high marks for in the past. Furthermore, the return unit can transmit the answer in the optimal format based on a format that the sales representative has used without any problems in the past. In this way, the return unit can transmit the answer in the optimal format by referring to the past response history.

[0047] When returning, the return unit can distribute the destinations of the response to multiple personnel, thereby improving the efficiency of the response. The return unit can distribute the destinations of the response by using, for example, a load balancing algorithm or the skill set of the personnel. For example, the return unit can distribute and send the response to multiple sales personnel, thereby improving the efficiency of the response. The return unit can also distribute and send the response to multiple departments, thereby improving the efficiency of the response. Furthermore, the return unit can distribute and send the response to multiple personnel, thereby improving the speed of the response. In this way, by distributing the destinations of the response, the efficiency of the response can be improved.

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

[0049] The reception unit can automatically determine the urgency of the inquiry based on the contents of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the urgency from the contents of the inquiry email. If the urgency is high, the inquiry is classified as one that requires an immediate response. If the urgency is medium, the inquiry is processed with normal priority. Furthermore, if the urgency is low, the inquiry can be postponed. This makes it possible to respond appropriately according to the urgency of the inquiry.

[0050] The generating unit can automatically provide a usage method or troubleshooting guide for a related product based on the inquiry content. For example, the generating unit can analyze the inquiry content and generate a guide including a usage method for a related product. The generating unit can also provide a troubleshooting guide based on the inquiry content. Furthermore, the generating unit can provide a video tutorial related to the inquiry content. This allows the user to quickly obtain information for solving the problem.

[0051] The replying unit can collect user feedback on the generated answer and reflect it in the next answer generation. For example, the replying unit attaches a feedback form to the answer email and collects evaluations from users. The replying unit can also analyze the user feedback and use it as training data for the generation AI. Furthermore, the replying unit can identify improvements to improve the quality of the answer based on the feedback. This makes it possible to utilize the user feedback to provide a more appropriate answer.

[0052] The reception unit can analyze the geographical information of the sender of the inquiry email and respond to problems specific to each region. For example, the reception unit can identify the region of the sender by using the domain information of the IP address or email address. The reception unit can also generate an appropriate answer based on the problems and needs specific to each region. Furthermore, the reception unit can provide an answer that takes into consideration the language and culture of each region. This can improve user satisfaction by responding to problems specific to each region.

[0053] The reception unit can automatically classify the category of the inquiry based on the content of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the content of the inquiry email and identify the category. An inquiry about a product is classified into a product category, and an inquiry about a service is classified into a service category. In addition, an inquiry about a technical problem can be classified into a technical support category. In this way, by classifying the inquiry email into an appropriate category, a quick response can be made.

[0054] The reception unit can automatically set the priority of an inquiry based on the contents of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the contents of the inquiry email and identify the priority. If the level of urgency is high, it is processed with the highest priority. If the level of urgency is medium, it is processed with normal priority. Furthermore, if the level of urgency is low, it can be postponed. This makes it possible to respond appropriately according to the priority of the inquiry.

[0055] The process flow of the first embodiment will be briefly described below.

[0056] Step 1: The reception unit receives an inquiry email. The inquiry email may be in text format, have an attachment, or the like, but is not limited to these examples. The reception unit may receive the inquiry email through a mail server, for example. The reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. Step 2: The generation unit uses the generation AI to analyze the inquiry email received by the reception unit, and generates an answer based on past inquiry response history and the latest information. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can use the generation AI to analyze past inquiry response history and generate an appropriate answer. For example, the generation AI generates an optimal answer to the inquiry content based on the past inquiry response history. The generation unit can also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. Step 3: The return unit returns the answer generated by the generation unit to the sales representative. The return unit can automatically return the generated answer by using, for example, a mail server setting or an automatic reply system.

[0057] (Example 2) The inquiry response system according to the embodiment of the present invention is a system that uses a generation AI with past inquiry response history as source data for closed use within a company. This inquiry response system first transfers an inquiry email from a customer to the system. Next, the generation AI generates an appropriate response based on the past inquiry response history. This response is automatically returned to the sales representative. This mechanism significantly reduces the man-hours required for sales inquiry response work. For example, an inquiry email such as "Please tell me the inventory status of the product" is transferred. This email is input to the generation AI. Next, the generation AI analyzes the input inquiry email. The generation AI generates an appropriate response based on the past inquiry response history. For example, a response such as "Currently, the product is in stock. We look forward to your order" is generated. The generated response is automatically returned to the sales representative. This eliminates the need for the sales representative to manually create a response, improving work efficiency. This mechanism significantly reduces the man-hours required for sales inquiry response work. The sales representative can focus on more important tasks. In addition, quick responses are possible, and customer satisfaction is improved. This enables the inquiry response system to significantly reduce the amount of work required for sales inquiries.

[0058] The inquiry response system according to the embodiment includes a reception unit, a generation unit, and a return unit. The reception unit receives an inquiry email. The inquiry email may be in text format or may have an attachment, but is not limited to such examples. The reception unit may receive the inquiry email through a mail server, for example. The reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. The generation unit may use a generation AI to analyze the inquiry email received by the reception unit and generate an answer based on past inquiry answer history and the latest information. The generation AI may be implemented using, for example, a machine learning algorithm or training data. The generation unit may use the generation AI to analyze past inquiry answer history and generate an appropriate answer. For example, the generation AI may generate an optimal answer to the inquiry content based on past inquiry answer history. The generation unit may also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. The return unit returns the answer generated by the generation unit to the sales representative. The reply unit can automatically reply the generated reply by using, for example, the settings of a mail server or an automatic reply system. As a result, the inquiry response system according to the embodiment automates the process from receipt of an inquiry email to generating and returning a reply, thereby reducing the man-hours required for sales inquiry response work.

[0059] The reception unit receives an inquiry email. The inquiry email may be in text format, have an attachment, or the like, but is not limited to such examples. The reception unit may receive the inquiry email through, for example, a mail server. Specifically, the mail server receives the inquiry email from the user using a protocol such as IMAP or POP3, and stores the email in a database. Furthermore, the reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. Natural language processing technology is used to understand the context of the email body and extract important information. For example, morphological analysis is used to divide the email body into words and identify the part of speech of each word. Keyword extraction technology extracts important keywords related to the inquiry content and uses them for subsequent processing. This allows the reception unit to efficiently analyze the content of the inquiry email and appropriately format it as input data to the generation unit. Furthermore, the reception unit may use spam filtering technology to exclude unnecessary emails and improve the efficiency of the system. For example, Bayesian filtering or a blacklist is used to automatically detect spam emails and exclude them from processing. This enables the reception unit to quickly and accurately carry out the process from reception of an inquiry email to content analysis, thereby improving the efficiency of the entire system.

[0060] The generation unit uses the generation AI to analyze the inquiry email received by the reception unit, and generates an answer based on the past inquiry response history and the latest information. The generation AI is implemented, for example, using a machine learning algorithm and training data. Specifically, the generation AI makes full use of natural language processing technology to understand the contents of the inquiry email and generate an appropriate answer. For example, the generation AI uses a transformer model to analyze the context of the email body and generate an optimal answer. The past inquiry response history is stored in a database, and the generation AI refers to this history to generate a new answer based on past answers to similar inquiries. Furthermore, the generation unit can also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. This allows the generation unit to quickly generate an optimal answer to the inquiry content and improve user satisfaction. In addition, the generation unit can regularly update the learning data of the generation AI and reflect the latest information, thereby always providing a highly accurate answer. For example, new product information and the latest FAQs are added to the training data to improve the accuracy of the generation AI. This enables the generation unit to always provide highly accurate answers based on the latest information, improving the efficiency and quality of inquiry responses.

[0061] The return unit returns the answer generated by the generation unit to the sales representative. The return unit can automatically return the generated answer, for example, by using the settings of a mail server or an automatic reply system. Specifically, the return unit sends the generated answer email using the SMTP protocol and delivers it to the mailbox of the sales representative. The automatic reply system sends the answer email at an appropriate time based on pre-set rules. For example, it can be set to send the answer email within a certain time after the inquiry email is received. Furthermore, the return unit can monitor the delivery status of the sent email and perform a resend process if a delivery error occurs. This allows the return unit to reliably deliver the generated answer to the sales representative. In addition, the return unit saves a log of the sent email so that it can be referenced later. This allows the history of the inquiry response to be managed and the past response content to be confirmed as necessary. Furthermore, the return unit can collect feedback from the sales representative and use it to improve the accuracy of the response of the generation unit. For example, the sales representative evaluates the content of the answer, and the evaluation result is reflected in the training data of the generation AI. This enables the reply section to promptly and reliably reply to the generated reply, thereby improving the efficiency and quality of inquiries handled.

[0062] The generation unit can analyze the past inquiry response history using the generation AI and generate an answer. The generation unit, for example, uses the generation AI to analyze the past inquiry response history. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can generate an appropriate answer based on the past inquiry response history using the generation AI. For example, the generation AI generates an optimal answer to the inquiry content based on the past inquiry response history. In this way, an appropriate answer can be generated by analyzing the past inquiry response history.

[0063] The generation unit can obtain the stock status using the generation AI and reflect it in the answer. The generation unit can obtain the latest stock status using, for example, the generation AI. The generation AI can obtain stock information in real time, for example, and reflect it in the answer. The generation unit can generate an appropriate answer based on the stock status using the generation AI. For example, the generation AI reflects in the answer whether there is stock based on the latest stock status. In this way, accurate information can be provided by obtaining the latest stock status and reflecting it in the answer.

[0064] The return unit can return the generated answer to the sales representative. The return unit, for example, automatically returns the generated answer. The return unit can return the generated answer to the sales representative, for example, by using a mail server setting or an automatic reply system. In this way, by automatically returning the generated answer, manual work by the sales representative can be reduced.

[0065] The reception unit can estimate the user's emotion and set the priority of the inquiry email based on the estimated user's emotion. The reception unit can use, for example, an emotion analysis algorithm or a text mining technique to estimate the user's emotion. For example, when the user feels dissatisfied, the reception unit processes the inquiry email with the highest priority. Also, when the user feels urgency, the reception unit can process the inquiry email with high priority. Furthermore, when the user is relaxed, the reception unit can process the inquiry email with normal priority. In this way, by determining the priority of the inquiry email based on the user's emotion, important inquiries can be processed with priority. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0066] The reception unit can analyze past inquiry histories and group similar inquiries. The reception unit can use, for example, keyword matching or clustering algorithms to analyze the past inquiry histories. For example, the reception unit can automatically group inquiries about the same product. The reception unit can also automatically group inquiries about the same problem. Furthermore, the reception unit can automatically group inquiries from the same customer. This allows for efficient handling by grouping similar inquiries.

[0067] The reception unit can classify the inquiry email into categories based on the content of the inquiry email. The reception unit can use, for example, natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. For example, the reception unit classifies inquiries about products into a product category. The reception unit can also classify inquiries about services into a service category. Furthermore, the reception unit can classify inquiries about technical issues into a technical support category. This makes it possible to respond quickly by classifying the inquiry email into an appropriate category.

[0068] The reception unit can estimate the user's emotion and adjust the reception time of the inquiry email based on the estimated user's emotion. The reception unit can use, for example, an emotion analysis algorithm or a text mining technique to estimate the user's emotion. For example, the reception unit immediately receives the inquiry email when the user feels dissatisfied. Also, the reception unit can quickly receive the inquiry email when the user feels urgency. Furthermore, the reception unit can also receive the inquiry email at a normal timing when the user is relaxed. In this way, by adjusting the reception timing based on the user's emotion, the inquiry can be received at an appropriate timing. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0069] The reception unit can analyze sender information of the inquiry email and give priority to receiving emails with high reliability. The reception unit can use, for example, an IP address or an email address domain to analyze the sender information. For example, the reception unit gives priority to receiving inquiry emails from existing customers. The reception unit can also give priority to receiving emails from customers who have made highly reliable inquiries in the past. Furthermore, the reception unit can also give priority to receiving inquiry emails from corporate domains. As a result, important inquiries can be quickly processed by giving priority to receiving highly reliable emails.

[0070] The reception unit can translate the contents of the inquiry email into multiple languages ​​and can also handle international inquiries. The reception unit can use a translation algorithm, for example, to translate the contents of the inquiry email into multiple languages. For example, the reception unit automatically translates an inquiry email sent in English into Japanese. The reception unit can also automatically translate an inquiry email sent in Chinese into Japanese. Furthermore, the reception unit can also automatically translate an inquiry email sent in Spanish into Japanese. This makes it possible to handle global inquiries through multilingual support.

[0071] The generation unit can estimate the user's emotion and adjust the expression of the answer based on the estimated user's emotion. The generation unit can estimate the user's emotion using, for example, a generation AI. The generation AI can be implemented using, for example, an emotion analysis algorithm or a text mining technique. The generation unit can adjust the way of expressing the answer based on the user's emotion using the generation AI. For example, the generation AI uses polite and kind expressions when the user is dissatisfied. The generation AI can also use quick and concise expressions when the user feels urgency. Furthermore, the generation AI can also use normal expressions when the user is relaxed. This makes it possible to provide a more appropriate answer by adjusting the way of expressing the answer based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0072] The generation unit can analyze the past inquiry response history and select an answer pattern. The generation unit can analyze the past inquiry response history using, for example, a generation AI. The generation AI is implemented using, for example, a machine learning algorithm and training data. The generation unit can use the generation AI to select the most appropriate answer pattern based on the past inquiry response history. For example, the generation AI can generate an optimal answer based on past answers about the same product. The generation AI can also generate an optimal answer based on past answers about the same problem. Furthermore, the generation AI can generate an optimal answer based on past answers from the same customer. This improves the accuracy of answers by generating an optimal answer based on past answer history.

[0073] The generation unit can acquire inventory status and product information in real time and reflect them in the answer. The generation unit acquires the latest inventory status and product information in real time, for example, using a generation AI. The generation AI is implemented, for example, using API integration and the update frequency of the database. The generation unit can generate an appropriate answer based on the inventory status and product information, using the generation AI. For example, the generation AI reflects in the answer whether there is inventory based on the latest inventory status. The generation AI can also reflect product details in the answer based on the latest product information. Furthermore, the generation AI can reflect the price in the answer based on the latest price information. This makes it possible to provide an accurate answer by reflecting the latest information.

[0074] The generation unit can estimate the user's emotion and adjust the details of the answer based on the estimated user's emotion. The generation unit can estimate the user's emotion using, for example, a generation AI. The generation AI can be implemented using, for example, an emotion analysis algorithm or a text mining technique. The generation unit can adjust the level of detail of the answer based on the user's emotion using the generation AI. For example, the generation AI can provide a detailed answer when the user is dissatisfied. The generation AI can also provide a concise answer when the user is feeling urgency. Furthermore, the generation AI can also provide an answer with normal detail when the user is relaxed. This allows a more appropriate answer to be provided by adjusting the level of detail of the answer based on the user's emotion. The emotion estimation is realized using, for example, an emotion engine or a generation AI using an emotion estimation function. The generation AI can be, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0075] The generation unit can attach related FAQs and support documents based on the inquiry content. The generation unit can analyze the inquiry content using, for example, a generation AI. The generation AI is implemented using, for example, keyword matching and relevance scores. The generation unit can automatically attach related FAQs and support documents based on the inquiry content using the generation AI. For example, the generation AI automatically attaches related FAQs to an inquiry about a product. The generation AI can also automatically attach related support documents to an inquiry about a service. Furthermore, the generation AI can automatically attach related manuals to an inquiry about a technical problem. This makes it possible to quickly resolve a user's questions by automatically attaching related documents.

[0076] The generation unit can evaluate the reliability of the answer based on the past inquiry response history and generate highly reliable answers preferentially. The generation unit, for example, uses a generation AI to analyze the past inquiry response history. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can evaluate the reliability of the answer based on the past inquiry response history and generate highly reliable answers preferentially using the generation AI. For example, the generation AI preferentially generates answer patterns that have been highly evaluated in the past. The generation AI can also preferentially generate answer patterns that have not caused any problems in the past. Furthermore, the generation AI can also preferentially generate answer patterns that have solved a similar problem in the past. This increases user satisfaction by preferentially generating highly reliable answers.

[0077] The return unit can estimate the user's emotion and adjust the transmission time of the answer based on the estimated user's emotion. The return unit can estimate the user's emotion using, for example, a generation AI. The generation AI is implemented using, for example, an emotion analysis algorithm or a text mining technique. The return unit can adjust the transmission timing of the answer based on the user's emotion using the generation AI. For example, the generation AI immediately transmits the answer when the user is dissatisfied. The generation AI can also transmit the answer quickly when the user feels urgency. Furthermore, the generation AI can also transmit the answer at a normal timing when the user is relaxed. In this way, the answer can be transmitted at an appropriate timing by adjusting the transmission timing based on the user's emotion. The estimation of the emotion is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0078] The return unit can evaluate the generated answer and make corrections as necessary. The return unit can automatically evaluate the quality of the generated answer using, for example, a generation AI. The generation AI can, for example, check grammar and spelling mistakes, evaluate the appropriateness of the content, and evaluate the appropriateness of the tone and expression. The return unit can evaluate the quality of the generated answer using the generation AI and make corrections as necessary. For example, the generation AI automatically checks the grammar and spelling mistakes of the answer and corrects them. The generation AI can also automatically evaluate whether the content of the answer is appropriate and correct them as necessary. Furthermore, the generation AI can automatically evaluate whether the tone and expression of the answer are appropriate and correct them as necessary. In this way, an accurate answer can be provided by automatically evaluating the quality of the answer and correcting it.

[0079] When returning the response, the return unit can transmit the response at the optimal timing, taking into account the schedule of the sales representative. For example, the return unit can perform adjustments based on calendar integration or priority in order to take into account the schedule of the sales representative. For example, the return unit transmits the response avoiding the time period when the sales representative is busy. The return unit can also transmit the response during the time period when the sales representative is available. Furthermore, the return unit can transmit the response at the optimal timing, in accordance with the schedule of the sales representative. This allows for efficient response by taking into account the schedule of the sales representative.

[0080] The return unit can estimate the user's emotion and adjust the means of sending the answer based on the estimated user's emotion. The return unit can estimate the user's emotion using, for example, a generation AI. The generation AI is implemented using, for example, an emotion analysis algorithm or a text mining technique. The return unit can adjust the method of sending the answer based on the user's emotion using the generation AI. For example, the generation AI sends the answer in a polite email format when the user is dissatisfied. The generation AI can also send the answer in a quick email format when the user is feeling urgency. Furthermore, the generation AI can also send the answer in a normal email format when the user is relaxed. This makes it possible to provide a more appropriate answer by adjusting the sending method based on the user's emotion. The estimation of emotion is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0081] When returning the answer, the return unit can refer to the sales representative's past response history and transmit the answer in the optimal format. The return unit can use a database or a log file, for example, to refer to the sales representative's past response history. For example, the return unit can transmit the answer in the optimal format based on a format that the sales representative has used in the past. The return unit can also transmit the answer in the optimal format based on a format that the sales representative has received high marks for in the past. Furthermore, the return unit can transmit the answer in the optimal format based on a format that the sales representative has used without any problems in the past. In this way, the return unit can transmit the answer in the optimal format by referring to the past response history.

[0082] When returning, the return unit can distribute the destinations of the response to multiple personnel, thereby improving the efficiency of the response. The return unit can distribute the destinations of the response by using, for example, a load balancing algorithm or the skill set of the personnel. For example, the return unit can distribute and send the response to multiple sales personnel, thereby improving the efficiency of the response. The return unit can also distribute and send the response to multiple departments, thereby improving the efficiency of the response. Furthermore, the return unit can distribute and send the response to multiple personnel, thereby improving the speed of the response. In this way, by distributing the destinations of the response, the efficiency of the response can be improved.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] The reception unit can automatically determine the urgency of the inquiry based on the contents of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the urgency from the contents of the inquiry email. If the urgency is high, the inquiry is classified as one that requires an immediate response. If the urgency is medium, the inquiry is processed with normal priority. Furthermore, if the urgency is low, the inquiry can be postponed. This makes it possible to respond appropriately according to the urgency of the inquiry.

[0085] The generating unit can automatically provide a usage method or troubleshooting guide for a related product based on the inquiry content. For example, the generating unit can analyze the inquiry content and generate a guide including a usage method for a related product. The generating unit can also provide a troubleshooting guide based on the inquiry content. Furthermore, the generating unit can provide a video tutorial related to the inquiry content. This allows the user to quickly obtain information for solving the problem.

[0086] The replying unit can collect user feedback on the generated answer and reflect it in the next answer generation. For example, the replying unit attaches a feedback form to the answer email and collects evaluations from users. The replying unit can also analyze the user feedback and use it as training data for the generation AI. Furthermore, the replying unit can identify improvements to improve the quality of the answer based on the feedback. This makes it possible to utilize the user feedback to provide a more appropriate answer.

[0087] The reception unit can analyze the geographical information of the sender of the inquiry email and respond to problems specific to each region. For example, the reception unit can identify the region of the sender by using the domain information of the IP address or email address. The reception unit can also generate an appropriate answer based on the problems and needs specific to each region. Furthermore, the reception unit can provide an answer that takes into consideration the language and culture of each region. This can improve user satisfaction by responding to problems specific to each region.

[0088] The generation unit can estimate the user's emotion and adjust the tone of the answer based on the estimated user's emotion. For example, the generation unit uses a polite and friendly tone when the user feels dissatisfied. The generation unit can also use a quick and concise tone when the user feels urgency. Furthermore, the generation unit can use a normal tone when the user is relaxed. This allows for more appropriate communication by adjusting the tone of the answer based on the user's emotion.

[0089] The reception unit can automatically classify the category of the inquiry based on the content of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the content of the inquiry email and identify the category. An inquiry about a product is classified into a product category, and an inquiry about a service is classified into a service category. In addition, an inquiry about a technical problem can be classified into a technical support category. In this way, by classifying the inquiry email into an appropriate category, a quick response can be made.

[0090] The generation unit can estimate the user's emotion and adjust the level of detail of the answer based on the estimated user's emotion. For example, the generation unit can provide a detailed answer when the user feels dissatisfied. The generation unit can also provide a concise answer when the user feels urgency. Furthermore, the generation unit can provide an answer with a normal level of detail when the user is relaxed. In this way, a more appropriate answer can be provided by adjusting the level of detail of the answer based on the user's emotion.

[0091] The reply unit can estimate the user's emotions regarding the generated answer and reflect them in the next answer generation. For example, the reply unit applies a sentiment analysis algorithm to the answer email to analyze the user's emotions. The reply unit can also use the user's emotions as training data for the generation AI based on the emotions. Furthermore, the reply unit can identify improvements to improve the quality of the answer based on the sentiment analysis. This makes it possible to provide a more appropriate answer by utilizing the user's emotions.

[0092] The reception unit can automatically set the priority of an inquiry based on the contents of the inquiry email. For example, the reception unit uses natural language processing technology to analyze the contents of the inquiry email and identify the priority. If the level of urgency is high, it is processed with the highest priority. If the level of urgency is medium, it is processed with normal priority. Furthermore, if the level of urgency is low, it can be postponed. This makes it possible to respond appropriately according to the priority of the inquiry.

[0093] The generation unit can estimate the user's emotions and adjust the expression of the answer based on the estimated user's emotions. For example, the generation unit uses polite and kind expressions when the user feels dissatisfied. The generation unit can also use quick and concise expressions when the user feels urgency. Furthermore, the generation unit can also use normal expressions when the user is relaxed. In this way, a more appropriate answer can be provided by adjusting the way the answer is expressed based on the user's emotions.

[0094] The process flow of the second embodiment will be briefly described below.

[0095] Step 1: The reception unit receives an inquiry email. The inquiry email may be in text format, have an attachment, or the like, but is not limited to these examples. The reception unit may receive the inquiry email through a mail server, for example. The reception unit may use natural language processing technology or keyword extraction technology to analyze the content of the inquiry email. Step 2: The generation unit uses the generation AI to analyze the inquiry email received by the reception unit, and generates an answer based on past inquiry response history and the latest information. The generation AI is implemented, for example, using a machine learning algorithm and training data. The generation unit can use the generation AI to analyze past inquiry response history and generate an appropriate answer. For example, the generation AI generates an optimal answer to the inquiry content based on the past inquiry response history. The generation unit can also use the generation AI to obtain the latest inventory status and product information and reflect it in the answer. For example, the generation AI obtains inventory information in real time and reflects it in the answer. Step 3: The return unit returns the answer generated by the generation unit to the sales representative. The return unit can automatically return the generated answer by using, for example, a mail server setting or an automatic reply system.

[0096] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0097] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0098] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0099] Each of the multiple elements including the above-mentioned reception unit, generation unit, and return 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 an inquiry email. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the inquiry email using a generation AI and generates a response based on the past inquiry response history. The return unit is realized, for example, by the control unit 46A of the smart device 14 and returns the generated response to the sales representative. In this way, the inquiry response system can automate the process from receipt of the inquiry email to generation and return of the response, thereby reducing the man-hours of the sales inquiry response work. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0100] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0101] 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.

[0102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0103] 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.

[0104] 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 the voice according to instructions from the processor 46.

[0105] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0106] 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 performed in a secure state.

[0107] Fig. 4 shows an example of 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.

[0108] 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.

[0109] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0110] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0111] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0112] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0113] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0114] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements including the above-mentioned reception unit, generation unit, and return 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 email. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the inquiry email using a generation AI and generates a response based on the past inquiry response history. The return unit is realized, for example, by the control unit 46A of the smart glasses 214 and returns the generated response to the sales representative. In this way, the inquiry response system can automate the process from receipt of the inquiry email to generation and return of the response, thereby reducing the man-hours of the sales inquiry response work. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0119] 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.

[0120] 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 the voice according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0122] 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 performed in a secure state.

[0123] 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.

[0124] 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.

[0125] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0126] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0127] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0128] 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 voice indicating a user input for 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.

[0129] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0130] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements including the above-mentioned reception unit, generation unit, and return 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 email. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the inquiry email using a generation AI and generates a response based on the past inquiry response history. The return unit is realized, for example, by the control unit 46A of the headset type terminal 314 and returns the generated response to the sales representative. In this way, the inquiry response system can automate the process from receipt of the inquiry email to generation and return of the response, thereby reducing the man-hours of the sales inquiry response work. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0135] 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.

[0136] 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 the voice according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0138] 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 performed in a secure state.

[0139] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0140] 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.

[0141] 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.

[0142] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0143] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 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.

[0144] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0145] 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 a voice indicating a user input for 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.

[0146] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0147] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0148] Each of the multiple elements including the above-mentioned reception unit, generation unit, and return 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 email. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the inquiry email using a generation AI and generates an answer based on the past inquiry answer history. The return unit is realized, for example, by the control unit 46A of the robot 414 and returns the generated answer to the sales representative. In this way, the inquiry response system can automate the process from receipt of the inquiry email to generation and return of the answer, thereby reducing the man-hours of the sales inquiry response work. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0149] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0150] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0152] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0153] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0154] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0156] 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.

[0157] 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 Universal Serial Bus (USB) 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.

[0158] In addition, 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 upon request from the data processing device 12.

[0159] 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.

[0160] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0161] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0162] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0163] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0165] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0167] (Appendix 1) A reception unit for receiving inquiry emails; a generation unit that analyzes the inquiry email received by the reception unit and generates an answer based on a history of past inquiry answers and the latest information; A system comprising: a return unit that returns the answer generated by the generation unit to a sales representative. (Appendix 2) The generation unit is Generative AI analyzes past inquiry response history and generates responses 2. The system of claim 1, (Appendix 3) The generation unit is Generative AI obtains stock status and reflects it in responses 2. The system of claim 1, (Appendix 4) The return unit includes: Send the generated response back to the sales rep 2. The system of claim 1, (Appendix 5) The reception unit is Infer user sentiment and prioritize inquiries based on the estimated user sentiment 2. The system of claim 1, (Appendix 6) The reception unit is Analyze past ticket history and group similar tickets 2. The system of claim 1, (Appendix 7) The reception unit is Categorize inquiries based on their content 2. The system of claim 1, (Appendix 8) The reception unit is Estimate user emotions and adjust the time for accepting inquiry emails based on the estimated user emotions 2. The system of claim 1, (Appendix 9) The reception unit is Analyze the sender information of inquiry emails and give priority to reliable emails. 2. The system of claim 1, (Appendix 10) The reception unit is Translate inquiry emails into multiple languages ​​to respond to international inquiries 2. The system of claim 1, (Appendix 11) The generation unit is Infer the user's emotions and adjust the wording of the answer based on the estimated user's emotions 2. The system of claim 1, (Appendix 12) The generation unit is Analyze past inquiry response history and select response patterns 2. The system of claim 1, (Appendix 13) The generation unit is Obtain inventory status and product information in real time and reflect it in responses 2. The system of claim 1, (Appendix 14) The generation unit is Infer user sentiment and adjust answer details based on the inferred user sentiment 2. The system of claim 1, (Appendix 15) The generation unit is Attach any relevant FAQs or support documents based on the inquiry 2. The system of claim 1, (Appendix 16) The generation unit is Based on past inquiry response history, the reliability of responses is evaluated and reliable responses are generated preferentially. 2. The system of claim 1, (Appendix 17) The return unit includes: Inferring user emotion and adjusting the time to send a response based on the estimated user emotion 2. The system of claim 1, (Appendix 18) The return unit includes: Evaluate the generated answers and make revisions if necessary 2. The system of claim 1, (Appendix 19) The return unit includes: When returning the item, responses will be sent in a timely manner that takes into account the sales rep's schedule. 2. The system of claim 1, (Appendix 20) The return unit includes: To estimate a user's emotion and adjust a means of sending a response based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The return unit includes: When returning the product, the sales representative will refer to the sales representative's past response history and send a response in a format. 2. The system of claim 1, (Appendix 22) The return unit includes: When returning the response, the responses can be distributed to multiple people to make the response more efficient. 2. The system of claim 1, [Explanation of symbols]

[0168] 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 for receiving inquiry emails; a generation unit that analyzes the inquiry email received by the reception unit and generates an answer based on a history of past inquiry answers and the latest information; A system comprising: a return unit that returns the answer generated by the generation unit to a sales representative.

2. The generation unit is Analyze past inquiry response history using generation AI and generate responses 2. The system of claim 1 .

3. The generation unit is Obtain inventory status using AI and reflect it in the answer 2. The system of claim 1 .

4. The reception unit is Infer user sentiment and prioritize inquiries based on the estimated user sentiment 2. The system of claim 1 .

5. The reception unit is Analyze past ticket history and group similar tickets 2. The system of claim 1 .

6. The reception unit is Categorize inquiries based on their content 2. The system of claim 1 .

7. The reception unit is Estimate user emotions and adjust the time for accepting inquiry emails based on the estimated user emotions 2. The system of claim 1 .

Images