System

Abstract

To provide a system that rapidly and accurately responses to many inquiries.SOLUTION: A system according to the embodiment comprises a reception unit, a generation unit, a transmission unit, and a correction unit. The reception unit receives the content of an inquiry. The generation unit analyzes the content of the inquiry received by the reception unit, and generates a draft answer. The transmission unit transmits the draft answer generated by the generation unit. The correction unit corrects the draft answer transmitted by the transmission unit.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] Conventional techniques have had the problem that it is difficult to respond to a large number of inquiries quickly and accurately.

[0005] The system according to the embodiment aims to quickly and accurately respond to a large number of inquiries. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a transmission unit, and a correction unit. The reception unit receives the content of an inquiry. The generation unit analyzes the content of the inquiry received by the reception unit and generates a draft answer. The transmission unit transmits the draft answer generated by the generation unit. The correction unit corrects the draft answer transmitted by the transmission unit. Effect of the Invention

[0007] The system according to the embodiment can quickly and accurately respond to a large number of inquiries. [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 to efficiently create a response draft for a person in charge who receives many inquiries every day, and responds to a registered team member such as a superior or a person in charge. In this system, first, an inquiry from a customer is read into the generation AI. Next, the generation AI analyzes the content of the inquiry and generates an appropriate response draft. This draft is sent to a registered team member such as a superior or a person in charge. The team member checks the draft content and makes corrections as necessary. Finally, the corrected draft is used as a response to the customer. For example, an inquiry from a customer is read into the generation AI. At this time, the inquiry content is input in text format. For example, an inquiry such as "Please tell me how to return a product" is input. This information is input into the generation AI. Next, the generation AI analyzes the input inquiry content. The generation AI understands the inquiry content and generates an appropriate response draft. For example, a draft such as "Please follow the steps below to return a product" is generated. The generated draft is sent to a registered team member such as a superior or a person in charge. The team member checks the draft content and makes corrections as necessary. For example, the person in charge can modify part of the draft or add additional information. Finally, the modified draft is used as a response to the customer. For example, the modified draft is sent to the customer by email. This system reduces the burden on the person in charge and enables a quick and accurate response. As a result, the inquiry response system can reduce the burden on the person in charge and provide a quick and accurate response.

[0029] The inquiry response system according to the embodiment includes a reception unit, a generation unit, a transmission unit, and a correction unit. The reception unit receives the inquiry content. The inquiry content includes, for example, a text format, a voice format, an image format, and the like, but is not limited to these examples. The reception unit receives the inquiry in, for example, a text format. The generation unit uses a generation AI to analyze the inquiry content received by the reception unit and generate a response draft. The generation AI uses, for example, a text generation AI (for example, LLM) to analyze the inquiry content and generate an appropriate response draft. The generation unit uses the generation AI to understand the inquiry content and generate an appropriate response draft. For example, the generation AI generates a response draft of "Please tell me how to return a product" in response to an inquiry of "Please follow the steps below to return the product." The transmission unit transmits the response draft generated by the generation unit to a registered team member such as a supervisor or a person in charge. The transmission unit transmits the response draft using, for example, an email or a messaging app. The correction unit corrects the response draft transmitted by the transmission unit. The correction unit can, for example, correct a part of the draft, add additional information, etc. This enables the inquiry response system according to the embodiment to efficiently accept and analyze the content of an inquiry, and generate, transmit, and correct a draft response.

[0030] The reception unit receives the inquiry content. The inquiry content includes, for example, a text format, a voice format, an image format, and the like, but is not limited to such examples. The reception unit receives, for example, an inquiry in text format. Specifically, the reception unit can receive inquiries from users through a web form, a chatbot, email, and the like. In a web form, a user inputs the inquiry content and presses a send button to send the data to the reception unit. In the case of a chatbot, when a user inputs a question in natural language, the chatbot analyzes the content and transfers it to the reception unit. For inquiries in voice format, voice data is converted into text using voice recognition technology, and the reception unit receives the text data. For inquiries in image format, image data is analyzed using image recognition technology, necessary information is extracted, and sent to the reception unit. This allows the reception unit to receive inquiries in various formats, improving user convenience. In addition, the reception unit centrally manages the received inquiry content and stores it in a database, allowing subsequent processing to be performed smoothly. For example, a unique ID is assigned to the inquiry content, and the subsequent generation unit and transmission unit refer to the ID, making it easier to track and manage the inquiry. Furthermore, the reception unit is also equipped with a function that automatically determines the importance and urgency of the inquiry and sets priorities, making it possible to respond quickly to inquiries with a high level of urgency.

[0031] The generation unit uses the generation AI to analyze the inquiry content received by the reception unit and generate a response draft. The generation AI, for example, uses a text generation AI (for example, LLM) to analyze the inquiry content and generate an appropriate response draft. The generation unit uses the generation AI to understand the inquiry content and generate an appropriate response draft. Specifically, the generation AI makes full use of natural language processing technology to extract the intention and main points of the inquiry content and generate an optimal response based on that. For example, in response to an inquiry such as "Please tell me how to return a product," the generation AI first recognizes the keyword "return method" and then retrieves information about the procedure from a database. The generation AI refers to past inquiry data and an FAQ database to generate the most appropriate response draft. The generated response draft is provided in a format that is grammatically correct and easy for the user to understand. Furthermore, the generation unit also has a function of presenting multiple response drafts generated by the generation AI as candidates at once and selecting the optimal one. This allows the generation unit to respond to the inquiry content quickly and accurately. The generation unit also has a function of automatically evaluating the generated response drafts and checking their quality. For example, if the generated answer draft is not appropriate or may be misleading, the quality is ensured by regenerating it. This allows the generator to always provide high-quality answer drafts, improving user satisfaction.

[0032] The sending unit sends the answer draft generated by the generating unit to registered team members such as a supervisor or a person in charge. The sending unit sends the answer draft using, for example, email or a messaging app. Specifically, the sending unit automatically formats the answer draft received from the generating unit and sends it to an appropriate destination. In the case of email, the sending unit generates an email including a subject, a body, an attachment, etc., and sends it to a specified address. In the case of a messaging app, the sending unit sends the answer draft in a chat format, enabling real-time communication. The sending unit also has a function of appropriately tagging and classifying the answer draft so that the team members to whom it is sent can easily check it. For example, different tags can be assigned depending on the type and importance of the inquiry, allowing team members to quickly identify inquiries that should be dealt with as a priority. In addition, the sending unit ensures traceability of the inquiry response by recording the sending history and making it available for later reference. In addition, the sending unit also has a function of following up after sending, allowing team members to provide feedback on the answer draft. This allows the sending unit to check whether the generated answer draft is appropriate or not, and to send feedback to the correction unit as necessary. This enables the sending unit to efficiently and effectively send answer drafts to team members, improving the quality of inquiries handled.

[0033] The correction department corrects the answer draft sent by the transmission department. The correction department can, for example, correct part of the draft or add additional information. Specifically, the correction department receives feedback from team members and reviews the content of the answer draft. For example, it corrects grammatical errors and inappropriate expressions to make the draft clearer and easier to understand. In addition, if additional information is required for the inquiry content, it refers to related data and materials and adds them to the draft. The correction department can be manually corrected by a person with specialized knowledge, but it also has an automatic correction function using AI. For example, it has a function to automatically evaluate the quality of the draft using natural language processing technology and suggest necessary corrections. This allows the correction department to quickly and accurately correct the draft and complete the final answer draft. Furthermore, the correction department ensures transparency and traceability of the inquiry response by recording the correction history and making it available for later reference. For example, it records in detail which parts were corrected and how, so that the past corrections can be checked as necessary. This allows the correction department to always provide high-quality answer drafts and improve user satisfaction. The correction department also has a process for sending the corrected draft back to the sending department for final checking, so that the correction department can check that the final answer draft is appropriate and prepare it for delivery to the user.

[0034] The correction unit includes a history storage unit that stores a correction history. The history storage unit stores the correction history. The correction history includes, for example, the correction date and time, the correction content, and the person who corrected, but is not limited to these examples. The history storage unit records, for example, the correction date and time and the correction content, and also stores information about the person who corrected. In this way, by storing the correction history, it becomes possible to track the correction content.

[0035] The correction unit includes a confirmation unit that checks the revised draft again. The confirmation unit checks the revised draft again. The confirmation unit can perform, for example, manual confirmation or automatic confirmation. In manual confirmation, a team member visually checks the revised draft and makes further corrections if necessary. In automatic confirmation, the system checks the revised draft and detects grammar and spelling errors. In this way, by checking the revised draft again, the accuracy of the draft is improved.

[0036] The reception unit can receive the inquiry content in a text format. The text format includes, but is not limited to, for example, plain text and rich text. The reception unit receives, for example, an inquiry in a plain text format. The reception unit can also receive an inquiry in a rich text format. This makes it easier to process the inquiry content by receiving it in a text format.

[0037] The generation unit can analyze the inquiry content using a generation AI and generate a draft answer. Examples of the generation AI include, but are not limited to, GPT-4 (registered trademark) and Gemini. The generation unit can analyze the inquiry content using, for example, GPT-4 and generate a draft answer. The generation unit can also analyze the inquiry content using Gemini and generate a draft answer. This improves the accuracy of generating the draft answer by using the generation AI.

[0038] The sending unit can send the generated draft answer to a registered team member of the supervisor or the person in charge. The registered team members include, but are not limited to, for example, the supervisor, the person in charge, and a specific job title. The sending unit sends the draft answer to, for example, the supervisor. The sending unit can also send the draft answer to the person in charge. Furthermore, the sending unit can also send the draft answer according to a specific job title. In this way, the generated draft answer can be sent to a team member for quick confirmation and correction.

[0039] The reception unit can analyze the past inquiry history and automatically classify similar inquiries. For example, the reception unit clusters the contents of the past inquiries and groups similar inquiries. The reception unit can also automatically tag similar inquiries and process them efficiently. Furthermore, the reception unit can identify and automatically classify frequently occurring inquiry patterns based on the past inquiry history. This makes it possible to efficiently process similar inquiries by analyzing the past inquiry history.

[0040] The reception unit can perform filtering based on the user's profile information when receiving the inquiry content. The reception unit prioritizes processing of related inquiries based on the user's purchase history, for example. The reception unit can also refer to the user's account information and apply different filtering to specific user groups. Furthermore, the reception unit can also prioritize processing of inquiries with high importance based on the user's past inquiry history. In this way, important inquiries can be prioritized by filtering based on the user's profile information.

[0041] When accepting inquiries, the reception unit can preferentially accept inquiries with high relevance based on the geographical location information of the user. The reception unit, for example, preferentially processes inquiries specific to a region based on the user's current location. The reception unit can also refer to the geographical location information of the user and preferentially accept inquiries about nearby services. Furthermore, the reception unit can also preferentially process inquiries related to local events and campaigns based on the user's location information. This allows for a rapid response to region-specific inquiries by preferentially accepting inquiries with high relevance based on the geographical location information of the user.

[0042] When accepting inquiries, the reception unit can analyze the user's social media activity and prioritize accepting related inquiries. For example, the reception unit analyzes the user's comments on social media and prioritizes processing related inquiries. The reception unit can also prioritize accepting inquiries about specific topics based on the user's social media activity history. Furthermore, the reception unit can also prioritize processing inquiries with a high level of importance, taking into account the number of followers and influence of the user on social media. In this way, related inquiries can be efficiently processed by analyzing the user's social media activity.

[0043] When generating a draft answer, the generation unit can adjust the level of detail based on the importance of the inquiry. For example, for an inquiry of high importance, the generation unit generates a draft answer including a detailed explanation. For an inquiry of low importance, the generation unit can also generate a concise draft answer. Furthermore, the generation unit can also generate a draft answer that appropriately includes necessary information according to the importance of the inquiry. In this way, by adjusting the level of detail based on the importance of the inquiry, appropriate information can be provided.

[0044] When generating a draft answer, the generation unit can apply different generation algorithms depending on the category of the inquiry. For example, the generation unit applies a generation algorithm based on product information to an inquiry about a product. The generation unit can also apply a generation algorithm based on the service content to an inquiry about a service. Furthermore, the generation unit can also apply a generation algorithm based on technical information to a technical inquiry. In this way, by applying a generation algorithm depending on the category of the inquiry, a more appropriate draft answer can be generated.

[0045] When generating a draft answer, the generation unit can determine the priority order based on the time of submission of the inquiry. For example, the generation unit prioritizes recently submitted inquiries and quickly generates a draft answer. The generation unit can also generate a draft answer with normal priority order for an inquiry that was submitted a long time ago. Furthermore, the generation unit can generate a draft answer at an appropriate timing depending on the time of submission. This allows for a quick response by determining the priority order based on the time of submission of the inquiry.

[0046] When generating a draft answer, the generation unit can improve the accuracy of the draft by referring to related past inquiry contents. For example, the generation unit generates a highly accurate draft answer by referring to similar past inquiry contents. The generation unit can also generate a draft answer that incorporates appropriate information based on the past inquiry history. Furthermore, the generation unit can analyze the past inquiry contents and generate an optimal draft answer. In this way, the accuracy of the draft answer is improved by referring to related past inquiry contents.

[0047] At the time of sending, the sending unit can customize the sending content based on the job title and specialty of the recipient's team member. For example, the sending unit sends a draft including detailed information to a supervisor. The sending unit can also send a draft including a specific response method to a person in charge. Furthermore, the sending unit can also send a draft including appropriate information according to the specialty. In this way, appropriate information can be provided by customizing the sending content based on the recipient's job title and specialty.

[0048] At the time of transmission, the transmission unit can select the optimal transmission method by referring to past transmission history. The transmission unit selects the optimal transmission method based on, for example, past transmission history. The transmission unit can also analyze past transmission history and select an effective transmission method. Furthermore, the transmission unit can also refer to past transmission history and transmit at an appropriate timing. In this way, the optimal transmission method can be selected by referring to past transmission history.

[0049] At the time of transmission, the transmission unit can select the optimal transmission method based on the geographical location information of the destination. The transmission unit selects the optimal transmission method based on, for example, the geographical location information of the destination. The transmission unit can also transmit a draft including region-specific information by referring to the geographical location information of the destination. Furthermore, the transmission unit can also transmit at an appropriate timing, taking into account the geographical location information of the destination. In this way, by selecting the optimal transmission method based on the geographical location information of the destination, a draft including region-specific information can be transmitted.

[0050] At the time of sending, the sending unit can analyze the recipient's social media activity and customize the sending content. For example, the sending unit analyzes the recipient's comments on social media and sends a draft message including relevant information. The sending unit can also send a draft message including appropriate information based on the recipient's social media activity history. Furthermore, the sending unit can also send a draft message including information of high importance, taking into consideration the number of followers and influence of the recipient on social media. In this way, by analyzing the recipient's social media activity, it is possible to send a draft message including relevant information.

[0051] At the time of correction, the correction unit can select the optimal correction method by referring to the past correction history. The correction unit selects the optimal correction method based on, for example, the past correction history. The correction unit can also analyze the past correction history and select an effective correction method. Furthermore, the correction unit can also perform correction at an appropriate time by referring to the past correction history. In this way, the optimal correction method can be selected by referring to the past correction history.

[0052] During revision, the revision unit can apply different revision algorithms depending on the category of the text. For example, the revision unit applies a revision algorithm based on product information to a text about a product. The revision unit can also apply a revision algorithm based on service content to a text about a service. Furthermore, the revision unit can apply a revision algorithm based on technical information to a technical text. This allows for more appropriate revision by applying a revision algorithm depending on the category of the text.

[0053] The correction unit can select the optimal correction method based on the geographical location information of the corrector at the time of correction. The correction unit selects the optimal correction method based on, for example, the geographical location information of the corrector. The correction unit can also make corrections including area-specific information by referring to the geographical location information of the corrector. Furthermore, the correction unit can also make corrections at an appropriate time by taking into account the geographical location information of the corrector. This makes it possible to make corrections including area-specific information by selecting the optimal correction method based on the geographical location information of the corrector.

[0054] When making a correction, the correction unit can analyze the social media activity of the person making the correction and customize the correction content. For example, the correction unit analyzes the comments made by the person making the correction on social media and makes a correction that includes relevant information. The correction unit can also make a correction that includes appropriate information based on the person's social media activity history. Furthermore, the correction unit can also make a correction that includes information of high importance, taking into account the number of followers and influence of the person making the correction on social media. In this way, by analyzing the social media activity of the person making the correction, it is possible to make a correction that includes relevant information.

[0055] When saving the revision history, the history saving unit can adjust the level of detail of the save based on the importance of the revision content. For example, the history saving unit saves a detailed revision history for revision content with high importance. The history saving unit can also save a concise revision history for revision content with low importance. Furthermore, the history saving unit can also save a revision history that includes appropriate information according to the importance of the revision content. In this way, by adjusting the level of detail of the save based on the importance of the revision content, appropriate information can be saved.

[0056] When saving the revision history, the history saving unit can select the optimal saving method based on the geographical location information of the corrector. The history saving unit selects the optimal saving method based on, for example, the geographical location information of the corrector. The history saving unit can also save the revision history including area-specific information by referring to the geographical location information of the corrector. Furthermore, the history saving unit can also save the revision history at an appropriate time, taking into account the geographical location information of the corrector. In this way, by selecting the optimal saving method based on the geographical location information of the corrector, it is possible to save the revision history including area-specific information.

[0057] When checking the revised draft, the confirmation unit can select the optimal confirmation method by referring to the past confirmation history. The confirmation unit selects the optimal confirmation method based on the past confirmation history, for example. The confirmation unit can also analyze the past confirmation history and select an effective confirmation method. Furthermore, the confirmation unit can also refer to the past confirmation history and perform confirmation at an appropriate time. In this way, the optimal confirmation method can be selected by referring to the past confirmation history.

[0058] When checking the revised draft, the confirmation unit can select the optimal confirmation method based on the geographical location information of the confirmer. The confirmation unit selects the optimal confirmation method based on, for example, the geographical location information of the confirmer. The confirmation unit can also refer to the geographical location information of the confirmer and perform confirmation including information specific to the region. Furthermore, the confirmation unit can also perform confirmation at an appropriate time, taking into account the geographical location information of the confirmer. In this way, by selecting the optimal confirmation method based on the geographical location information of the confirmer, confirmation including information specific to the region becomes possible.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The inquiry response system may further include an analysis unit that analyzes the user's past inquiry history and identifies frequent inquiry patterns. The analysis unit, for example, clusters the past inquiry contents and groups similar inquiries. The analysis unit may also identify frequent inquiry patterns and generate templates for efficient processing. Furthermore, the analysis unit may grasp trends in inquiry contents and predict future inquiries. In this way, the efficiency of inquiry response is improved by analyzing the past inquiry history.

[0061] The modification unit may include a priority determination unit that determines the priority of modifications based on the importance of the modification content. For example, the priority determination unit prioritizes modifications to modifications with high importance. The priority determination unit can also perform modifications with normal priority to modifications with low importance. Furthermore, the priority determination unit can also perform modifications immediately depending on the urgency of the modification content. In this way, important modifications can be performed quickly by determining the priority of modifications based on the importance of the modification content.

[0062] When reviewing the revised draft, the reviewing unit can change the reviewing method based on the reviewer's field of expertise. For example, the reviewing unit requests a review from a technical reviewing unit regarding technical content. The reviewing unit can also request a review from a customer service reviewing unit regarding content related to customer service. Furthermore, the reviewing unit can also request a review from a legal reviewing unit regarding content related to legal matters. In this way, by changing the reviewing method based on the reviewing unit's field of expertise, more appropriate review is possible.

[0063] When receiving the inquiry content, the reception unit can give priority to processing related inquiries based on the user's purchase history. For example, the reception unit gives priority to processing inquiries about products that the user has purchased in the past. The reception unit can also analyze the user's purchase history and efficiently process inquiries about related products. Furthermore, the reception unit can automatically classify inquiries about specific products based on the user's purchase history. This allows for efficient response by giving priority to processing related inquiries based on the user's purchase history.

[0064] When generating a draft answer, the generation unit can apply different generation algorithms depending on the category of the inquiry content. For example, the generation unit applies a generation algorithm based on technical information to a technical inquiry. The generation unit can also apply a generation algorithm based on customer service information to an inquiry about customer service. Furthermore, the generation unit can apply a generation algorithm based on legal information to an inquiry about legal matters. In this way, by applying a generation algorithm depending on the category of the inquiry content, a more appropriate draft answer can be generated.

[0065] The process flow of the first embodiment will be briefly described below.

[0066] Step 1: The reception unit receives the inquiry content. The inquiry content may be in a text format, a voice format, an image format, or the like, but is not limited to these examples. For example, an inquiry in text format is received. Step 2: The generation unit uses a generation AI to analyze the inquiry received by the reception unit and generate a draft response. The generation AI analyzes the inquiry using, for example, a text generation AI (e.g., LLM) and generates an appropriate draft response. For example, in response to the inquiry "Please tell me how to return a product," the generation AI generates a draft response saying, "Please follow the steps below to return the product." Step 3: The sending unit sends the answer draft generated by the generating unit to a registered team member such as a supervisor or a person in charge. The sending unit sends the answer draft using, for example, email or a messaging app. Step 4: The correction unit corrects the answer draft sent by the sending unit. For example, the correction unit can correct a part of the draft or add additional information.

[0067] (Example 2) The inquiry response system according to the embodiment of the present invention is a system that uses a generation AI to efficiently create a response draft for a person in charge who receives many inquiries every day, and responds to a registered team member such as a superior or a person in charge. In this system, first, an inquiry from a customer is read into the generation AI. Next, the generation AI analyzes the content of the inquiry and generates an appropriate response draft. This draft is sent to a registered team member such as a superior or a person in charge. The team member checks the draft content and makes corrections as necessary. Finally, the corrected draft is used as a response to the customer. For example, an inquiry from a customer is read into the generation AI. At this time, the inquiry content is input in text format. For example, an inquiry such as "Please tell me how to return a product" is input. This information is input into the generation AI. Next, the generation AI analyzes the input inquiry content. The generation AI understands the inquiry content and generates an appropriate response draft. For example, a draft such as "Please follow the steps below to return a product" is generated. The generated draft is sent to a registered team member such as a superior or a person in charge. The team member checks the draft content and makes corrections as necessary. For example, the person in charge can modify part of the draft or add additional information. Finally, the modified draft is used as a response to the customer. For example, the modified draft is sent to the customer by email. This system reduces the burden on the person in charge and enables a quick and accurate response. As a result, the inquiry response system can reduce the burden on the person in charge and provide a quick and accurate response.

[0068] The inquiry response system according to the embodiment includes a reception unit, a generation unit, a transmission unit, and a correction unit. The reception unit receives the inquiry content. The inquiry content includes, for example, a text format, a voice format, an image format, and the like, but is not limited to these examples. The reception unit receives the inquiry in, for example, a text format. The generation unit uses a generation AI to analyze the inquiry content received by the reception unit and generate a response draft. The generation AI uses, for example, a text generation AI (for example, LLM) to analyze the inquiry content and generate an appropriate response draft. The generation unit uses the generation AI to understand the inquiry content and generate an appropriate response draft. For example, the generation AI generates a response draft of "Please tell me how to return a product" in response to an inquiry of "Please follow the steps below to return the product." The transmission unit transmits the response draft generated by the generation unit to a registered team member such as a supervisor or a person in charge. The transmission unit transmits the response draft using, for example, an email or a messaging app. The correction unit corrects the response draft transmitted by the transmission unit. The correction unit can, for example, correct a part of the draft, add additional information, etc. This enables the inquiry response system according to the embodiment to efficiently accept and analyze the content of an inquiry, and generate, transmit, and correct a draft response.

[0069] The reception unit receives the inquiry content. The inquiry content includes, for example, a text format, a voice format, an image format, and the like, but is not limited to such examples. The reception unit receives, for example, an inquiry in text format. Specifically, the reception unit can receive inquiries from users through a web form, a chatbot, email, and the like. In a web form, a user inputs the inquiry content and presses a send button to send the data to the reception unit. In the case of a chatbot, when a user inputs a question in natural language, the chatbot analyzes the content and transfers it to the reception unit. For inquiries in voice format, voice data is converted into text using voice recognition technology, and the reception unit receives the text data. For inquiries in image format, image data is analyzed using image recognition technology, necessary information is extracted, and sent to the reception unit. This allows the reception unit to receive inquiries in various formats, improving user convenience. In addition, the reception unit centrally manages the received inquiry content and stores it in a database, allowing subsequent processing to be performed smoothly. For example, a unique ID is assigned to the inquiry content, and the subsequent generation unit and transmission unit refer to the ID, making it easier to track and manage the inquiry. Furthermore, the reception unit is also equipped with a function that automatically determines the importance and urgency of the inquiry and sets priorities, making it possible to respond quickly to inquiries with a high level of urgency.

[0070] The generation unit uses the generation AI to analyze the inquiry content received by the reception unit and generate a response draft. The generation AI, for example, uses a text generation AI (for example, LLM) to analyze the inquiry content and generate an appropriate response draft. The generation unit uses the generation AI to understand the inquiry content and generate an appropriate response draft. Specifically, the generation AI makes full use of natural language processing technology to extract the intention and main points of the inquiry content and generate an optimal response based on that. For example, in response to an inquiry such as "Please tell me how to return a product," the generation AI first recognizes the keyword "return method" and then retrieves information about the procedure from a database. The generation AI refers to past inquiry data and an FAQ database to generate the most appropriate response draft. The generated response draft is provided in a format that is grammatically correct and easy for the user to understand. Furthermore, the generation unit also has a function of presenting multiple response drafts generated by the generation AI as candidates at once and selecting the optimal one. This allows the generation unit to respond to the inquiry content quickly and accurately. The generation unit also has a function of automatically evaluating the generated response drafts and checking their quality. For example, if the generated answer draft is not appropriate or may be misleading, the quality is ensured by regenerating it. This allows the generator to always provide high-quality answer drafts, improving user satisfaction.

[0071] The sending unit sends the answer draft generated by the generating unit to registered team members such as a supervisor or a person in charge. The sending unit sends the answer draft using, for example, email or a messaging app. Specifically, the sending unit automatically formats the answer draft received from the generating unit and sends it to an appropriate destination. In the case of email, the sending unit generates an email including a subject, a body, an attachment, etc., and sends it to a specified address. In the case of a messaging app, the sending unit sends the answer draft in a chat format, enabling real-time communication. The sending unit also has a function of appropriately tagging and classifying the answer draft so that the team members to whom it is sent can easily check it. For example, different tags can be assigned depending on the type and importance of the inquiry, allowing team members to quickly identify inquiries that should be dealt with as a priority. In addition, the sending unit ensures traceability of the inquiry response by recording the sending history and making it available for later reference. In addition, the sending unit also has a function of following up after sending, allowing team members to provide feedback on the answer draft. This allows the sending unit to check whether the generated answer draft is appropriate or not, and to send feedback to the correction unit as necessary. This enables the sending unit to efficiently and effectively send answer drafts to team members, improving the quality of inquiries handled.

[0072] The correction department corrects the answer draft sent by the transmission department. The correction department can, for example, correct part of the draft or add additional information. Specifically, the correction department receives feedback from team members and reviews the content of the answer draft. For example, it corrects grammatical errors and inappropriate expressions to make the draft clearer and easier to understand. In addition, if additional information is required for the inquiry content, it refers to related data and materials and adds them to the draft. The correction department can be manually corrected by a person with specialized knowledge, but it also has an automatic correction function using AI. For example, it has a function to automatically evaluate the quality of the draft using natural language processing technology and suggest necessary corrections. This allows the correction department to quickly and accurately correct the draft and complete the final answer draft. Furthermore, the correction department ensures transparency and traceability of the inquiry response by recording the correction history and making it available for later reference. For example, it records in detail which parts were corrected and how, so that the past corrections can be checked as necessary. This allows the correction department to always provide high-quality answer drafts and improve user satisfaction. The correction department also has a process for sending the corrected draft back to the sending department for final checking, so that the correction department can check that the final answer draft is appropriate and prepare it for delivery to the user.

[0073] The correction unit includes a history storage unit that stores a correction history. The history storage unit stores the correction history. The correction history includes, for example, the correction date and time, the correction content, and the person who corrected, but is not limited to these examples. The history storage unit records, for example, the correction date and time and the correction content, and also stores information about the person who corrected. In this way, by storing the correction history, it becomes possible to track the correction content.

[0074] The correction unit includes a confirmation unit that checks the revised draft again. The confirmation unit checks the revised draft again. The confirmation unit can perform, for example, manual confirmation or automatic confirmation. In manual confirmation, a team member visually checks the revised draft and makes further corrections if necessary. In automatic confirmation, the system checks the revised draft and detects grammar and spelling errors. In this way, by checking the revised draft again, the accuracy of the draft is improved.

[0075] The reception unit can receive the inquiry content in a text format. The text format includes, but is not limited to, for example, plain text and rich text. The reception unit receives, for example, an inquiry in a plain text format. The reception unit can also receive an inquiry in a rich text format. This makes it easier to process the inquiry content by receiving it in a text format.

[0076] The generation unit can analyze the inquiry content using a generation AI and generate a draft answer. Examples of the generation AI include, but are not limited to, GPT-4 and Gemini. The generation unit can analyze the inquiry content using, for example, GPT-4 and generate a draft answer. The generation unit can also analyze the inquiry content using Gemini and generate a draft answer. This improves the accuracy of generating the draft answer by using the generation AI.

[0077] The sending unit can send the generated draft answer to a registered team member of the supervisor or the person in charge. The registered team members include, but are not limited to, for example, the supervisor, the person in charge, and a specific job title. The sending unit sends the draft answer to, for example, the supervisor. The sending unit can also send the draft answer to the person in charge. Furthermore, the sending unit can also send the draft answer according to a specific job title. In this way, the generated draft answer can be sent to a team member for quick confirmation and correction.

[0078] The reception unit can estimate the user's emotion and determine the priority of the inquiry content based on the estimated user's emotion. For example, when the user is dissatisfied, the reception unit processes the inquiry content with priority. Also, when the user is satisfied, the reception unit can process the inquiry with normal priority. Furthermore, when the user feels urgency, the reception unit can raise the priority to respond immediately. In this way, important inquiries can be promptly processed by determining the priority based on the user's emotion. 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.

[0079] The reception unit can analyze the past inquiry history and automatically classify similar inquiries. For example, the reception unit clusters the contents of the past inquiries and groups similar inquiries. The reception unit can also automatically tag similar inquiries and process them efficiently. Furthermore, the reception unit can identify and automatically classify frequently occurring inquiry patterns based on the past inquiry history. This makes it possible to efficiently process similar inquiries by analyzing the past inquiry history.

[0080] The reception unit can perform filtering based on the user's profile information when receiving the inquiry content. The reception unit prioritizes processing of related inquiries based on the user's purchase history, for example. The reception unit can also refer to the user's account information and apply different filtering to specific user groups. Furthermore, the reception unit can also prioritize processing of inquiries with high importance based on the user's past inquiry history. In this way, important inquiries can be prioritized by filtering based on the user's profile information.

[0081] The reception unit can estimate the user's emotion and change the method of receiving the inquiry content based on the estimated user's emotion. For example, when the user is stressed, the reception unit provides a simple interface and minimizes the input procedure. In addition, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and enable the user to input the inquiry content quickly. This allows for a more appropriate response by adjusting the reception method according to the user's emotion. 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.

[0082] When accepting inquiries, the reception unit can preferentially accept inquiries with high relevance based on the geographical location information of the user. The reception unit, for example, preferentially processes inquiries specific to a region based on the user's current location. The reception unit can also refer to the geographical location information of the user and preferentially accept inquiries about nearby services. Furthermore, the reception unit can also preferentially process inquiries related to local events and campaigns based on the user's location information. This allows for a rapid response to region-specific inquiries by preferentially accepting inquiries with high relevance based on the geographical location information of the user.

[0083] When accepting inquiries, the reception unit can analyze the user's social media activity and prioritize accepting related inquiries. For example, the reception unit analyzes the user's comments on social media and prioritizes processing related inquiries. The reception unit can also prioritize accepting inquiries about specific topics based on the user's social media activity history. Furthermore, the reception unit can also prioritize processing inquiries with a high level of importance, taking into account the number of followers and influence of the user on social media. In this way, related inquiries can be efficiently processed by analyzing the user's social media activity.

[0084] The generation unit can estimate the user's emotion and adjust the expression method of the answer draft based on the estimated user's emotion. For example, when the user is dissatisfied, the generation unit generates an answer draft using polite and empathetic expressions. In addition, when the user is satisfied, the generation unit can also generate an answer draft using friendly and casual expressions. Furthermore, when the user feels urgency, the generation unit can also generate an answer draft using quick and concise expressions. This allows for a more appropriate answer by adjusting the expression method of the answer draft according to the user's emotion. 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.

[0085] When generating a draft answer, the generation unit can adjust the level of detail based on the importance of the inquiry. For example, for an inquiry of high importance, the generation unit generates a draft answer including a detailed explanation. For an inquiry of low importance, the generation unit can also generate a concise draft answer. Furthermore, the generation unit can also generate a draft answer that appropriately includes necessary information according to the importance of the inquiry. In this way, by adjusting the level of detail based on the importance of the inquiry, appropriate information can be provided.

[0086] When generating a draft answer, the generation unit can apply different generation algorithms depending on the category of the inquiry. For example, the generation unit applies a generation algorithm based on product information to an inquiry about a product. The generation unit can also apply a generation algorithm based on the service content to an inquiry about a service. Furthermore, the generation unit can also apply a generation algorithm based on technical information to a technical inquiry. In this way, by applying a generation algorithm depending on the category of the inquiry, a more appropriate draft answer can be generated.

[0087] The generation unit can estimate the user's emotion and adjust the length of the answer draft based on the estimated user's emotion. For example, when the user is dissatisfied, the generation unit generates a longer answer draft including a detailed explanation. In addition, when the user is satisfied, the generation unit can also generate a shorter answer draft that is concise and to the point. Furthermore, when the user feels urgency, the generation unit can also generate a short answer draft that is short and to the point so that a quick response can be made. This allows a more appropriate answer to be given by adjusting the length of the answer draft according to the user's emotion. The emotion estimation 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.

[0088] When generating a draft answer, the generation unit can determine the priority order based on the time of submission of the inquiry. For example, the generation unit prioritizes recently submitted inquiries and quickly generates a draft answer. The generation unit can also generate a draft answer with normal priority order for an inquiry that was submitted a long time ago. Furthermore, the generation unit can generate a draft answer at an appropriate timing depending on the time of submission. This allows for a quick response by determining the priority order based on the time of submission of the inquiry.

[0089] When generating a draft answer, the generation unit can improve the accuracy of the draft by referring to related past inquiry contents. For example, the generation unit generates a highly accurate draft answer by referring to similar past inquiry contents. The generation unit can also generate a draft answer that incorporates appropriate information based on the past inquiry history. Furthermore, the generation unit can analyze the past inquiry contents and generate an optimal draft answer. In this way, the accuracy of the draft answer is improved by referring to related past inquiry contents.

[0090] The transmission unit can estimate the user's emotion and determine the order of the drafts to be sent based on the estimated user's emotion. For example, when the user is dissatisfied, the transmission unit determines the draft to be sent with priority. Also, when the user is satisfied, the transmission unit can determine the draft to be sent with normal priority. Furthermore, when the user feels urgency, the transmission unit can determine the draft to be sent immediately. In this way, by determining the priority of the drafts to be sent based on the user's emotion, important drafts can be sent quickly. 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.

[0091] At the time of sending, the sending unit can customize the sending content based on the job title and specialty of the recipient's team member. For example, the sending unit sends a draft including detailed information to a supervisor. The sending unit can also send a draft including a specific response method to a person in charge. Furthermore, the sending unit can also send a draft including appropriate information according to the specialty. In this way, appropriate information can be provided by customizing the sending content based on the recipient's job title and specialty.

[0092] At the time of transmission, the transmission unit can select the optimal transmission method by referring to past transmission history. The transmission unit selects the optimal transmission method based on, for example, past transmission history. The transmission unit can also analyze past transmission history and select an effective transmission method. Furthermore, the transmission unit can also refer to past transmission history and transmit at an appropriate timing. In this way, the optimal transmission method can be selected by referring to past transmission history.

[0093] The transmission unit can estimate the user's emotion and change the display method of the draft to be transmitted based on the estimated user's emotion. For example, when the user is dissatisfied, the transmission unit provides a polite and highly visible display method. Furthermore, when the user is satisfied, the transmission unit can also provide a friendly and casual display method. Furthermore, when the user feels urgency, the transmission unit can also provide a quick and concise display method. This allows for more appropriate display by adjusting the display method of the draft to be transmitted according to the user's emotion. 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.

[0094] At the time of transmission, the transmission unit can select the optimal transmission method based on the geographical location information of the destination. The transmission unit selects the optimal transmission method based on, for example, the geographical location information of the destination. The transmission unit can also transmit a draft including region-specific information by referring to the geographical location information of the destination. Furthermore, the transmission unit can also transmit at an appropriate timing, taking into account the geographical location information of the destination. In this way, by selecting the optimal transmission method based on the geographical location information of the destination, a draft including region-specific information can be transmitted.

[0095] At the time of sending, the sending unit can analyze the recipient's social media activity and customize the sending content. For example, the sending unit analyzes the recipient's comments on social media and sends a draft message including relevant information. The sending unit can also send a draft message including appropriate information based on the recipient's social media activity history. Furthermore, the sending unit can also send a draft message including information of high importance, taking into consideration the number of followers and influence of the recipient on social media. In this way, by analyzing the recipient's social media activity, it is possible to send a draft message including relevant information.

[0096] The correction unit can estimate the user's emotion and determine the priority of correction based on the estimated user's emotion. For example, when the user is dissatisfied, the correction unit performs correction with priority. Also, when the user is satisfied, the correction unit can perform correction with normal priority. Furthermore, when the user feels urgency, the correction unit can perform correction immediately. In this way, important corrections can be made quickly by determining the priority of correction 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 is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0097] At the time of correction, the correction unit can select the optimal correction method by referring to the past correction history. The correction unit selects the optimal correction method based on, for example, the past correction history. The correction unit can also analyze the past correction history and select an effective correction method. Furthermore, the correction unit can also perform correction at an appropriate time by referring to the past correction history. In this way, the optimal correction method can be selected by referring to the past correction history.

[0098] During revision, the revision unit can apply different revision algorithms depending on the category of the text. For example, the revision unit applies a revision algorithm based on product information to a text about a product. The revision unit can also apply a revision algorithm based on service content to a text about a service. Furthermore, the revision unit can apply a revision algorithm based on technical information to a technical text. This allows for more appropriate revision by applying a revision algorithm depending on the category of the text.

[0099] The correction unit can estimate the user's emotion and change the display method of the correction based on the estimated user's emotion. For example, when the user is dissatisfied, the correction unit provides a polite and highly visible display method. In addition, when the user is satisfied, the correction unit can also provide a friendly and casual display method. Furthermore, when the user feels urgency, the correction unit can also provide a quick and concise display method. This allows for more appropriate display by adjusting the display method of the correction according to the user's emotion. The estimation of the emotion 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.

[0100] The correction unit can select the optimal correction method based on the geographical location information of the corrector at the time of correction. The correction unit selects the optimal correction method based on, for example, the geographical location information of the corrector. The correction unit can also make corrections including area-specific information by referring to the geographical location information of the corrector. Furthermore, the correction unit can also make corrections at an appropriate time by taking into account the geographical location information of the corrector. This makes it possible to make corrections including area-specific information by selecting the optimal correction method based on the geographical location information of the corrector.

[0101] When making a correction, the correction unit can analyze the social media activity of the person making the correction and customize the correction content. For example, the correction unit analyzes the comments made by the person making the correction on social media and makes a correction that includes relevant information. The correction unit can also make a correction that includes appropriate information based on the person's social media activity history. Furthermore, the correction unit can also make a correction that includes information of high importance, taking into account the number of followers and influence of the person making the correction on social media. In this way, by analyzing the social media activity of the person making the correction, it is possible to make a correction that includes relevant information.

[0102] The history storage unit can estimate the emotion of the corrector when saving the revision history, and change the saving method based on the estimated emotion. For example, when the corrector is dissatisfied, the history storage unit saves a detailed revision history. Also, when the corrector is satisfied, the history storage unit can save a concise revision history. Furthermore, when the corrector feels urgency, the history storage unit can provide a method for quick saving. This allows more appropriate saving by adjusting the saving method based on the emotion of the corrector. 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.

[0103] When saving the revision history, the history saving unit can adjust the level of detail of the save based on the importance of the revision content. For example, the history saving unit saves a detailed revision history for revision content with high importance. The history saving unit can also save a concise revision history for revision content with low importance. Furthermore, the history saving unit can also save a revision history that includes appropriate information according to the importance of the revision content. In this way, by adjusting the level of detail of the save based on the importance of the revision content, appropriate information can be saved.

[0104] When saving the revision history, the history saving unit can estimate the emotions of the person who corrects the revision, and determine the order of saving based on the estimated emotions. For example, when the person who corrects is dissatisfied, the history saving unit saves the revision history with priority. Also, when the person who corrects is satisfied, the history saving unit can save the revision history with normal priority. Furthermore, when the person who corrects feels urgency, the history saving unit can save the revision history immediately. In this way, important revision histories can be quickly saved by determining the priority of saving based on the emotions of the person who corrects the revision. The estimation of emotions 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.

[0105] When saving the revision history, the history saving unit can select the optimal saving method based on the geographical location information of the corrector. The history saving unit selects the optimal saving method based on, for example, the geographical location information of the corrector. The history saving unit can also save the revision history including area-specific information by referring to the geographical location information of the corrector. Furthermore, the history saving unit can also save the revision history at an appropriate time, taking into account the geographical location information of the corrector. In this way, by selecting the optimal saving method based on the geographical location information of the corrector, it is possible to save the revision history including area-specific information.

[0106] When checking the revised draft, the confirmation unit can estimate the emotions of the confirmer and change the confirmation method based on the estimated emotions. For example, when the confirmer is dissatisfied, the confirmation unit provides a polite and highly visible confirmation method. Furthermore, when the confirmer is satisfied, the confirmation unit can also provide a friendly and casual confirmation method. Furthermore, when the confirmer feels urgency, the confirmation unit can also provide a quick and concise confirmation method. This allows for more appropriate confirmation by adjusting the confirmation method based on the confirmer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0107] When checking the revised draft, the confirmation unit can select the optimal confirmation method by referring to the past confirmation history. The confirmation unit selects the optimal confirmation method based on the past confirmation history, for example. The confirmation unit can also analyze the past confirmation history and select an effective confirmation method. Furthermore, the confirmation unit can also refer to the past confirmation history and perform confirmation at an appropriate time. In this way, the optimal confirmation method can be selected by referring to the past confirmation history.

[0108] When reviewing the revised draft, the verification unit can estimate the reviewer's emotions and determine the order of verification based on the estimated emotions. For example, if the reviewer is dissatisfied, the verification unit performs verification with priority. Also, if the reviewer is satisfied, the verification unit can perform verification with normal priority. Furthermore, if the reviewer feels urgency, the verification unit can perform verification immediately. In this way, important verification can be performed quickly by determining the priority of verification based on the reviewer's emotions. Estimation of emotions 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 (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0109] When checking the revised draft, the confirmation unit can select the optimal confirmation method based on the geographical location information of the confirmer. The confirmation unit selects the optimal confirmation method based on, for example, the geographical location information of the confirmer. The confirmation unit can also refer to the geographical location information of the confirmer and perform confirmation including information specific to the region. Furthermore, the confirmation unit can also perform confirmation at an appropriate time, taking into account the geographical location information of the confirmer. In this way, by selecting the optimal confirmation method based on the geographical location information of the confirmer, confirmation including information specific to the region becomes possible.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The inquiry response system may further include an analysis unit that analyzes the user's past inquiry history and identifies frequent inquiry patterns. The analysis unit, for example, clusters the past inquiry contents and groups similar inquiries. The analysis unit may also identify frequent inquiry patterns and generate templates for efficient processing. Furthermore, the analysis unit may grasp trends in inquiry contents and predict future inquiries. In this way, the efficiency of inquiry response is improved by analyzing the past inquiry history.

[0112] The modification unit may include a priority determination unit that determines the priority of modifications based on the importance of the modification content. For example, the priority determination unit prioritizes modifications to modifications with high importance. The priority determination unit can also perform modifications with normal priority to modifications with low importance. Furthermore, the priority determination unit can also perform modifications immediately depending on the urgency of the modification content. In this way, important modifications can be performed quickly by determining the priority of modifications based on the importance of the modification content.

[0113] When reviewing the revised draft, the reviewing unit can change the reviewing method based on the reviewer's field of expertise. For example, the reviewing unit requests a review from a technical reviewing unit regarding technical content. The reviewing unit can also request a review from a customer service reviewing unit regarding content related to customer service. Furthermore, the reviewing unit can also request a review from a legal reviewing unit regarding content related to legal matters. In this way, by changing the reviewing method based on the reviewing unit's field of expertise, more appropriate review is possible.

[0114] When receiving the inquiry content, the reception unit can give priority to processing related inquiries based on the user's purchase history. For example, the reception unit gives priority to processing inquiries about products that the user has purchased in the past. The reception unit can also analyze the user's purchase history and efficiently process inquiries about related products. Furthermore, the reception unit can automatically classify inquiries about specific products based on the user's purchase history. This allows for efficient response by giving priority to processing related inquiries based on the user's purchase history.

[0115] When generating a draft answer, the generation unit can apply different generation algorithms depending on the category of the inquiry content. For example, the generation unit applies a generation algorithm based on technical information to a technical inquiry. The generation unit can also apply a generation algorithm based on customer service information to an inquiry about customer service. Furthermore, the generation unit can apply a generation algorithm based on legal information to an inquiry about legal matters. In this way, by applying a generation algorithm depending on the category of the inquiry content, a more appropriate draft answer can be generated.

[0116] The reception unit can estimate the user's emotions and determine the priority of the inquiry content based on the estimated user's emotions. For example, when the user is dissatisfied, the reception unit processes the inquiry content with priority. Also, when the user is satisfied, the reception unit can process the inquiry with normal priority. Furthermore, when the user feels urgency, the reception unit can raise the priority to respond immediately. In this way, important inquiries can be quickly processed by determining the priority based on the user's emotions.

[0117] The generation unit can estimate the user's emotions and adjust the expression method of the answer proposal based on the estimated user's emotions. For example, when the user is dissatisfied, the generation unit generates an answer proposal using polite and empathetic expressions. In addition, when the user is satisfied, the generation unit can also generate an answer proposal using friendly and casual expressions. Furthermore, when the user feels urgency, the generation unit can also generate an answer proposal using quick and concise expressions. This allows for a more appropriate answer by adjusting the expression method of the answer proposal according to the user's emotions.

[0118] The transmission unit can estimate the user's emotions and determine the order of proposed messages to be sent based on the estimated user's emotions. For example, when the user is dissatisfied, the transmission unit determines a proposed message to be sent with priority. Also, when the user is satisfied, the transmission unit can determine a proposed message to be sent with normal priority. Furthermore, when the user feels urgency, the transmission unit can determine a proposed message to be sent immediately. In this way, important proposed messages can be sent quickly by determining the priority of proposed messages to be sent based on the user's emotions.

[0119] The correction unit can estimate the user's emotions and determine the priority of corrections based on the estimated user's emotions. For example, when the user is dissatisfied, the correction unit performs corrections with priority. Also, when the user is satisfied, the correction unit can perform corrections with normal priority. Furthermore, when the user feels urgency, the correction unit can perform corrections immediately. In this way, important corrections can be made quickly by determining the priority of corrections based on the user's emotions.

[0120] When reviewing the revised draft, the confirmation unit can estimate the reviewer's emotions and change the confirmation method based on the estimated emotions. For example, when the reviewer is dissatisfied, the confirmation unit can provide a polite and highly visible confirmation method. When the reviewer is satisfied, the confirmation unit can also provide a friendly and casual confirmation method. Furthermore, when the reviewer feels urgency, the confirmation unit can also provide a quick and concise confirmation method. This allows for more appropriate confirmation by adjusting the confirmation method based on the reviewer's emotions.

[0121] The process flow of the second embodiment will be briefly described below.

[0122] Step 1: The reception unit receives the inquiry content. The inquiry content may be in a text format, a voice format, an image format, or the like, but is not limited to these examples. For example, an inquiry in text format is received. Step 2: The generation unit uses a generation AI to analyze the inquiry received by the reception unit and generate a draft response. The generation AI analyzes the inquiry using, for example, a text generation AI (e.g., LLM) and generates an appropriate draft response. For example, in response to the inquiry "Please tell me how to return a product," the generation AI generates a draft response saying, "Please follow the steps below to return the product." Step 3: The sending unit sends the answer draft generated by the generating unit to a registered team member such as a supervisor or a person in charge. The sending unit sends the answer draft using, for example, email or a messaging app. Step 4: The correction unit corrects the answer draft sent by the sending unit. For example, the correction unit can correct a part of the draft or add additional information.

[0123] 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.

[0124] 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 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.

[0125] 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.

[0126] Each of the multiple elements including the above-mentioned reception unit, generation unit, transmission unit, correction unit, and history storage 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 the inquiry content. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response draft using a generation AI. The transmission unit is realized, for example, by the control unit 46A of the smart device 14 and transmits the generated draft to the team members. The correction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and corrects the transmitted draft. The history storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and stores the correction history. The confirmation unit is realized, for example, by the control unit 46A of the smart device 14 and confirms the revised draft again. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements including the above-mentioned reception unit, generation unit, transmission unit, correction unit, and history storage 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 the inquiry content. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response draft using a generation AI. The transmission unit is realized, for example, by the control unit 46A of the smart glasses 214 and transmits the generated draft to the team members. The correction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and corrects the transmitted draft. The history storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and stores the correction history. The confirmation unit is realized, for example, by the control unit 46A of the smart glasses 214 and confirms the revised draft again. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements including the above-mentioned reception unit, generation unit, transmission unit, correction unit, and history storage 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 the inquiry content. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response draft using a generation AI. The transmission unit is realized, for example, by the control unit 46A of the headset type terminal 314 and transmits the generated draft to the team members. The correction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and corrects the transmitted draft. The history storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and stores the correction history. The confirmation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and confirms the revised draft again. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements including the above-mentioned reception unit, generation unit, transmission unit, correction unit, and history storage 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 the inquiry content. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response draft using a generation AI. The transmission unit is realized, for example, by the control unit 46A of the robot 414 and transmits the generated draft to the team members. The correction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and corrects the transmitted draft. The history storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and stores the correction history. The confirmation unit is realized, for example, by the control unit 46A of the robot 414 and confirms the revised draft again. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0176] 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.

[0177] 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.

[0178] These emotions are distributed in the 3 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.

[0179] 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 you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Appendix 1) A reception unit that receives inquiries; a generation unit that analyzes the inquiry content received by the reception unit and generates a draft answer; A sending unit that sends the answer draft generated by the generating unit; A correction unit that corrects the answer draft transmitted by the transmission unit. A system characterized by: (Appendix 2) Equipped with a history storage section that stores revision history 2. The system of claim 1, (Appendix 3) Equipped with a review section to review revised texts again 2. The system of claim 1, (Appendix 4) The reception unit is Accept inquiries in text format 2. The system of claim 1, (Appendix 5) The generation unit is Analyze the inquiry using generative AI and generate a response draft 2. The system of claim 1, (Appendix 6) The transmission unit is Send the generated response draft to your manager or the person in charge's registered team members 2. The system of claim 1, (Appendix 7) The reception unit is Estimate user emotions and prioritize inquiries based on the estimated user emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze past ticket history and automatically categorize similar tickets 2. The system of claim 1, (Appendix 9) The reception unit is When accepting inquiries, filters are performed based on the user's profile information. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the user's emotions and change the way inquiries are accepted based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The reception unit is When accepting inquiries, prioritize inquiries that are more relevant based on the user's geographic location information 2. The system of claim 1, (Appendix 12) The reception unit is When accepting inquiries, analyze users' social media activity and prioritize similar inquiries. 2. The system of claim 1, (Appendix 13) The generation unit is Infer the user's emotions and adjust the way the answer is presented based on the estimated user's emotions 2. The system of claim 1, (Appendix 14) The generation unit is When generating answer templates, adjust the level of detail based on the importance of the inquiry 2. The system of claim 1, (Appendix 15) The generation unit is When generating answer templates, different generation algorithms are applied depending on the category of the inquiry. 2. The system of claim 1, (Appendix 16) The generation unit is Infer the user's emotions and adjust the length of the answer based on the estimated user emotions 2. The system of claim 1, (Appendix 17) The generation unit is When generating response templates, prioritize queries based on when they were submitted 2. The system of claim 1, (Appendix 18) The generation unit is When generating answer templates, improve the accuracy of the templates by referencing related past inquiries 2. The system of claim 1, (Appendix 19) The transmission unit is Estimate the user's emotions and determine the order of text to be sent based on the estimated user emotions 2. The system of claim 1, (Appendix 20) The transmission unit is At the time of sending, customize your send based on the job title or area of ​​expertise of the team member you are sending it to 2. The system of claim 1, (Appendix 21) The transmission unit is When sending, refer to past sending history to select the optimal sending method 2. The system of claim 1, (Appendix 22) The transmission unit is Infer the user's emotions and change the way the text to be sent is displayed based on the estimated user's emotions 2. The system of claim 1, (Appendix 23) The transmission unit is When sending, the optimal sending method is selected based on the geographic location of the destination 2. The system of claim 1, (Appendix 24) The transmission unit is At the time of sending, analyze the recipient's social media activity to customize the content of the send 2. The system of claim 1, (Appendix 25) The correction unit is Inferring user sentiment and prioritizing modifications based on the estimated user sentiment 2. The system of claim 1, (Appendix 26) The correction unit is When making corrections, refer to past correction history to select the optimal correction method. 2. The system of claim 1, (Appendix 27) The correction unit is During revision, different revision algorithms are applied depending on the category of copy 2. The system of claim 1, (Appendix 28) The correction unit is Inferring a user's emotion and changing the way corrections are displayed based on the estimated user's emotion 2. The system of claim 1, (Appendix 29) The correction unit is When making corrections, the most appropriate correction method is selected based on the geographic location information of the corrector. 2. The system of claim 1, (Appendix 30) The correction unit is When making revisions, analyze the social media activity of the person making the revision to customize the revision. 2. The system of claim 1, (Appendix 31) The history storage unit When saving revision history, estimate the sentiment of the person who made the revision and change the saving method based on the estimated sentiment. 3. The system of claim 2, (Appendix 32) The history storage unit When saving revision history, adjust the level of detail saved based on the importance of the revisions 3. The system of claim 2, (Appendix 33) The history storage unit When saving revision history, the sentiment of the person who made the revision is estimated, and the order of saving is determined based on the estimated sentiment. 3. The system of claim 2, (Appendix 34) The history storage unit When saving revision history, the optimal saving method is selected based on the geographic location information of the person who made the revision. 3. The system of claim 2, (Appendix 35) The confirmation unit is When reviewing revised text, estimate the reviewer's sentiment and change the review method based on the estimated sentiment. 4. The system of claim 3. (Appendix 36) The confirmation unit is When reviewing revised text, select the most appropriate review method by referring to past review history 4. The system of claim 3. (Appendix 37) The confirmation unit is When reviewing revised text, estimate reviewers' feelings and decide the review order based on the estimated feelings. 4. The system of claim 3. (Appendix 38) The confirmation unit is When reviewing revised text, the most appropriate review method is selected based on the reviewer's geographic location information. 4. The system of claim 3. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives inquiries; a generation unit that analyzes the inquiry content received by the reception unit and generates a draft answer; A sending unit that sends the answer draft generated by the generating unit; A correction unit that corrects the answer draft transmitted by the transmission unit. A system characterized by:

2. Equipped with a history storage section that stores revision history 2. The system of claim 1 .

3. Equipped with a review section to review revised texts again 2. The system of claim 1 .

4. The reception unit is Accept inquiries in text format 2. The system of claim 1 .

5. The generation unit is Analyze the inquiry using generative AI and generate a response draft 2. The system of claim 1 .

6. The transmission unit is The answer draft generated by the generating unit is sent to the supervisor or the person in charge's registered team members.

2. The system of claim 1 .

7. The reception unit is Estimate user emotions and prioritize inquiries based on the estimated user emotions 2. The system of claim 1 .

8. The reception unit is Analyze past ticket history and automatically categorize similar tickets 2. The system of claim 1 .

9. The reception unit is When accepting inquiries, filters are performed based on the user's profile information.

2. The system of claim 1 .

10. The reception unit is Estimate the user's emotions and change the way inquiries are accepted based on the estimated user emotions 2. The system of claim 1 .

Images