System

Abstract

An object of a system according to an embodiment is to automatically analyze request contents and determine an appropriate escalation destination.SOLUTION: A system includes a request content analysis part, an escalation determination part, and a mail generation part. The request content analysis unit analyzes the request content. The escalation determining unit determines an appropriate escalation destination based on the request content analyzed by the request content analyzing unit. The mail generation part generates request mail contents to the escalation destination determined by the escalation determination part.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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] In conventional technology, analyzing the request content and determining the appropriate escalation destination are done manually, which is inefficient and prone to errors.

[0005] The system according to the embodiment aims to automatically analyze the request content and determine an appropriate escalation destination. [Means for solving the problem]

[0006] The system according to the embodiment includes a request content analysis unit, an escalation determination unit, and an email generation unit. The request content analysis unit analyzes the request content. The escalation determination unit determines an appropriate escalation destination based on the request content analyzed by the request content analysis unit. The email generation unit generates request email content for the escalation destination determined by the escalation determination unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically analyze the request content and determine the appropriate escalation destination. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The business efficiency improvement system according to an embodiment of the present invention is a system that uses a generation AI to improve the efficiency of outsourced business operations. In this system, the generation AI escalates requests that are not of a type for which pre-defined procedures have been prepared, and displays the appropriate escalation destination and the request email content. This enables the business efficiency improvement system to respond quickly and accurately even when the request content is complex.

[0029] A business efficiency improvement system according to an embodiment includes a request content analysis unit, an escalation determination unit, and an email generation unit. The request content analysis unit analyzes the request content. For example, the request content analysis unit uses a generation AI to perform text analysis of the request content and identify the type and content of the request. The request content analysis unit can also analyze the request content using data mining technology. For example, the request content analysis unit can extract patterns of the request content based on past data and obtain analysis results. The request content analysis unit can also analyze the request content using natural language processing technology. For example, the request content analysis unit can understand the context of the request content and obtain appropriate analysis results. The escalation determination unit determines an appropriate escalation destination based on the request content analyzed by the request content analysis unit. For example, the escalation determination unit uses a generation AI to evaluate the urgency and importance of the request content and determine an appropriate escalation destination. The escalation determination unit can also refer to past escalation history to identify the most effective escalation destination. For example, the escalation determination unit determines the optimal escalation destination based on past escalation results. The escalation determination unit can also perform escalation at the optimal timing, taking into account the current workload and schedule of the escalation destination. For example, the escalation determination unit evaluates the workload of the person in charge of the escalation destination and performs escalation at the appropriate timing. The email generation unit generates request email content for the escalation destination determined by the escalation determination unit. For example, the email generation unit generates appropriate email content based on the request content using a generation AI. The email generation unit can also generate optimal email content, taking into account the requester's past communication style and preferences. For example, the email generation unit generates email content using expressions and formats preferred by the requester. The email generation unit can also generate appropriate email content, taking into account legal requirements and regulations related to the request content. For example, the email generation unit generates email content that complies with legal requirements. This enables the business efficiency improvement system according to the embodiment to respond quickly and accurately, even when the request content is complex.For example, generation AI is expected to improve work efficiency and quality by analyzing the content of requests and automatically generating the appropriate escalation destination and request email content.

[0030] The request content analysis unit can evaluate the urgency and importance of the request content by referring to the requester's past history and performance data. For example, when the generation AI determines the request content, the request content analysis unit refers to the requester's past history to evaluate the urgency of the request content. For example, if a similar request has been made in the past, the urgency is determined based on the response results. The request content analysis unit also refers to the requester's performance data to evaluate the importance of the request content. For example, the importance is determined based on the requester's response time and resolution rate. The request content analysis unit also combines the requester's past history and performance data to comprehensively evaluate the urgency and importance of the request content. For example, it determines the priority of the request content based on the past history and performance data. This enables more appropriate escalation by evaluating the urgency and importance of the request content based on the requester's past history and performance data.

[0031] The request content analysis unit can refer to external data related to the request content to understand the background of the request content. For example, when the generation AI judges the request content, the request content analysis unit refers to industry news to understand the background of the request content. For example, it evaluates the importance of the request content based on the latest industry trends. The request content analysis unit also refers to market trends to understand the background of the request content. For example, it evaluates the urgency of the request content based on the market demand and supply situation. The request content analysis unit also comprehensively refers to external data related to the request content to understand the background of the request content. For example, it grasps the overall picture of the request content based on industry news and market trends. In this way, by referring to external data related to the request content, the background of the request content can be understood, enabling more appropriate escalation.

[0032] The request content analysis unit can analyze voice input and image data and make decisions based on multimodal information. For example, when the generation AI judges the content of a request, the request content analysis unit analyzes voice input and evaluates the urgency and importance of the request. For example, it makes a judgment based on the requester's tone of voice and wording. The request content analysis unit also analyzes image data to understand the background of the request. For example, it analyzes images related to the request content and grasps the details of the request. The request content analysis unit also combines voice input and image data to make a comprehensive judgment on the request content. For example, it integrates voice and image information to grasp the overall picture of the request content. This enables more accurate escalation by analyzing voice input and image data and making judgments based on multimodal information.

[0033] The request content analysis unit can improve the accuracy of judgment by referring to data from different industries and fields and utilizing knowledge from different fields. For example, when the generation AI judges the request content, the request content analysis unit refers to data from different industries to improve the accuracy of the judgment. For example, it evaluates the urgency of the request content based on data from the medical industry. The request content analysis unit also utilizes knowledge from different fields to understand the background of the request content. For example, it evaluates the importance of the request content based on data from the technical field. The request content analysis unit also comprehensively refers to data from different industries and fields to improve the accuracy of the judgment. For example, it grasps the overall picture of the request content based on research results and expert opinions from different fields. In this way, the accuracy of judgment can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0034] The escalation determination unit can refer to past escalation history and identify the most effective escalation destination. For example, when the generation AI decides on the escalation destination, the escalation determination unit refers to past escalation history and identifies the most effective escalation destination. For example, if a similar request has been made in the past, the escalation determination unit decides on the escalation destination based on the response results. The escalation determination unit also identifies the optimal escalation destination based on the results of past escalations. For example, it analyzes past escalation history and selects the most effective escalation destination. The escalation determination unit also comprehensively refers to past escalation history and identifies the optimal escalation destination. For example, it evaluates the effectiveness of the escalation destination based on the results of past escalations. In this way, by referring to past escalation history, the most effective escalation destination can be identified, enabling a quick and appropriate response.

[0035] The escalation determination unit can escalate at the optimal timing, taking into account the current workload and schedule of the escalation destination. For example, when the generation AI determines the escalation destination, the escalation determination unit takes into account the current workload of the escalation destination and escalates at the optimal timing. For example, if the person in charge of the escalation destination is busy, it escalates to another person in charge. The escalation determination unit also takes into account the schedule of the escalation destination and escalates at the optimal timing. For example, it checks the schedule of the person in charge of the escalation destination and escalates when they are free. The escalation determination unit also takes into consideration the workload and schedule of the escalation destination overall and escalates at the optimal timing. For example, it escalates when the workload of the person in charge of the escalation destination is reduced. In this way, by taking into account the workload and schedule of the escalation destination, escalation is performed at the optimal timing, enabling efficient response.

[0036] The escalation determination unit can refer to data from different regions and cultural spheres and identify the optimal escalation destination from a global perspective. For example, when the generation AI determines the escalation destination, the escalation determination unit refers to data from different regions and identifies the optimal escalation destination from a global perspective. For example, the escalation destination is determined taking into account the business practices of each region. The escalation determination unit also refers to data from different cultural spheres and identifies the optimal escalation destination. For example, the escalation destination is determined taking into account cultural background and practices. The escalation determination unit also comprehensively refers to data from different regions and cultural spheres and identifies the optimal escalation destination from a global perspective. For example, the escalation destination is determined based on international standards and cross-cultural understanding. This makes it possible to respond internationally by referring to data from different regions and cultural spheres and identifying the optimal escalation destination from a global perspective.

[0037] The escalation determination unit can select the most appropriate person in charge by taking into consideration the expertise and skill set of the escalation destination. For example, when the generation AI decides who to escalate to, the escalation determination unit takes into consideration the expertise of the escalation destination and selects the most appropriate person in charge. For example, it may escalate to a person who is knowledgeable about a particular technology. The escalation determination unit also takes into consideration the skill set of the escalation destination and selects the most appropriate person in charge. For example, it may escalate to a person with programming skills or communication skills. The escalation determination unit also takes into consideration the expertise and skill set of the escalation destination and selects the most appropriate person in charge. For example, it selects the optimal person in charge based on the expertise and skill set. This makes it possible to select the most appropriate person in charge by taking into consideration the expertise and skill set of the escalation destination, enabling an efficient and effective response.

[0038] The email generation unit can generate optimal email content by taking into account the requester's past communication style and preferences. For example, when the generation AI generates the content of a request email, the email generation unit generates optimal email content by taking into account the requester's past communication style. For example, if the requester prefers short sentences, it generates concise email content. The email generation unit also generates optimal email content by taking into account the requester's preferences. For example, if the requester prefers formal expressions, it generates formal email content. The email generation unit also generates optimal email content by comprehensively taking into account the requester's past communication style and preferences. For example, it generates optimal email content based on the requester's preferences and style. In this way, by taking into account the requester's past communication style and preferences, it is possible to generate optimal email content and improve the requester's satisfaction.

[0039] The email generation unit can generate appropriate email content by taking into account legal requirements and regulations related to the request content. For example, when the generation AI generates the request email content, the email generation unit takes into account legal requirements related to the request content and generates appropriate email content. For example, it generates email content that complies with specific laws and regulations. The email generation unit also takes into account regulations related to the request content and generates appropriate email content. For example, it generates email content that complies with industry regulations. The email generation unit also comprehensively takes into account legal requirements and regulations related to the request content and generates appropriate email content. For example, it generates appropriate email content based on legal requirements and regulations. In this way, by taking into account legal requirements and regulations related to the request content, appropriate email content can be generated and legal risks can be avoided.

[0040] The email generation unit automatically translates the content of the request email into different languages ​​and obtains feedback from an international perspective. For example, when the generation AI generates the content of the request email, the email generation unit automatically translates it into different languages ​​and obtains feedback from an international perspective. For example, it translates it into multiple languages ​​such as English, French, and Chinese. The email generation unit also automatically translates the content of the request email and obtains feedback in different languages. For example, it collects opinions from an international perspective based on the translated email content. The email generation unit also automatically translates the content of the request email into different languages ​​and obtains comprehensive feedback from an international perspective. For example, it improves the email content based on feedback in multiple languages. In this way, the quality of the email content can be improved by automatically translating the content of the request email into different languages ​​and obtaining feedback from an international perspective.

[0041] The email generation unit can convert the contents of the request email into a visual note and a mind map, thereby generating email content that is visually easy to understand. For example, when the generation AI generates the contents of the request email, the email generation unit converts it into a visual note, thereby generating email content that is visually easy to understand. For example, important points are indicated with diagrams and icons. The email generation unit also converts the contents of the request email into a mind map, thereby generating email content that is visually easy to understand. For example, the relationships between the contents of the request are visually indicated. The email generation unit also comprehensively converts the contents of the request email into a visual note and a mind map, thereby generating email content that is visually easy to understand. For example, the request content is indicated clearly using diagrams and illustrations. In this way, by converting the contents of the request email into a visual note or a mind map, email content that is visually easy to understand can be generated, thereby promoting the requester's understanding.

[0042] The escalation determination unit can refer to the CSR's past performance data to determine the optimal timing for escalation. For example, when the generation AI escalates from the CSR to the SV, the escalation determination unit refers to the CSR's past performance data to determine the optimal timing for escalation. For example, the escalation timing is determined based on the time the CSR took to process similar requests in the past. The escalation determination unit also determines the optimal timing for escalation based on the CSR's performance data. For example, the escalation timing is determined based on the CSR's response time and resolution rate. The escalation determination unit also comprehensively refers to the CSR's past performance data to determine the optimal timing for escalation. For example, the optimal timing for escalation is determined based on the past performance data. In this way, by referring to the CSR's past performance data, the optimal timing for escalation can be determined, enabling efficient escalation.

[0043] The escalation determination unit takes into account the SV's current workload and schedule and can escalate from the CSR to the SV at the optimal timing. For example, when the generation AI escalates from the CSR to the SV, the escalation determination unit takes into account the SV's current workload and escalates at the optimal timing. For example, if the SV is busy, it escalates to another SV. The escalation determination unit also takes into account the SV's schedule and escalates at the optimal timing. For example, it checks the SV's schedule and escalates when they are free. The escalation determination unit also takes into account the SV's workload and schedule comprehensively and escalates at the optimal timing. For example, it escalates when the SV's workload is reduced. This allows escalation to be performed at the optimal timing by taking into account the SV's workload and schedule, enabling efficient response.

[0044] When escalating from CSR to SV, the escalation decision unit can refer to data from different industries and fields and utilize knowledge from different fields to improve the accuracy of the escalation. For example, when the generation AI escalates from CSR to SV, the escalation decision unit refers to data from different industries to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the medical industry. The escalation decision unit also utilizes knowledge from different fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the technical field. The escalation decision unit also comprehensively refers to data from different industries and fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on research results and expert opinions from different fields. In this way, the accuracy of the escalation can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0045] When escalating from CSR to SV, the escalation decision unit can convert the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, when the generation AI escalates from CSR to SV, the escalation decision unit converts the escalation content into a visual note and displays it in a visually easy-to-understand format. For example, it shows important points using diagrams and icons. The escalation decision unit also converts the escalation content into a mind map and displays it in a visually easy-to-understand format. For example, it visually shows the relationships between the escalation content. The escalation decision unit also comprehensively converts the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, it uses diagrams and illustrations to clearly show the escalation content. By converting the escalation content into a visual note or a mind map, it can be displayed in a visually easy-to-understand format, enabling efficient escalation.

[0046] The escalation determination unit can refer to the SV's past performance data to determine the optimal timing for escalation. For example, when the generation AI escalates from the SV to a managerial employee, the escalation determination unit refers to the SV's past performance data to determine the optimal timing for escalation. For example, the escalation timing is determined based on the time the SV took to process similar requests in the past. The escalation determination unit also determines the optimal timing for escalation based on the SV's performance data. For example, the escalation timing is determined based on the SV's response time and resolution rate. The escalation determination unit also comprehensively refers to the SV's past performance data to determine the optimal timing for escalation. For example, the optimal timing for escalation is determined based on past performance data. In this way, by referring to the SV's past performance data, the optimal timing for escalation can be determined, enabling efficient escalation.

[0047] The escalation determination unit is capable of escalating from the SV to a managerial employee at the optimal timing, taking into account the managerial employee's current workload and schedule. For example, when the generation AI escalates from the SV to a managerial employee, the escalation determination unit takes into account the managerial employee's current workload and escalates at the optimal timing. For example, if a managerial employee is busy, it escalates to another managerial employee. The escalation determination unit also takes into account the managerial employee's schedule and escalates at the optimal timing. For example, it checks the managerial employee's schedule and escalates when they are free. The escalation determination unit also takes into consideration the managerial employee's workload and schedule comprehensively and escalates at the optimal timing. For example, it escalates when the managerial employee's workload is reduced. This allows for escalation at the optimal timing by taking into account the managerial employee's workload and schedule, enabling efficient response.

[0048] When escalating from a supervisor to a manager, the escalation decision unit can refer to data from different industries and fields and utilize knowledge from different fields to improve the accuracy of the escalation. For example, when the generation AI escalates from a supervisor to a manager, the escalation decision unit refers to data from different industries to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the medical industry. The escalation decision unit also utilizes knowledge from different fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the technical field. The escalation decision unit also comprehensively refers to data from different industries and fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on research results and expert opinions from different fields. In this way, the accuracy of the escalation can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0049] When an escalation is made from a supervisor to a manager, the escalation decision unit converts the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, when the generation AI escalates from a supervisor to a manager, the escalation decision unit converts the escalation content into a visual note and displays it in a visually easy-to-understand format. For example, it shows important points using diagrams and icons. The escalation decision unit also converts the escalation content into a mind map and displays it in a visually easy-to-understand format. For example, it visually shows the relationships between the escalation content. The escalation decision unit also comprehensively converts the escalation content into a visual note and a mind map and displays it in a visually easy-to-understand format. For example, it uses diagrams and illustrations to clearly show the escalation content. By converting the escalation content into a visual note or a mind map, it can be displayed in a visually easy-to-understand format, enabling efficient escalation.

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

[0051] The request content analysis unit can refer to social media data related to the request content to understand the background of the request content. For example, when the generation AI judges the request content, the request content analysis unit refers to social media data such as Twitter and Facebook to understand the background of the request content. For example, it evaluates the importance of the request content based on trends and topics on social media. The request content analysis unit also analyzes social media data to evaluate the urgency of the request content. For example, it determines the urgency of the request content based on reactions and comments on social media. The request content analysis unit also comprehensively refers to social media data to understand the background of the request content. For example, it grasps the overall picture of the request content based on the opinions and emotions of users on social media. In this way, by referring to social media data related to the request content, the background of the request content can be understood, enabling more appropriate escalation.

[0052] The escalation determination unit can determine the optimal escalation destination by taking into account the seasonality of the request content. For example, when the generation AI determines the request content, the escalation determination unit determines the optimal escalation destination by taking into account the seasonal workload. For example, if work is concentrated at certain times of the year, such as summer or the end of the year, the escalation determination unit selects an escalation destination that can handle the request at that time. The escalation determination unit also adjusts the schedule of the person in charge of the escalation destination by taking into account seasonality. For example, it selects a person in charge who can handle the request during busy periods. The escalation determination unit also comprehensively considers seasonality to determine the optimal escalation destination. For example, it selects the optimal escalation destination based on the seasonal workload and schedule. This makes it possible to determine the optimal escalation destination by taking into account the seasonality of the request content, enabling efficient response.

[0053] The email generation unit generates visual content related to the request content, and can provide email content that is visually easy to understand. For example, when the generation AI generates the request email content, the email generation unit generates graphs and charts related to the request content, and provides email content that is visually easy to understand. For example, the progress of the request content is shown in a graph. The email generation unit also generates images and videos related to the request content, and provides email content that is visually easy to understand. For example, the steps of the request content are shown in a video. The email generation unit also comprehensively generates visual content related to the request content, and provides email content that is visually easy to understand. For example, the request content is shown in an easy-to-understand manner by combining graphs, charts, images, and videos. In this way, by generating visual content related to the request content, email content that is visually easy to understand can be provided, and the requester's understanding can be promoted.

[0054] The escalation decision unit performs a risk assessment of the request content and is able to prioritize escalating requests with high risk. For example, when the generation AI judges the request content, the escalation decision unit performs a risk assessment and prioritizes escalating requests with high risk. For example, if the request content involves legal risk, it will process that request with priority. The escalation decision unit also performs a risk assessment of the request content and identifies requests with high risk. For example, if the request content will affect customer satisfaction, it will process that request promptly. The escalation decision unit also performs a comprehensive risk assessment of the request content and prioritizes escalating requests with high risk. For example, it determines the priority of requests based on the type and degree of risk in the request content. This enables a prompt and appropriate response by performing a risk assessment of the request content and prioritizing escalating requests with high risk.

[0055] The request content analysis unit can analyze legal documents related to the request content and evaluate legal risks. For example, when the generation AI judges the request content, the request content analysis unit analyzes legal documents and evaluates legal risks. For example, it analyzes contracts and regulations to check whether the request content is legally problematic. The request content analysis unit also analyzes legal documents and identifies the legal risks of the request content. For example, it checks whether the request content violates specific laws and regulations. The request content analysis unit also comprehensively analyzes legal documents and evaluates the legal risks of the request content. For example, it makes a comprehensive judgment on the legal risks of the request content based on multiple legal documents. This makes it possible to evaluate legal risks and escalate more appropriately by analyzing legal documents related to the request content.

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

[0057] Step 1: The request content analysis unit analyzes the request content. For example, it uses generation AI to perform text analysis of the request content and identify the type and content of the request. It can also use data mining technology to extract patterns in the request content from past data and obtain analysis results. It can also use natural language processing technology to understand the context of the request content and obtain appropriate analysis results. Step 2: The escalation decision unit determines the appropriate escalation destination based on the request content analyzed by the request content analysis unit. For example, it uses generation AI to evaluate the urgency and importance of the request content and determines the appropriate escalation destination. It can also refer to past escalation history to identify the most effective escalation destination. It can also escalate at the optimal time, taking into account the current workload and schedule of the escalation destination. Step 3: The email generation unit generates the content of the request email to the escalation destination determined by the escalation determination unit. For example, it uses generation AI to generate appropriate email content based on the request content. It can also generate optimal email content by taking into account the requester's past communication style and preferences. It can also generate appropriate email content by taking into account legal requirements and regulations related to the request content.

[0058] (Example 2) The business efficiency improvement system according to an embodiment of the present invention is a system that uses a generation AI to improve the efficiency of outsourced business operations. In this system, the generation AI escalates requests that are not of a type for which pre-defined procedures have been prepared, and displays the appropriate escalation destination and the request email content. This enables the business efficiency improvement system to respond quickly and accurately even when the request content is complex.

[0059] A business efficiency improvement system according to an embodiment includes a request content analysis unit, an escalation determination unit, and an email generation unit. The request content analysis unit analyzes the request content. For example, the request content analysis unit uses a generation AI to perform text analysis of the request content and identify the type and content of the request. The request content analysis unit can also analyze the request content using data mining technology. For example, the request content analysis unit can extract patterns of the request content based on past data and obtain analysis results. The request content analysis unit can also analyze the request content using natural language processing technology. For example, the request content analysis unit can understand the context of the request content and obtain appropriate analysis results. The escalation determination unit determines an appropriate escalation destination based on the request content analyzed by the request content analysis unit. For example, the escalation determination unit uses a generation AI to evaluate the urgency and importance of the request content and determine an appropriate escalation destination. The escalation determination unit can also refer to past escalation history to identify the most effective escalation destination. For example, the escalation determination unit determines the optimal escalation destination based on past escalation results. The escalation determination unit can also perform escalation at the optimal timing, taking into account the current workload and schedule of the escalation destination. For example, the escalation determination unit evaluates the workload of the person in charge of the escalation destination and performs escalation at the appropriate timing. The email generation unit generates request email content for the escalation destination determined by the escalation determination unit. For example, the email generation unit generates appropriate email content based on the request content using a generation AI. The email generation unit can also generate optimal email content, taking into account the requester's past communication style and preferences. For example, the email generation unit generates email content using expressions and formats preferred by the requester. The email generation unit can also generate appropriate email content, taking into account legal requirements and regulations related to the request content. For example, the email generation unit generates email content that complies with legal requirements. This enables the business efficiency improvement system according to the embodiment to respond quickly and accurately, even when the request content is complex.For example, generation AI is expected to improve work efficiency and quality by analyzing the content of requests and automatically generating the appropriate escalation destination and request email content.

[0060] The request content analysis unit can evaluate the urgency and importance of the request content by referring to the requester's past history and performance data. For example, when the generation AI determines the request content, the request content analysis unit refers to the requester's past history to evaluate the urgency of the request content. For example, if a similar request has been made in the past, the urgency is determined based on the response results. The request content analysis unit also refers to the requester's performance data to evaluate the importance of the request content. For example, the importance is determined based on the requester's response time and resolution rate. The request content analysis unit also combines the requester's past history and performance data to comprehensively evaluate the urgency and importance of the request content. For example, it determines the priority of the request content based on the past history and performance data. This enables more appropriate escalation by evaluating the urgency and importance of the request content based on the requester's past history and performance data.

[0061] The request content analysis unit can refer to external data related to the request content to understand the background of the request content. For example, when the generation AI judges the request content, the request content analysis unit refers to industry news to understand the background of the request content. For example, it evaluates the importance of the request content based on the latest industry trends. The request content analysis unit also refers to market trends to understand the background of the request content. For example, it evaluates the urgency of the request content based on the market demand and supply situation. The request content analysis unit also comprehensively refers to external data related to the request content to understand the background of the request content. For example, it grasps the overall picture of the request content based on industry news and market trends. In this way, by referring to external data related to the request content, the background of the request content can be understood, enabling more appropriate escalation.

[0062] The request content analysis unit can analyze the emotions of the requester using the emotion estimation function and prioritize escalating emotionally important requests. For example, when the generation AI determines the content of a request, the request content analysis unit uses the emotion estimation function to analyze the emotions of the requester and prioritize escalating emotionally important requests. For example, if the requester is feeling strong anxiety, the request is processed with priority. The request content analysis unit also analyzes the emotions of the requester and identifies emotionally important requests. For example, if the requester is feeling anger, the request is processed promptly. The request content analysis unit also comprehensively analyzes the emotions of the requester and prioritizes escalating emotionally important requests. For example, it determines the priority of requests based on the strength and type of the requester's emotion. This enables a prompt and appropriate response by analyzing the emotions of the requester and prioritize escalating emotionally important requests.

[0063] The request content analysis unit can analyze voice input and image data and make decisions based on multimodal information. For example, when the generation AI judges the content of a request, the request content analysis unit analyzes voice input and evaluates the urgency and importance of the request. For example, it makes a judgment based on the requester's tone of voice and wording. The request content analysis unit also analyzes image data to understand the background of the request. For example, it analyzes images related to the request content and grasps the details of the request. The request content analysis unit also combines voice input and image data to make a comprehensive judgment on the request content. For example, it integrates voice and image information to grasp the overall picture of the request content. This enables more accurate escalation by analyzing voice input and image data and making judgments based on multimodal information.

[0064] The request content analysis unit can improve the accuracy of judgment by referring to data from different industries and fields and utilizing knowledge from different fields. For example, when the generation AI judges the request content, the request content analysis unit refers to data from different industries to improve the accuracy of the judgment. For example, it evaluates the urgency of the request content based on data from the medical industry. The request content analysis unit also utilizes knowledge from different fields to understand the background of the request content. For example, it evaluates the importance of the request content based on data from the technical field. The request content analysis unit also comprehensively refers to data from different industries and fields to improve the accuracy of the judgment. For example, it grasps the overall picture of the request content based on research results and expert opinions from different fields. In this way, the accuracy of judgment can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0065] The request content analysis unit uses the emotion estimation function to analyze the emotions of the requester when they enter their request in real time, and can make suggestions that elicit positive emotions. For example, when the generation AI judges the request content, the request content analysis unit uses the emotion estimation function to analyze the emotion of the requester in real time, and makes suggestions that elicit positive emotions. For example, if the requester is feeling anxious, it makes suggestions that give the requester a sense of security. The request content analysis unit also analyzes the emotion of the requester in real time and provides appropriate feedback. For example, if the requester is feeling stressed, it makes suggestions that will help the requester relax. The request content analysis unit also comprehensively analyzes the emotion of the requester and makes suggestions that elicit positive emotions. For example, it makes appropriate suggestions based on changes in the emotion of the requester. In this way, by analyzing the emotion of the requester in real time and making suggestions that elicit positive emotions, it is possible to improve the satisfaction of the requester.

[0066] The escalation determination unit can refer to past escalation history and identify the most effective escalation destination. For example, when the generation AI decides on the escalation destination, the escalation determination unit refers to past escalation history and identifies the most effective escalation destination. For example, if a similar request has been made in the past, the escalation determination unit decides on the escalation destination based on the response results. The escalation determination unit also identifies the optimal escalation destination based on the results of past escalations. For example, it analyzes past escalation history and selects the most effective escalation destination. The escalation determination unit also comprehensively refers to past escalation history and identifies the optimal escalation destination. For example, it evaluates the effectiveness of the escalation destination based on the results of past escalations. In this way, by referring to past escalation history, the most effective escalation destination can be identified, enabling a quick and appropriate response.

[0067] The escalation determination unit can escalate at the optimal timing, taking into account the current workload and schedule of the escalation destination. For example, when the generation AI determines the escalation destination, the escalation determination unit takes into account the current workload of the escalation destination and escalates at the optimal timing. For example, if the person in charge of the escalation destination is busy, it escalates to another person in charge. The escalation determination unit also takes into account the schedule of the escalation destination and escalates at the optimal timing. For example, it checks the schedule of the person in charge of the escalation destination and escalates when they are free. The escalation determination unit also takes into consideration the workload and schedule of the escalation destination overall and escalates at the optimal timing. For example, it escalates when the workload of the person in charge of the escalation destination is reduced. In this way, by taking into account the workload and schedule of the escalation destination, escalation is performed at the optimal timing, enabling efficient response.

[0068] The escalation determination unit can use the emotion estimation function to analyze the emotional state of the person at the escalation destination and select the most appropriate person. For example, when the generation AI determines the escalation destination, the escalation determination unit uses the emotion estimation function to analyze the emotional state of the person at the escalation destination and select the most appropriate person. For example, if the person is feeling stressed, the escalation determination unit escalates to another person. The escalation determination unit also comprehensively analyzes the emotional state of the person at the escalation destination and selects the most appropriate person. For example, it selects the optimal person based on the person's emotional state. The escalation determination unit also uses the emotion estimation function to analyze the emotional state of the person at the escalation destination in real time and select the most appropriate person. For example, if the person's emotional state changes, the escalation destination is changed at the appropriate time. This enables an efficient and effective response by analyzing the emotional state of the person at the escalation destination and selecting the most appropriate person.

[0069] The escalation determination unit can refer to data from different regions and cultural spheres and identify the optimal escalation destination from a global perspective. For example, when the generation AI determines the escalation destination, the escalation determination unit refers to data from different regions and identifies the optimal escalation destination from a global perspective. For example, the escalation destination is determined taking into account the business practices of each region. The escalation determination unit also refers to data from different cultural spheres and identifies the optimal escalation destination. For example, the escalation destination is determined taking into account cultural background and practices. The escalation determination unit also comprehensively refers to data from different regions and cultural spheres and identifies the optimal escalation destination from a global perspective. For example, the escalation destination is determined based on international standards and cross-cultural understanding. This makes it possible to respond internationally by referring to data from different regions and cultural spheres and identifying the optimal escalation destination from a global perspective.

[0070] The escalation determination unit can select the most appropriate person in charge by taking into consideration the expertise and skill set of the escalation destination. For example, when the generation AI decides who to escalate to, the escalation determination unit takes into consideration the expertise of the escalation destination and selects the most appropriate person in charge. For example, it may escalate to a person who is knowledgeable about a particular technology. The escalation determination unit also takes into consideration the skill set of the escalation destination and selects the most appropriate person in charge. For example, it may escalate to a person with programming skills or communication skills. The escalation determination unit also takes into consideration the expertise and skill set of the escalation destination and selects the most appropriate person in charge. For example, it selects the optimal person in charge based on the expertise and skill set. This makes it possible to select the most appropriate person in charge by taking into consideration the expertise and skill set of the escalation destination, enabling an efficient and effective response.

[0071] The escalation determination unit can use the emotion estimation function to predict the emotional response of the person at the escalation destination and select the person at the escalation destination who will elicit the most positive response. For example, when the generation AI determines the escalation destination, the escalation determination unit uses the emotion estimation function to predict the emotional response of the person at the escalation destination and selects the person at the escalation destination who will elicit the most positive response. For example, if the person at the escalation destination is relaxed, the escalation determination unit will escalate to that person. The escalation determination unit also comprehensively predicts the emotional response of the person at the escalation destination and selects the person at the escalation destination who will elicit the most positive response. For example, it selects the most suitable person based on the person's emotional state. The escalation determination unit also uses the emotion estimation function to predict the emotional response of the person at the escalation destination in real time and selects the person at the escalation destination who will elicit the most positive response. For example, if the person's emotional state changes, the escalation destination is changed at the appropriate time. This enables efficient and effective response by predicting the emotional response of the person at the escalation destination and selecting the person at the escalation destination who will elicit the most positive response.

[0072] The email generation unit can generate optimal email content by taking into account the requester's past communication style and preferences. For example, when the generation AI generates the content of a request email, the email generation unit generates optimal email content by taking into account the requester's past communication style. For example, if the requester prefers short sentences, it generates concise email content. The email generation unit also generates optimal email content by taking into account the requester's preferences. For example, if the requester prefers formal expressions, it generates formal email content. The email generation unit also generates optimal email content by comprehensively taking into account the requester's past communication style and preferences. For example, it generates optimal email content based on the requester's preferences and style. In this way, by taking into account the requester's past communication style and preferences, it is possible to generate optimal email content and improve the requester's satisfaction.

[0073] The email generation unit can generate appropriate email content by taking into account legal requirements and regulations related to the request content. For example, when the generation AI generates the request email content, the email generation unit takes into account legal requirements related to the request content and generates appropriate email content. For example, it generates email content that complies with specific laws and regulations. The email generation unit also takes into account regulations related to the request content and generates appropriate email content. For example, it generates email content that complies with industry regulations. The email generation unit also comprehensively takes into account legal requirements and regulations related to the request content and generates appropriate email content. For example, it generates appropriate email content based on legal requirements and regulations. In this way, by taking into account legal requirements and regulations related to the request content, appropriate email content can be generated and legal risks can be avoided.

[0074] The email generation unit can analyze the client's emotions using the emotion estimation function and generate email content that is likely to resonate emotionally. For example, when the generation AI generates the content of a request email, the email generation unit uses the emotion estimation function to analyze the client's emotions and generate email content that is likely to resonate emotionally. For example, if the client is feeling anxious, the email generation unit generates email content that gives a sense of security. The email generation unit also analyzes the client's emotions and generates email content that is likely to resonate emotionally. For example, if the client is feeling happy, the email generation unit generates email content that shares that emotion. The email generation unit also comprehensively analyzes the client's emotions and generates email content that is likely to resonate emotionally. For example, email content that elicits empathy is generated based on the strength and type of the client's emotions. In this way, by analyzing the client's emotions and generating email content that is likely to resonate emotionally, the client's satisfaction can be improved.

[0075] The email generation unit automatically translates the content of the request email into different languages ​​and obtains feedback from an international perspective. For example, when the generation AI generates the content of the request email, the email generation unit automatically translates it into different languages ​​and obtains feedback from an international perspective. For example, it translates it into multiple languages ​​such as English, French, and Chinese. The email generation unit also automatically translates the content of the request email and obtains feedback in different languages. For example, it collects opinions from an international perspective based on the translated email content. The email generation unit also automatically translates the content of the request email into different languages ​​and obtains comprehensive feedback from an international perspective. For example, it improves the email content based on feedback in multiple languages. In this way, the quality of the email content can be improved by automatically translating the content of the request email into different languages ​​and obtaining feedback from an international perspective.

[0076] The email generation unit can convert the contents of the request email into a visual note and a mind map, thereby generating email content that is visually easy to understand. For example, when the generation AI generates the contents of the request email, the email generation unit converts it into a visual note, thereby generating email content that is visually easy to understand. For example, important points are indicated with diagrams and icons. The email generation unit also converts the contents of the request email into a mind map, thereby generating email content that is visually easy to understand. For example, the relationships between the contents of the request are visually indicated. The email generation unit also comprehensively converts the contents of the request email into a visual note and a mind map, thereby generating email content that is visually easy to understand. For example, the request content is indicated clearly using diagrams and illustrations. In this way, by converting the contents of the request email into a visual note or a mind map, email content that is visually easy to understand can be generated, thereby promoting the requester's understanding.

[0077] The email generation unit can use the emotion estimation function to predict the recipient's emotional response to the request email content and generate email content that will elicit the most positive response. For example, when the generation AI generates the request email content, the email generation unit uses the emotion estimation function to predict the recipient's emotional response and generates email content that will elicit the most positive response. For example, it uses expressions that make the recipient feel happy. The email generation unit also predicts the recipient's emotional response and generates email content that will elicit the most positive response. For example, it uses expressions that make the recipient feel reassured. The email generation unit also comprehensively predicts the recipient's emotional response and generates email content that will elicit the most positive response. For example, it generates optimal email content based on the recipient's emotional state. In this way, it is possible to predict the recipient's emotional response to the request email content and generate email content that will elicit the most positive response, thereby improving recipient satisfaction.

[0078] The escalation determination unit can refer to the CSR's past performance data to determine the optimal timing for escalation. For example, when the generation AI escalates from the CSR to the SV, the escalation determination unit refers to the CSR's past performance data to determine the optimal timing for escalation. For example, the escalation timing is determined based on the time the CSR took to process similar requests in the past. The escalation determination unit also determines the optimal timing for escalation based on the CSR's performance data. For example, the escalation timing is determined based on the CSR's response time and resolution rate. The escalation determination unit also comprehensively refers to the CSR's past performance data to determine the optimal timing for escalation. For example, the optimal timing for escalation is determined based on the past performance data. In this way, by referring to the CSR's past performance data, the optimal timing for escalation can be determined, enabling efficient escalation.

[0079] The escalation determination unit takes into account the SV's current workload and schedule and can escalate from the CSR to the SV at the optimal timing. For example, when the generation AI escalates from the CSR to the SV, the escalation determination unit takes into account the SV's current workload and escalates at the optimal timing. For example, if the SV is busy, it escalates to another SV. The escalation determination unit also takes into account the SV's schedule and escalates at the optimal timing. For example, it checks the SV's schedule and escalates when they are free. The escalation determination unit also takes into account the SV's workload and schedule comprehensively and escalates at the optimal timing. For example, it escalates when the SV's workload is reduced. This allows escalation to be performed at the optimal timing by taking into account the SV's workload and schedule, enabling efficient response.

[0080] The escalation decision unit uses the emotion estimation function to analyze the emotional states of the CSR and SV and escalate at the most appropriate timing. For example, when the generation AI escalates from the CSR to the SV, the escalation decision unit uses the emotion estimation function to analyze the emotional states of the CSR and SV and escalates at the most appropriate timing. For example, if the CSR is feeling stressed, it escalates to another CSR. The escalation decision unit also analyzes the emotional state of the SV and escalates at the most appropriate timing. For example, if the SV is relaxed, it escalates at that timing. The escalation decision unit also comprehensively analyzes the emotional states of the CSR and SV and escalates at the most appropriate timing. For example, it determines the optimal timing for escalation based on the emotional states of the CSR and SV. This enables efficient and effective responses by analyzing the emotional states of the CSR and SV and escalating at the most appropriate timing.

[0081] When escalating from CSR to SV, the escalation decision unit can refer to data from different industries and fields and utilize knowledge from different fields to improve the accuracy of the escalation. For example, when the generation AI escalates from CSR to SV, the escalation decision unit refers to data from different industries to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the medical industry. The escalation decision unit also utilizes knowledge from different fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the technical field. The escalation decision unit also comprehensively refers to data from different industries and fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on research results and expert opinions from different fields. In this way, the accuracy of the escalation can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0082] When escalating from CSR to SV, the escalation decision unit can convert the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, when the generation AI escalates from CSR to SV, the escalation decision unit converts the escalation content into a visual note and displays it in a visually easy-to-understand format. For example, it shows important points using diagrams and icons. The escalation decision unit also converts the escalation content into a mind map and displays it in a visually easy-to-understand format. For example, it visually shows the relationships between the escalation content. The escalation decision unit also comprehensively converts the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, it uses diagrams and illustrations to clearly show the escalation content. By converting the escalation content into a visual note or a mind map, it can be displayed in a visually easy-to-understand format, enabling efficient escalation.

[0083] The escalation determination unit can use the emotion estimation function to predict the emotional reactions of the CSR and SV and generate escalation content that will elicit the most positive reaction. For example, when the generation AI escalates from the CSR to the SV, the escalation determination unit uses the emotion estimation function to predict the emotional reactions of the CSR and SV and generates escalation content that will elicit the most positive reaction. For example, it uses expressions that make the CSR feel at ease. The escalation determination unit also predicts the emotional reaction of the SV and generates escalation content that will elicit the most positive reaction. For example, if the SV is relaxed, it escalates at that time. The escalation determination unit also comprehensively predicts the emotional reactions of the CSR and SV and generates escalation content that will elicit the most positive reaction. For example, it determines the optimal escalation content based on the emotional states of the CSR and SV. This enables efficient and effective responses by predicting the emotional reactions of the CSR and SV and generating escalation content that will elicit the most positive reaction.

[0084] The escalation determination unit can refer to the SV's past performance data to determine the optimal timing for escalation. For example, when the generation AI escalates from the SV to a managerial employee, the escalation determination unit refers to the SV's past performance data to determine the optimal timing for escalation. For example, the escalation timing is determined based on the time the SV took to process similar requests in the past. The escalation determination unit also determines the optimal timing for escalation based on the SV's performance data. For example, the escalation timing is determined based on the SV's response time and resolution rate. The escalation determination unit also comprehensively refers to the SV's past performance data to determine the optimal timing for escalation. For example, the optimal timing for escalation is determined based on past performance data. In this way, by referring to the SV's past performance data, the optimal timing for escalation can be determined, enabling efficient escalation.

[0085] The escalation determination unit is capable of escalating from the SV to a managerial employee at the optimal timing, taking into account the managerial employee's current workload and schedule. For example, when the generation AI escalates from the SV to a managerial employee, the escalation determination unit takes into account the managerial employee's current workload and escalates at the optimal timing. For example, if a managerial employee is busy, it escalates to another managerial employee. The escalation determination unit also takes into account the managerial employee's schedule and escalates at the optimal timing. For example, it checks the managerial employee's schedule and escalates when they are free. The escalation determination unit also takes into consideration the managerial employee's workload and schedule comprehensively and escalates at the optimal timing. For example, it escalates when the managerial employee's workload is reduced. This allows for escalation at the optimal timing by taking into account the managerial employee's workload and schedule, enabling efficient response.

[0086] The escalation decision unit uses the emotion estimation function to analyze the emotional states of the supervisor and managerial staff and escalate at the most appropriate time. For example, when the generation AI escalates from the supervisor to a manager, the escalation decision unit uses the emotion estimation function to analyze the emotional states of the supervisor and managerial staff and escalate at the most appropriate time. For example, if the supervisor is feeling stressed, it will escalate to another supervisor. The escalation decision unit also analyzes the emotional state of the managerial staff and escalates at the most appropriate time. For example, if the managerial staff is relaxed, it will escalate at that time. The escalation decision unit also comprehensively analyzes the emotional states of the supervisor and managerial staff and escalates at the most appropriate time. For example, it determines the optimal timing for escalation based on the emotional states of the supervisor and managerial staff. This enables efficient and effective responses by analyzing the emotional states of the supervisor and managerial staff and escalating at the most appropriate time.

[0087] When escalating from a supervisor to a manager, the escalation decision unit can refer to data from different industries and fields and utilize knowledge from different fields to improve the accuracy of the escalation. For example, when the generation AI escalates from a supervisor to a manager, the escalation decision unit refers to data from different industries to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the medical industry. The escalation decision unit also utilizes knowledge from different fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on data from the technical field. The escalation decision unit also comprehensively refers to data from different industries and fields to improve the accuracy of the escalation. For example, it determines the content of the escalation based on research results and expert opinions from different fields. In this way, the accuracy of the escalation can be improved by referring to data from different industries and fields and utilizing knowledge from different fields.

[0088] When an escalation is made from a supervisor to a manager, the escalation decision unit converts the escalation content into a visual note and a mind map, displaying it in a visually easy-to-understand format. For example, when the generation AI escalates from a supervisor to a manager, the escalation decision unit converts the escalation content into a visual note and displays it in a visually easy-to-understand format. For example, it shows important points using diagrams and icons. The escalation decision unit also converts the escalation content into a mind map and displays it in a visually easy-to-understand format. For example, it visually shows the relationships between the escalation content. The escalation decision unit also comprehensively converts the escalation content into a visual note and a mind map and displays it in a visually easy-to-understand format. For example, it uses diagrams and illustrations to clearly show the escalation content. By converting the escalation content into a visual note or a mind map, it can be displayed in a visually easy-to-understand format, enabling efficient escalation.

[0089] The escalation determination unit can use the emotion estimation function to predict the emotional reactions of the supervisor and manager and generate escalation content that will elicit the most positive reaction. For example, when the generation AI escalates from the supervisor to a manager, the escalation determination unit uses the emotion estimation function to predict the emotional reactions of the supervisor and manager and generates escalation content that will elicit the most positive reaction. For example, it uses expressions that make the supervisor feel at ease. The escalation determination unit also predicts the emotional reaction of the manager and generates escalation content that will elicit the most positive reaction. For example, if the manager is relaxed, it escalates at that time. The escalation determination unit also comprehensively predicts the emotional reactions of the supervisor and manager and generates escalation content that will elicit the most positive reaction. For example, it determines the optimal escalation content based on the emotional states of the supervisor and manager. This enables efficient and effective responses by predicting the emotional reactions of the supervisor and manager and generating escalation content that will elicit the most positive reaction.

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

[0091] The request content analysis unit can refer to social media data related to the request content to understand the background of the request content. For example, when the generation AI judges the request content, the request content analysis unit refers to social media data such as Twitter and Facebook to understand the background of the request content. For example, it evaluates the importance of the request content based on trends and topics on social media. The request content analysis unit also analyzes social media data to evaluate the urgency of the request content. For example, it determines the urgency of the request content based on reactions and comments on social media. The request content analysis unit also comprehensively refers to social media data to understand the background of the request content. For example, it grasps the overall picture of the request content based on the opinions and emotions of users on social media. In this way, by referring to social media data related to the request content, the background of the request content can be understood, enabling more appropriate escalation.

[0092] The escalation determination unit can determine the optimal escalation destination by taking into account the seasonality of the request content. For example, when the generation AI determines the request content, the escalation determination unit determines the optimal escalation destination by taking into account the seasonal workload. For example, if work is concentrated at certain times of the year, such as summer or the end of the year, the escalation determination unit selects an escalation destination that can handle the request at that time. The escalation determination unit also adjusts the schedule of the person in charge of the escalation destination by taking into account seasonality. For example, it selects a person in charge who can handle the request during busy periods. The escalation determination unit also comprehensively considers seasonality to determine the optimal escalation destination. For example, it selects the optimal escalation destination based on the seasonal workload and schedule. This makes it possible to determine the optimal escalation destination by taking into account the seasonality of the request content, enabling efficient response.

[0093] The email generation unit generates visual content related to the request content, and can provide email content that is visually easy to understand. For example, when the generation AI generates the request email content, the email generation unit generates graphs and charts related to the request content, and provides email content that is visually easy to understand. For example, the progress of the request content is shown in a graph. The email generation unit also generates images and videos related to the request content, and provides email content that is visually easy to understand. For example, the steps of the request content are shown in a video. The email generation unit also comprehensively generates visual content related to the request content, and provides email content that is visually easy to understand. For example, the request content is shown in an easy-to-understand manner by combining graphs, charts, images, and videos. In this way, by generating visual content related to the request content, email content that is visually easy to understand can be provided, and the requester's understanding can be promoted.

[0094] The escalation decision unit performs a risk assessment of the request content and is able to prioritize escalating requests with high risk. For example, when the generation AI judges the request content, the escalation decision unit performs a risk assessment and prioritizes escalating requests with high risk. For example, if the request content involves legal risk, it will process that request with priority. The escalation decision unit also performs a risk assessment of the request content and identifies requests with high risk. For example, if the request content will affect customer satisfaction, it will process that request promptly. The escalation decision unit also performs a comprehensive risk assessment of the request content and prioritizes escalating requests with high risk. For example, it determines the priority of requests based on the type and degree of risk in the request content. This enables a prompt and appropriate response by performing a risk assessment of the request content and prioritizing escalating requests with high risk.

[0095] The request content analysis unit can analyze legal documents related to the request content and evaluate legal risks. For example, when the generation AI judges the request content, the request content analysis unit analyzes legal documents and evaluates legal risks. For example, it analyzes contracts and regulations to check whether the request content is legally problematic. The request content analysis unit also analyzes legal documents and identifies the legal risks of the request content. For example, it checks whether the request content violates specific laws and regulations. The request content analysis unit also comprehensively analyzes legal documents and evaluates the legal risks of the request content. For example, it makes a comprehensive judgment on the legal risks of the request content based on multiple legal documents. This makes it possible to evaluate legal risks and escalate more appropriately by analyzing legal documents related to the request content.

[0096] The escalation determination unit can analyze the emotions of the requester using the emotion estimation function and prioritize escalating emotionally important requests. For example, when the generation AI determines the content of a request, the escalation determination unit uses the emotion estimation function to analyze the emotions of the requester and prioritize escalating emotionally important requests. For example, if the requester is feeling strong anxiety, the escalation determination unit will prioritize processing that request. The escalation determination unit also analyzes the emotions of the requester and identifies emotionally important requests. For example, if the requester is feeling anger, the escalation determination unit will quickly process that request. The escalation determination unit also comprehensively analyzes the emotions of the requester and prioritizes escalating emotionally important requests. For example, it determines the priority of requests based on the strength and type of the requester's emotion. This enables a quick and appropriate response by analyzing the emotions of the requester and prioritize escalating emotionally important requests.

[0097] The email generation unit can use the emotion estimation function to analyze the client's emotions and generate email content that is easy to empathize with emotionally. For example, when the generation AI generates the content of a request email, the email generation unit uses the emotion estimation function to analyze the client's emotions and generate email content that is easy to empathize with emotionally. For example, if the client is feeling anxious, the email generation unit generates email content that gives a sense of security. The email generation unit also analyzes the client's emotions and generates email content that is easy to empathize with emotionally. For example, if the client is feeling happy, the email generation unit generates email content that shares that emotion. The email generation unit also comprehensively analyzes the client's emotions and generates email content that is easy to empathize with emotionally. For example, email content that elicits empathy is generated based on the strength and type of the client's emotion. In this way, by analyzing the client's emotions and generating email content that is easy to empathize with emotionally, the client's satisfaction can be improved.

[0098] The escalation decision unit can use the emotion estimation function to analyze the emotional state of the person at the escalation destination and select the most appropriate person. For example, when the generation AI decides who to escalate to, the escalation decision unit uses the emotion estimation function to analyze the emotional state of the person at the escalation destination and select the most appropriate person. For example, if the person is feeling stressed, it escalates to another person. The escalation decision unit also comprehensively analyzes the emotional state of the person at the escalation destination and selects the most appropriate person. For example, it selects the optimal person based on the person's emotional state. The escalation decision unit also uses the emotion estimation function to analyze the emotional state of the person at the escalation destination in real time and select the most appropriate person. For example, if the person's emotional state changes, it changes the escalation destination at the appropriate time. This enables an efficient and effective response by analyzing the emotional state of the person at the escalation destination and selecting the most appropriate person.

[0099] The escalation determination unit can use the emotion estimation function to predict the emotional response of the escalation destination agent and select the escalation destination that will elicit the most positive response. For example, when the generation AI determines the escalation destination, the escalation determination unit uses the emotion estimation function to predict the emotional response of the escalation destination agent and selects the agent who will elicit the most positive response. For example, if the agent is relaxed, the escalation determination unit will escalate to that agent. The escalation determination unit also comprehensively predicts the emotional response of the escalation destination agent and selects the agent who will elicit the most positive response. For example, it selects the most suitable agent based on the agent's emotional state. The escalation determination unit also uses the emotion estimation function to predict the emotional response of the escalation destination agent in real time and selects the agent who will elicit the most positive response. For example, if the agent's emotional state changes, the escalation destination is changed at the appropriate time. This enables efficient and effective response by predicting the emotional response of the escalation destination agent and selecting the escalation destination that will elicit the most positive response.

[0100] The email generation unit can use the emotion estimation function to predict the recipient's emotional response to the request email content and generate email content that will elicit the most positive response. For example, when the generation AI generates the request email content, the email generation unit uses the emotion estimation function to predict the recipient's emotional response and generates email content that will elicit the most positive response. For example, it uses expressions that make the recipient feel happy. The email generation unit also predicts the recipient's emotional response and generates email content that will elicit the most positive response. For example, it uses expressions that make the recipient feel reassured. The email generation unit also comprehensively predicts the recipient's emotional response and generates email content that will elicit the most positive response. For example, it generates optimal email content based on the recipient's emotional state. This makes it possible to predict the recipient's emotional response to the request email content and generate email content that will elicit the most positive response, thereby improving recipient satisfaction.

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

[0102] Step 1: The request content analysis unit analyzes the request content. For example, it uses generation AI to perform text analysis of the request content and identify the type and content of the request. It can also use data mining technology to extract patterns in the request content from past data and obtain analysis results. It can also use natural language processing technology to understand the context of the request content and obtain appropriate analysis results. Step 2: The escalation decision unit determines the appropriate escalation destination based on the request content analyzed by the request content analysis unit. For example, it uses generation AI to evaluate the urgency and importance of the request content and determines the appropriate escalation destination. It can also refer to past escalation history to identify the most effective escalation destination. It can also escalate at the optimal time, taking into account the current workload and schedule of the escalation destination. Step 3: The email generation unit generates the content of the request email to the escalation destination determined by the escalation determination unit. For example, it uses generation AI to generate appropriate email content based on the request content. It can also generate optimal email content by taking into account the requester's past communication style and preferences. It can also generate appropriate email content by taking into account legal requirements and regulations related to the request content.

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

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

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

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] 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.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] 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.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] 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.

[0129] 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.

[0130] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] 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.

[0145] 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.

[0146] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] 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.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0162] 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.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 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 request content analysis unit that analyzes the request content; an escalation determination unit that determines an appropriate escalation destination based on the request content analyzed by the request content analysis unit; an email generation unit that generates the contents of an email request to the escalation destination determined by the escalation determination unit; A system characterized by:

2. The request content analysis unit Refer to external data related to the request and understand the background of the request.

2. The system of claim 1.

3. The escalation determination unit Review past escalation history to identify the most effective escalation destination 2. The system of claim 1.

4. The email generation unit Generate optimal email content by taking into account the client's past communication style and preferences.

2. The system of claim 1.

5. The request content analysis unit Analyze the client's emotions and prioritize escalating emotionally important requests.

2. The system of claim 1.

Images