system

Abstract

Provide a system. A means for receiving a question from a user as an input; A means of comparing the entered question with past consultation cases and a database of created FAQs; means for identifying and presenting to the user the most relevant answers and related departments based on the matching results; A system including:

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 modern companies, employees need to be able to quickly find the right person to consult or the right support team to quickly progress through a wide range of projects and investigations. However, it is not always easy for employees to know who to consult or which department is responsible, which can result in a decline in work efficiency. Furthermore, there is no system in place to refer to past consultation history or inquiries from other employees, so similar questions are often asked repeatedly. A system that can solve these problems and enable employees to work smoothly is needed. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting a user's question as input, a means for comparing the input question with past consultation examples and a created FAQ database, and a means for identifying the most relevant answer and relevant department based on the comparison results and presenting them to the user. The system also includes a means for storing a history including the input question and the reason for the selection, and for referencing it the next time the system is compared, as well as a means for saving referrals to relevant departments as a history and considering that history when making subsequent referrals, thereby enabling the system to efficiently provide the most appropriate answer based on the content of the user's consultation. This allows employees to quickly find the appropriate person to consult with, improving work efficiency.

[0006] "Questions from users" are inquiries that individuals who use the system input to seek answers.

[0007] "Means for accepting input" refers to a method for acquiring questions posed by a user to the system in digital form and processing them as data.

[0008] "Past consultation examples" are data on the content of inquiries previously entered and recorded in the system and records of responses to those inquiries.

[0009] A "created FAQ database" is a collection of data in which frequently asked questions (FAQs) and their answers are systematically organized and stored.

[0010] "Matching means" refers to a method of searching and finding matching or relevant records by comparing the input question with past consultation cases and FAQ databases.

[0011] "Matching results" are the relevant information or answers obtained as a result of the system matching the input question.

[0012] A "highly relevant answer" is information that is determined to be the most appropriate answer to the user's question from the collation results.

[0013] A "related department" is a specific department within an organization that is responsible for responding to and supporting users' inquiries.

[0014] The "means for identifying and presenting" is a method for selecting an appropriate answer and the department related to that answer based on the collation result, and displaying them to the user.

[0015] "Means for retaining history and reasons" refers to a method for saving previously entered questions, their matching results, and related information, and utilizing them for future inquiries.

[0016] The "means for saving introductions to related departments as a history" is a method for saving a record of guiding a user to a specific department, and for referencing it at the time of a later inquiry. [Brief explanation of the drawings]

[0017] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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, a 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), and an APU (Accelerated Processing Unit).

[0021] 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.

[0022] 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.

[0023] 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), Bluetooth (registered trademark), etc.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] 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.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system that provides a consultation point for efficiently advancing business operations. A specific embodiment of this system will be described below.

[0039] This system is mainly composed of a server and a terminal. Users access the system through the terminal and input a question. The server accepts the question, searches for an appropriate answer, and sends the result to the terminal.

[0040] 1. Get the user's question

[0041] The terminal accepts questions from the user as input. The user enters the question according to the system's prompts, and the question is collected by the terminal. For example, if the user asks, "How do I connect office automation equipment?", the question is entered into the terminal and sent directly to the server.

[0042] 2. Database Verification

[0043] The server receives the user's input question and compares it with past consultations and a database of frequently asked questions (FAQs) that contain past consultation history and answers. The server searches through this data to identify the answer and relevant department that is most relevant to the user's question.

[0044] 3. Presentation of matching results

[0045] The server identifies the most relevant answer and the relevant department based on the matching results and sends them to the terminal. The terminal then presents them to the user. For example, in response to a question such as "How do I connect my office automation equipment?", the server presents the answer "Please contact the office automation support team" and the relevant department "Office Automation Support."

[0046] 4. Preserving and Reusing History

[0047] The server stores a history of entered questions and their answers. This history is referenced the next time a similar question is entered, and is used to efficiently provide an appropriate answer. For example, if the question "How do I connect my office automation equipment?" was previously asked, and the answer was saved as "Please contact the office automation support team," this answer will be provided immediately the next time the same question is entered.

[0048] 5. Department introduction history management

[0049] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the user asks the same question multiple times. For example, if a user asks "how to connect office equipment" and is referred to the "Office Support" department, the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0050] Specific examples

[0051] As a specific example, suppose a user enters the question "Check on the progress of the project" into a terminal. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This answer and information about the relevant department are presented to the user via the terminal. The history of this exchange is also saved on the server and can be referenced if a similar question arises in the future.

[0052] As described above, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. This system effectively utilizes past consultation history and FAQ data to enable quick and accurate responses.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The server loads a database that stores past consultation cases and FAQ data. The server opens the database file and loads its contents into memory, preparing it for quick matching when a question is entered.

[0056] Step 2:

[0057] The terminal accepts as input a question from the user, who types the question in response to a prompt displayed on the terminal's screen and the question is captured by the terminal.

[0058] Step 3:

[0059] The terminal sends the captured question to the server, and the question data entered by the user is transferred from the terminal to the server via the network.

[0060] Step 4:

[0061] The server compares the received question with past consultations and FAQ data in its database. Specifically, the server breaks down the user's question into keywords and phrases and compares them with relevant entries in the database.

[0062] Step 5:

[0063] The server identifies the most relevant answers and related departments based on the matching results. The server calculates a correlation score for each entry in the database and selects the entry with the highest score.

[0064] Step 6:

[0065] The server sends the identified answer and information on the relevant department to the terminal, and then the server packages the best answer to the user's question and information on the department to be contacted, and returns it to the terminal.

[0066] Step 7:

[0067] The terminal presents the answer received from the server and the information on the relevant department to the user, who can then check the presented answer and the information on the relevant department on the screen of the terminal.

[0068] Step 8:

[0069] The server stores a history of user questions and their answers, and the history data is referenced to provide quick answers to future queries.

[0070] Step 9:

[0071] The server also stores a history of referrals to relevant departments, so that if the same question is asked again, the same department will be referred to, taking into account the history information.

[0072] Through the above steps, the system is able to provide users with prompt and accurate answers to their questions and information on where to seek advice.

[0073] Example 1

[0074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0075] In conventional business support systems, there are many cases where users are unable to provide appropriate answers to their questions or refer them to relevant departments quickly and accurately. In addition, it is difficult to provide consistent answers to users who ask the same question multiple times, which leads to a decrease in business efficiency.

[0076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0077] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with a past consultation history database and an FAQ database, means for identifying the most relevant answer and relevant department based on the comparison results and presenting them to the user, and means for the server to store the user's question and its answer in the history database, thereby enabling the provision of quick and accurate responses to user questions and history management for consistent response.

[0078] "User" refers to any person or entity that accesses the system and enters a query.

[0079] A "question" refers to an inquiry or consultation that a user inputs to the system.

[0080] "Terminal" refers to a device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[0081] The term "server" refers to a central processing unit that receives questions entered by users, processes them, and sends the results to the terminal.

[0082] "Means for receiving" refers to a method or function by which the system receives a question entered by a user.

[0083] "Matching method" refers to the method or algorithm used to compare and search the input query against information in the database.

[0084] "Answer" refers to a solution or piece of information provided to a user's question.

[0085] "Related departments" refers to the departments and teams involved in the user's question.

[0086] "Presentation means" refers to the method or technology used by the server to present search results or answers to the user.

[0087] "History database" refers to a database for storing previously entered questions and their answers.

[0088] "Storage means" refers to the method or technology by which the server stores received questions and their answers in a history database.

[0089] The "consultation history database" refers to a database that stores past consultations and their responses.

[0090] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0091] "Consistent response" means that the same quality of response is always provided even when the same question is entered repeatedly.

[0092] The present invention relates to a system that provides a consultation service for efficiently advancing business operations. This system is mainly composed of a server and a terminal. Here, a specific embodiment of this system will be described.

[0093] Get the user's question

[0094] The terminal accepts questions from the user as input. The user inputs the question following the system's prompts, and the question is collected by the terminal. For example, if a user asks, "How do I connect office equipment?", the question is entered into the terminal and sent directly to the server. The terminal can be a computer, smartphone, tablet, or other device.

[0095] Database Collation

[0096] The server receives questions sent from the device and compares them with an internal database. This database includes past consultation history and FAQs (frequently asked questions) and their answers. The server uses a generative AI model to search this data and identify the most relevant answer and relevant department for the user's question. For example, the server might search the database for the question "How do I connect office equipment?" to find the most relevant past consultation examples and FAQs.

[0097] Presentation of matching results

[0098] The server sends the most relevant answer and the associated department identified based on the database match to the terminal, which then displays it to the user. For example, in response to the question "How do I connect my office automation equipment?", the server displays the answer "Please contact the office automation support team" and the associated department "Office Automation Support."

[0099] Preserving and reusing history

[0100] The server stores the history of entered questions and their answers in a database. This history is used for reference the next time a question is asked. For example, if a user enters the same question again, "How do I connect to office equipment?", the server immediately provides the previously saved information.

[0101] Department introduction history management

[0102] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the same question is asked repeatedly. For example, if a user is referred to the "OA Support" department in response to a question about "how to connect office equipment," the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0103] Specific examples

[0104] As a specific example, suppose a user types "I would like to know about the progress of the project" into their device. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This information is presented to the user via their device. The history of this exchange is also saved on the server and can be referenced the next time a similar question is asked.

[0105] Example prompts to input to the generative AI model

[0106] An example prompt might look like this:

[0107] "How do I connect my office automation equipment?"

[0108] "I want to check on the progress of a project. Which department should I contact?"

[0109] "I would like to know the steps to install new software."

[0110] In this way, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. The present invention makes it possible to respond quickly and accurately by effectively utilizing past consultation history and FAQ data.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1: The user operates the terminal and inputs a question.

[0113] The user inputs a question into an input field on the terminal. For example, the user inputs "How do I connect OA equipment?" and clicks the send button. The input data is a text-format question and is obtained from the input field on the terminal.

[0114] Input: The question entered by the user

[0115] Output: The question text entered

[0116] Step 2: The terminal sends the user's input to the server.

[0117] The terminal sends the question entered by the user to the server. The transmission is performed using an HTTP request or other communication protocol. For example, the terminal sends the entered question, "How do I connect to office equipment?" to the server.

[0118] Input: Question text obtained by the device

[0119] Output: The question data sent to the server

[0120] Step 3: The server receives the query and checks it against its database.

[0121] The server receives questions sent from the device. It analyzes the questions and compares them with past consultation history and an FAQ database. This matching uses a generative AI model to find the most relevant answer. For example, the server receives the question "How do I connect office equipment?" and searches for relevant answers in the database.

[0122] Input: Question data received from the terminal

[0123] Output: Matching responses and associated department information

[0124] Step 4: The server sends the matching result to the terminal.

[0125] The server sends the answer and related department information identified as a result of the database check to the terminal, for example, the answer "Please contact the OA support team" and the "OA support" department information to the terminal.

[0126] Input: Matched answers and related department information

[0127] Output: Answers and department information sent to the terminal

[0128] Step 5: The terminal displays the results sent from the server to the user.

[0129] The terminal displays the response and department information received from the server to the user. The user can see the information on the service screen that says, "Please contact the OA support team regarding how to connect the OA equipment."

[0130] Input: Response received from the server and department information

[0131] Output: Answers and department information presented to the user

[0132] Step 6: The server stores the history of questions and answers.

[0133] The server stores user questions and their answers in a history database. This history data allows for quick matching the next time a similar question is asked. For example, the server stores the question "How do I connect my office automation equipment?" and the answer "Please contact the office automation support team" as history.

[0134] Input: Question and its answer

[0135] Output: Questions and answers stored in a history database

[0136] Step 7: The server stores the department referral history.

[0137] The server stores the history of when a user was referred to a specific department and the reason for that referral in a history database. This allows for a consistent response if the same question is asked again. For example, the server stores the history of when a user was referred to the "OA Support" department regarding "how to connect office automation equipment" and the reason for that referral.

[0138] Input: Department referred and reason

[0139] Output: History of department referrals stored in the history database

[0140] In this way, the system efficiently processes user questions and provides appropriate consultation, thereby improving business efficiency.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] Conventional support systems have difficulty responding to user questions quickly and appropriately. Furthermore, when users repeatedly ask the same question, the system is unable to provide consistent responses, causing significant user frustration. Furthermore, in food delivery services, delays in responses regarding order status and problems can lead to lower customer satisfaction.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with past consultation examples and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, and means for using a generative AI model to generate an optimal answer to the user's question. This makes it possible to provide a quick and appropriate answer to the user's question, thereby improving customer satisfaction in food delivery services.

[0146] The "means for accepting a question from a user as an input" refers to an interface or function for receiving a question that a user has input to the system.

[0147] "Means for checking the entered question against past consultation cases and a database of pre-created FAQs" refers to the process or function for comparing the question received from the user with past consultation cases in the database and pre-created FAQ data to confirm relevance.

[0148] "Means for identifying the most relevant answer and related department based on the matching results and presenting them to the user" is a function for selecting the most appropriate answer and the department responsible for it from the matching results and displaying them to the user.

[0149] "Means of using a generative AI model to generate optimal answers to user questions" refers to processes or functions that use AI technology to generate optimal answers to user questions.

[0150] This invention is a support system that aims to enable users to obtain prompt and appropriate answers to questions related to food delivery services. Specifically, this system uses AI technology to analyze questions from users, compares them with past consultation cases and an FAQ database, and generates and provides the most appropriate answers.

[0151] 1. Obtaining and inputting user questions

[0152] A user accesses the application using a smartphone and inputs a question. The smartphone acts as an interface and sends the input question to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the question is sent to the server.

[0153] 2. Database Matching

[0154] The server processes the question received from the user and compares it with past inquiries and created FAQ data in the database. The server performs this process using database management software. For example, in response to a question such as "The food I ordered hasn't arrived," the server searches to see if similar questions have been asked in the past, and finds the answer "Please contact the delivery team."

[0155] 3. Use of generative AI models

[0156] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model performs advanced calculations to appropriately respond to the user's doubts. This AI model uses natural language processing technology, for example, to understand the intent of the user's question and generate a relevant answer. An example of a prompt sentence is, "Based on the question entered by the user, please compare it with past FAQ data and provide the optimal answer and relevant department."

[0157] 4. Matching results and optimal answer presentation

[0158] The server sends the matching results and the optimal answer obtained by the generative AI model to the smartphone, which then displays it to the user. For example, the user can confirm the answer "Please contact the delivery team" along with the "delivery team" contact information.

[0159] 5. Preserving and Reusing History

[0160] The server saves the entered questions and their answers as a history in a database. This history is referenced the next time a similar question is entered, allowing for a quick response. This allows for a consistent response even if the user asks the same question multiple times.

[0161] Through the above steps, the system can provide quick and appropriate answers to users' questions and improve customer satisfaction in food delivery services.

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] A user inputs a question through a smartphone device. The input question is collected by the device's interface. The input (question text) is sent to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the text is passed from the device to the server.

[0165] Step 2:

[0166] The server checks the received question against a database, which stores past consultation cases and FAQ data. The server uses the question text to search the database and find related questions and their answers. The entered question text is used to obtain a matching result (the best answer) from the database. For example, in response to a question such as "The food I ordered hasn't arrived," the server finds the answer "Please contact the delivery team" from the past database.

[0167] Step 3:

[0168] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model uses natural language processing technology to analyze the intent of the question and generate an appropriate answer text. The input is the question text, and the output is the generated answer text. For example, in response to the question "The food I ordered hasn't arrived," the AI ​​model generates an answer such as "Please contact our delivery team immediately."

[0169] Step 4:

[0170] The server sends the generated answer and the relevant department information to the terminal, which then displays it to the user. The input is the answer text and department information from the server, and the output is what is displayed to the user. For example, the generated answer "Contact our delivery team immediately" and the contact information for the "delivery team" are displayed on the user's terminal.

[0171] Step 5:

[0172] The server stores the questions and answers received from the user in a database as history. This allows for a quick response if a similar question is entered in the future. The input is the question text and the answer text, and the output is saved in the history database. For example, the question "The food I ordered hasn't arrived" and its answer are saved in the database.

[0173] Step 6:

[0174] If the user enters the same question again, the server references the history database and quickly provides past answers. This allows the system to provide answers efficiently and consistently. The input is the question text received again, and the output is the text of the previous answer. For example, if the user asks again, "My order hasn't arrived," the previous answer "Please contact the delivery team" is immediately provided.

[0175] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0176] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0177] 1. Data preparation

[0178] The server reads the necessary information from a database that stores past consultation examples and FAQ data, and loads it into memory. This preparation creates a system that can respond quickly when a question is entered by a user.

[0179] 2. Getting questions from users

[0180] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question and sends it to the server.

[0181] 3. Recognizing User Emotions

[0182] The server analyzes the received user question and uses an emotion engine to recognize the user's emotions. This recognition is performed using text analysis and natural language processing techniques. For example, emotions such as "troubled," "angry," and "anxious" can be detected from the user's input.

[0183] 4. Database Verification

[0184] The server compares the user's question with past consultation cases and a FAQ database. This database contains past consultation history, frequently asked questions (FAQs), and their answers. The server selects the most appropriate answer and relevant department, taking into account the user's question and emotional state.

[0185] 5. Adjustment and presentation of matching results

[0186] The server identifies the most relevant answer and related department based on the matching results, and adjusts the content of the presentation taking into account the user's emotion recognition results from the emotion engine. For example, if the user is in trouble, the server will provide a more detailed and thorough explanation. The results are then sent to the terminal and presented to the user.

[0187] 6. Preserving and Reusing History

[0188] The server stores the user's questions and answers, which are used to provide a quick and appropriate answer when a similar question is entered in the future. The server also records the user's emotional state along with the history and uses it for future responses.

[0189] 7. Department introduction history management

[0190] The server also stores the history of referrals to related departments. This history includes the reasons and circumstances behind the referral, and this information is referenced when a referral is made again. This allows for consistent responses.

[0191] Specific examples

[0192] For example, if a user types the question "Check on the progress of the project" into a device, the device sends this information to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then compares past consultation cases and the FAQ database to identify the answer "Please contact the Project Management Department" and the "Project Management" department. At this time, a more detailed explanation is added, taking into account the user's emotions. This answer and information about the relevant department are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0193] As described above, this system not only provides fast and accurate answers to user questions and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, thereby improving work efficiency and the user experience.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] The server loads a database containing past consultation examples and FAQ data. The server first opens the database file and loads its contents into memory. This preparation process prepares the server for quick search and matching when a question is entered.

[0197] Step 2:

[0198] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question. For example, the user enters "Check the progress of the project."

[0199] Step 3:

[0200] The terminal sends the captured question to the server, and the entered question data is transferred to the server via the network. The server receives this data.

[0201] Step 4:

[0202] The server analyzes the received question text and uses an emotion engine to recognize the user's emotions. For example, the server can detect emotions such as "I'm in trouble" or "I'm anxious" from the text.

[0203] Step 5:

[0204] The server compares the question with past consultation cases and a FAQ database, taking into account the results of emotion recognition. Specifically, it breaks down the user's question into keywords and searches for related entries in the database.

[0205] Step 6:

[0206] The server then uses the matching results to identify relevant answers and relevant departments, such as "Please contact the Project Management department," and adjusts the tone and specificity of the answer based on the emotion recognition results.

[0207] Step 7:

[0208] The server sends the identified answer and information about the relevant department to the terminal. For example, the server may package the information about the "Project Management" department with the answer "Please contact the Project Management Department" and send it to the terminal.

[0209] Step 8:

[0210] The terminal receives the response from the server and presents the relevant department information to the user. The terminal displays the information on the screen in a format that is easy for the user to understand. For example, it displays "To check the progress of the project, please contact the project management department."

[0211] Step 9:

[0212] The server stores the user's questions, their answers, and the emotion recognition results as a history, which can be used to quickly respond to similar questions in the future.

[0213] Step 10:

[0214] The server also stores a history of referrals to related departments, allowing for a consistent response when the user asks the same question again. The server also takes into account the user's past emotional state and provides an appropriate response.

[0215] Through these steps, the system not only provides users with quick and accurate answers and information on where to seek help, but also responds optimally to their emotional state, which is expected to improve both work efficiency and the user experience.

[0216] Example 2

[0217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] Conventional consultation systems often respond mechanically to user questions and provide only uniform answers. Furthermore, they do not take the user's emotional state into consideration, which can lead to frustration and anxiety. Furthermore, there is no mechanism for referencing past consultation history or emotional state, making it difficult to provide a consistent response. This leads to a poor user experience and a lack of work efficiency.

[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0220] In this invention, the server includes means for receiving a question from a user as input, means including an emotion engine for analyzing the input question and recognizing the user's emotion, and means for comparing the analysis results with past consultation cases and an FAQ database. This makes it possible to identify the most appropriate answer and relevant department taking into account the user's emotional state, thereby improving user satisfaction and streamlining operations.

[0221] "User" refers to an individual or organization that utilizes the system to enter questions and obtain information.

[0222] A "question" refers to text information that a user inputs to the system, requesting specific information or advice.

[0223] "Emotion engine" refers to a software module that analyzes and recognizes a user's emotional state from input text information.

[0224] "Past consultation examples" refers to records of questions previously submitted by users and the answers to those questions.

[0225] An "FAQ database" refers to a database that systematically collects and stores frequently asked questions and their answers.

[0226] "Matching" refers to the process of evaluating the relevance of the input question and emotional state by comparing it with past consultation cases and the FAQ database.

[0227] "Relevant department" refers to a department or person within an organization who has the authority and knowledge to provide an appropriate answer to a user's question.

[0228] "History" refers to a record of a user's questions, answers, and emotional state, data that is kept for future reference.

[0229] "Emotional state" refers to information that indicates the psychological state of the user when they input a question, and is recognized by the emotion engine.

[0230] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0231] Hardware and Software Configuration

[0232] This system is built using a server, a terminal, and an emotion engine that performs text analysis. Specific software includes relational database management systems such as MySQL (registered trademark) and PostgreSQL for the database, and natural language processing (NLP) tools such as IBM Watson (registered trademark) and Microsoft (registered trademark) Azure (registered trademark) Sentiment Analysis for the emotion analysis.

[0233] Data preparation

[0234] The server reads the necessary information from a database that stores past consultation examples and FAQ data and loads it into memory. This prepares the server to respond quickly when a question is entered by a user. Information from the database is extracted using SQL queries and temporarily cached in memory.

[0235] Getting questions from users

[0236] The device receives a question from the user as input. The user enters the question in an input field displayed on the device screen and clicks the send button. The device then sends this question in JSON format to the server. Specifically, the device creates an input field in the user interface (UI), captures the question, and sends it to the server as an HTTP POST request.

[0237] Recognizing user emotions

[0238] The server analyzes the received user question and recognizes the user's emotion using an emotion engine. This recognition is performed using text analysis technology through the emotion engine. For example, it detects whether the user is expressing emotions such as "troubled," "angry," or "anxious."

[0239] Database Collation

[0240] The server compares the user's question and the perceived emotion with the past consultation case and FAQ database, and searches the database with the appropriate SQL query to select the most appropriate answer and relevant department, taking into account the question and emotional state.

[0241] Reconciliation and presentation of match results

[0242] The server identifies the appropriate answer and relevant department based on the matching results. If the user is having trouble, the server adds a more detailed and specific explanation based on the emotion recognition results of the emotion engine. This final answer is sent to the device in JSON format and presented to the user.

[0243] Preserving and reusing history

[0244] The server stores the history of user questions, their answers, and their emotional state, which can be used to provide immediate and appropriate answers when similar questions are entered in the future. The historical data is stored in a database using appropriate SQL queries.

[0245] Department introduction history management

[0246] The server also stores the referral history to related departments in a database. This history includes the reason for the referral and the circumstances surrounding it, and can be referenced the next time a referral is made, allowing for consistent handling.

[0247] Specific examples

[0248] Consider the case where a user types "I would like to check the progress of the project" into a device. The device sends this question to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then searches past consultation cases and a database of FAQs to identify the answer "Please contact the project management department." At this time, it adds a more detailed explanation, taking into account the user's emotions. This answer and information about the relevant departments are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0249] This system not only provides users with quick and accurate answers and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, which is expected to improve work efficiency and the user experience.

[0250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0251] Step 1:

[0252] The server begins the process of loading past case and FAQ data from a database (e.g., MySQL, PostgreSQL). This information is used for future lookups. Specifically, the server executes SQL queries to extract the necessary data and caches it in memory.

[0253] Input: Database connection information and SQL query

[0254] Output: Cached in-memory consultation examples and FAQ data

[0255] Step 2:

[0256] The terminal accepts a user's question as input. This question is entered through an input field in the user interface and submitted by the user clicking a submit button. The terminal converts this information into JSON format and sends it to the server as an HTTP POST request.

[0257] Input: The question text that the user types into the terminal

[0258] Output: Question data in JSON format sent to the server

[0259] Step 3:

[0260] The server analyzes the question data received from the device using natural language processing (NLP) technology and an emotion engine (e.g., IBM Watson, Microsoft Azure Sentiment Analysis). This process recognizes not only the content of the user's question, but also the emotion hidden in the question (e.g., "troubled," "angry," "anxious").

[0261] Input: JSON format question data received from the terminal

[0262] Output: Question content and emotion recognition results

[0263] Step 4:

[0264] Based on the analysis results, the server compares the question and emotional state with past consultation cases and a database of FAQs. Specifically, it uses SQL queries to search the database and extract the most relevant answers. In doing so, it also takes the user's emotional state into consideration to select the most appropriate answer.

[0265] Input: Question content, emotion recognition results, past consultation examples, and FAQ data

[0266] Output: The most relevant answers as a result of matching and related department information

[0267] Step 5:

[0268] The server formats the answer and related department information based on the matching results. Taking into account the user's emotion recognition results, it adds a more detailed explanation to users who are in trouble, for example. This final response data is converted into JSON format and sent to the device.

[0269] Input: Answer as matching result, related department information, emotion recognition result

[0270] Output: Response data in JSON format to send to the device

[0271] Step 6:

[0272] The terminal displays the response data received from the server on the user interface, allowing the user to obtain an appropriate answer to their question and information on where to seek advice.

[0273] Input: JSON format response data received from the server

[0274] Output: Answers and associated department information displayed in the user interface

[0275] Step 7:

[0276] The server stores the user's question, the answer, and the emotion recognition results in a database, allowing it to respond quickly to similar questions in the future.

[0277] Input: Question, answer, emotion recognition result

[0278] Output: Historical data stored in a database

[0279] Step 8:

[0280] The server also stores the referral history to the relevant department in a database, including the reason and circumstances for the referral, so that it can be referenced the next time a referral is made.

[0281] Input: Referral information, reason for referral and background

[0282] Output: Referral history stored in a database

[0283] (Application example 2)

[0284] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0285] In modern brick-and-mortar stores, users need to be able to quickly and accurately obtain product information. However, conventional methods often fail to respond appropriately to user questions, resulting in a poor user experience. Furthermore, because they do not take into account the user's feelings regarding the question, it is difficult to improve customer satisfaction.

[0286] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question from a user as input, means for comparing the input question with past consultation cases and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, means for converting the user's question into text data using voice input and voice recognition technology, emotion recognition means for analyzing the user's emotions, and means for adjusting the presented content based on the emotion recognition results. This enables flexible responses and efficient product guidance according to the user's emotions.

[0287] The "means for accepting a question from a user as input" refers to an interface that allows a user to input a question to a terminal. This includes functions for accepting information through voice input or text input.

[0288] "Means for comparing the entered question with past consultation examples and an existing FAQ database" is a function for comparing a new question entered by a user with past questions and answers stored in an existing database.

[0289] "Means of identifying the most relevant answer and relevant department based on the matching results and presenting them to the user" is a function that uses the information obtained through matching to select the most appropriate answer and contact point for the user's question and provides them to the user.

[0290] The "means for converting a user's question into text data using voice input and voice recognition technology" is a function that allows a user to input a question by voice and automatically convert the voice data into text data.

[0291] "Emotion recognition means for analyzing user emotions" refers to algorithms or technologies that determine the user's emotions based on the text data entered by the user. For example, it can recognize emotions such as distress or anger.

[0292] The "means for adjusting the content of presentation based on the emotion recognition result" is a function for adjusting the content of answers or guidance according to the emotion of the user after the emotion of the user is determined by the emotion recognition means.

[0293] "Means for saving history and referencing it the next time" is a function that saves user questions, their answers, and the accompanying emotional data in a database, allowing for a quick response when a similar question is entered at a later date.

[0294] "A means of saving referrals to related departments as a history and taking that history into consideration when making a second referral" is a function that records the circumstances and reasons when a user is referred to a specific department, and uses that history when the same user makes another inquiry in the future.

[0295] The present invention relates to a consultation service provider system that aims to improve the user experience in brick-and-mortar stores. This system uses smart glasses and makes full use of voice input and emotion recognition technology to quickly provide appropriate answers to users' questions.

[0296] System configuration

[0297] The system consists of the following main components:

[0298] 1. Smart glasses: For example, the general term "wearable device."

[0299] 2. Server: Deployed in a cloud environment.

[0300] 3. Emotion recognition engine: For example, the generic name "emotion analysis software."

[0301] 4. Database: A data repository for storing user questions, emotional states, and answer history.

[0302] Hardware and Software Use

[0303] The wearable device (smart glasses) has a voice input function and captures the user's questions.

[0304] The server is primarily responsible for analyzing the question data and generating answers.

[0305] Sentiment analysis software recognizes emotions from user input and determines appropriate responses.

[0306] The database uses a cloud database such as AWS (registered trademark) RDS.

[0307] Program implementation example

[0308] 1. Retrieving and submitting user questions:

[0309] The user speaks a question into the smart glasses, which then recognize the voice and convert it into text. This process is performed using a speech recognition API.

[0310] 2. Emotion Recognition and Analysis:

[0311] The received text data is sent to a server, where sentiment analysis software analyzes the user's emotions. For example, the text is tagged with "I'm in trouble" or "I'm looking for something." This allows the system to understand the user's emotional state and select an appropriate response.

[0312] 3. Historical comparison:

[0313] Based on the user's text data and emotional state, the server matches the user's past questions with a database of answers, and identifies the most relevant answers and related departments based on the matching results.

[0314] 4. Present the response:

[0315] The answer obtained through the matching is sent to the smart glasses and presented to the user, with the content of the presentation adjusted according to the user's emotions.

[0316] 5. History Preservation:

[0317] All questions, answers, and the user's emotional state are stored in a database, allowing for fast and accurate answers when similar questions are asked in the future.

[0318] Adding specific examples

[0319] Example of operation scene

[0320] A user is shopping and wearing smart glasses. The user asks, "Where is this item?"

[0321] Speak: "Where is this item?"

[0322] Emotion recognition: "I'm in trouble"

[0323] Server response: "It's on the shelf near the register. I'll show you where it is."

[0324] Example prompts to input to the generative AI model

[0325] User Question: "Where is this item?"

[0326] Emotion recognition: "I'm in trouble"

[0327] Past data collation: Product search, in-store guidance history

[0328] API usage: speech recognition API, sentiment analysis software, cloud database

[0329] This system will improve the user experience and make operations in physical stores more efficient.

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] The user speaks a question into the smart glasses. The smart glasses capture the voice data and convert it into text data using a voice recognition API. Specifically, if the user speaks "Where is this product?", the voice is converted into the text "Where is this product?" The input of this process is voice data, and the output is text data.

[0333] Step 2:

[0334] The user's question data (text data) is sent from the terminal to the server. The terminal then sends the converted text data to the server, which then receives it and prepares it for analysis. The input to this process is text data, and the output is data that can be analyzed on the server side.

[0335] Step 3:

[0336] The server uses an emotion recognition engine to analyze the received text data and recognize the user's emotions. For example, the emotion "troubled" is detected from the text data. Specifically, the emotion analysis software assigns a tag of "troubled." The input for this process is text data, and the output is data with an emotion tag.

[0337] Step 4:

[0338] The server uses emotion-tagged question data to match past consultations and an FAQ database. This matching identifies the most relevant answer and the appropriate related department. The specific operation of the matching is to use a database search to check whether a similar question has been asked in the past and find the appropriate answer. The input to this process is emotion-tagged question data, and the output is the best answer and information on the related department.

[0339] Step 5:

[0340] The server adjusts the answer based on the matching results and emotion recognition results, and prepares to present it to the user. For example, if the server recognizes that the user is "troubled," it adds a more detailed explanation. The input to this process is the optimal answer and emotion tag, and the output is the adjusted answer data.

[0341] Step 6:

[0342] The adjusted answer data is sent from the server to the device (smart glasses) and presented to the user. The smart glasses then provide the received answer data to the user via voice or screen display. Specifically, the glasses provide voice guidance such as, "It's on the shelf near the register. We'll guide you to where the product is." The input for this process is the adjusted answer data, and the output is an audio or visual presentation to the user.

[0343] Step 7:

[0344] The server stores the entire history of user questions, emotion tags, and suggested answers in a database. This allows for a quick and appropriate response when a similar question is entered in the future. The input of this process is the entire history data, and the output is an update to the history database.

[0345] 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.

[0346] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0347] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 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.

[0351] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0352] 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.

[0353] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0354] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0355] 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. 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.

[0356] 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.

[0357] 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 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.

[0358] 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.

[0359] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0360] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0361] The present invention relates to a system that provides a consultation point for efficiently advancing business operations. A specific embodiment of this system will be described below.

[0362] This system is mainly composed of a server and a terminal. Users access the system through the terminal and input a question. The server accepts the question, searches for an appropriate answer, and sends the result to the terminal.

[0363] 1. Get the user's question

[0364] The terminal accepts questions from the user as input. The user enters the question according to the system's prompts, and the question is collected by the terminal. For example, if the user asks, "How do I connect office automation equipment?", the question is entered into the terminal and sent directly to the server.

[0365] 2. Database Verification

[0366] The server receives the user's input question and compares it with past consultations and a database of frequently asked questions (FAQs) that contain past consultation history and answers. The server searches through this data to identify the answer and relevant department that is most relevant to the user's question.

[0367] 3. Presentation of matching results

[0368] The server identifies the most relevant answer and the relevant department based on the matching results and sends them to the terminal. The terminal then presents them to the user. For example, in response to a question such as "How do I connect my office automation equipment?", the server presents the answer "Please contact the office automation support team" and the relevant department "Office Automation Support."

[0369] 4. Preserving and Reusing History

[0370] The server stores a history of entered questions and their answers. This history is referenced the next time a similar question is entered, and is used to efficiently provide an appropriate answer. For example, if the question "How do I connect my office automation equipment?" was previously asked, and the answer was saved as "Please contact the office automation support team," this answer will be provided immediately the next time the same question is entered.

[0371] 5. Department introduction history management

[0372] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the user asks the same question multiple times. For example, if a user asks "how to connect office equipment" and is referred to the "Office Support" department, the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0373] Specific examples

[0374] As a specific example, suppose a user enters the question "Check on the progress of the project" into a terminal. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This answer and information about the relevant department are presented to the user via the terminal. The history of this exchange is also saved on the server and can be referenced if a similar question arises in the future.

[0375] As described above, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. This system effectively utilizes past consultation history and FAQ data to enable quick and accurate responses.

[0376] The processing flow will be explained below.

[0377] Step 1:

[0378] The server loads a database that stores past consultation cases and FAQ data. The server opens the database file and loads its contents into memory, preparing it for quick matching when a question is entered.

[0379] Step 2:

[0380] The terminal accepts as input a question from the user, who types the question in response to a prompt displayed on the terminal's screen and the question is captured by the terminal.

[0381] Step 3:

[0382] The terminal sends the captured question to the server, and the question data entered by the user is transferred from the terminal to the server via the network.

[0383] Step 4:

[0384] The server compares the received question with past consultations and FAQ data in its database. Specifically, the server breaks down the user's question into keywords and phrases and compares them with relevant entries in the database.

[0385] Step 5:

[0386] The server identifies the most relevant answers and related departments based on the matching results. The server calculates a correlation score for each entry in the database and selects the entry with the highest score.

[0387] Step 6:

[0388] The server sends the identified answer and information on the relevant department to the terminal, and then the server packages the best answer to the user's question and information on the department to be contacted, and returns it to the terminal.

[0389] Step 7:

[0390] The terminal presents the answer received from the server and the information on the relevant department to the user, who can then check the presented answer and the information on the relevant department on the screen of the terminal.

[0391] Step 8:

[0392] The server stores a history of user questions and their answers, and the history data is referenced to provide quick answers to future queries.

[0393] Step 9:

[0394] The server also stores a history of referrals to relevant departments, so that if the same question is asked again, the same department will be referred to, taking into account the history information.

[0395] Through the above steps, the system is able to provide users with prompt and accurate answers to their questions and information on where to seek advice.

[0396] Example 1

[0397] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0398] In conventional business support systems, there are many cases where users are unable to provide appropriate answers to their questions or refer them to relevant departments quickly and accurately. In addition, it is difficult to provide consistent answers to users who ask the same question multiple times, which leads to a decrease in business efficiency.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0400] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with a past consultation history database and an FAQ database, means for identifying the most relevant answer and relevant department based on the comparison results and presenting them to the user, and means for the server to store the user's question and its answer in the history database, thereby enabling the provision of quick and accurate responses to user questions and history management for consistent response.

[0401] "User" refers to any person or entity that accesses the system and enters a query.

[0402] A "question" refers to an inquiry or consultation that a user inputs to the system.

[0403] "Terminal" refers to a device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[0404] The term "server" refers to a central processing unit that receives questions entered by users, processes them, and sends the results to the terminal.

[0405] "Means for receiving" refers to a method or function by which the system receives a question entered by a user.

[0406] "Matching method" refers to the method or algorithm used to compare and search the input query against information in the database.

[0407] "Answer" refers to a solution or piece of information provided to a user's question.

[0408] "Related departments" refers to the departments and teams involved in the user's question.

[0409] "Presentation means" refers to the method or technology used by the server to present search results or answers to the user.

[0410] "History database" refers to a database for storing previously entered questions and their answers.

[0411] "Storage means" refers to the method or technology by which the server stores received questions and their answers in a history database.

[0412] The "consultation history database" refers to a database that stores past consultations and their responses.

[0413] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0414] "Consistent response" means that the same quality of response is always provided even when the same question is entered repeatedly.

[0415] The present invention relates to a system that provides a consultation service for efficiently advancing business operations. This system is mainly composed of a server and a terminal. Here, a specific embodiment of this system will be described.

[0416] Get the user's question

[0417] The terminal accepts questions from the user as input. The user inputs the question following the system's prompts, and the question is collected by the terminal. For example, if a user asks, "How do I connect office equipment?", the question is entered into the terminal and sent directly to the server. The terminal can be a computer, smartphone, tablet, or other device.

[0418] Database Collation

[0419] The server receives questions sent from the device and compares them with an internal database. This database includes past consultation history and FAQs (frequently asked questions) and their answers. The server uses a generative AI model to search this data and identify the most relevant answer and relevant department for the user's question. For example, the server might search the database for the question "How do I connect office equipment?" to find the most relevant past consultation examples and FAQs.

[0420] Presentation of matching results

[0421] The server sends the most relevant answer and the associated department identified based on the database match to the terminal, which then displays it to the user. For example, in response to the question "How do I connect my office automation equipment?", the server displays the answer "Please contact the office automation support team" and the associated department "Office Automation Support."

[0422] Preserving and reusing history

[0423] The server stores the history of entered questions and their answers in a database. This history is used for reference the next time a question is asked. For example, if a user enters the same question again, "How do I connect to office equipment?", the server immediately provides the previously saved information.

[0424] Department introduction history management

[0425] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the same question is asked repeatedly. For example, if a user is referred to the "OA Support" department in response to a question about "how to connect office equipment," the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0426] Specific examples

[0427] As a specific example, suppose a user types "I would like to know about the progress of the project" into their device. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This information is presented to the user via their device. The history of this exchange is also saved on the server and can be referenced the next time a similar question is asked.

[0428] Example prompts to input to the generative AI model

[0429] An example prompt might look like this:

[0430] "How do I connect my office automation equipment?"

[0431] "I want to check on the progress of a project. Which department should I contact?"

[0432] "I would like to know the steps to install new software."

[0433] In this way, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. The present invention makes it possible to respond quickly and accurately by effectively utilizing past consultation history and FAQ data.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1: The user operates the terminal and inputs a question.

[0436] The user inputs a question into an input field on the terminal. For example, the user inputs "How do I connect OA equipment?" and clicks the send button. The input data is a text-format question and is obtained from the input field on the terminal.

[0437] Input: The question entered by the user

[0438] Output: The question text entered

[0439] Step 2: The terminal sends the user's input to the server.

[0440] The terminal sends the question entered by the user to the server. The transmission is performed using an HTTP request or other communication protocol. For example, the terminal sends the entered question, "How do I connect to office equipment?" to the server.

[0441] Input: Question text obtained by the device

[0442] Output: The question data sent to the server

[0443] Step 3: The server receives the query and checks it against its database.

[0444] The server receives questions sent from the device. It analyzes the questions and compares them with past consultation history and an FAQ database. This matching uses a generative AI model to find the most relevant answer. For example, the server receives the question "How do I connect office equipment?" and searches for relevant answers in the database.

[0445] Input: Question data received from the terminal

[0446] Output: Matching responses and associated department information

[0447] Step 4: The server sends the matching result to the terminal.

[0448] The server sends the answer and related department information identified as a result of the database check to the terminal, for example, the answer "Please contact the OA support team" and the "OA support" department information to the terminal.

[0449] Input: Matched answers and related department information

[0450] Output: Answers and department information sent to the terminal

[0451] Step 5: The terminal displays the results sent from the server to the user.

[0452] The terminal displays the response and department information received from the server to the user. The user can see the information on the service screen that says, "Please contact the OA support team regarding how to connect the OA equipment."

[0453] Input: Response received from the server and department information

[0454] Output: Answers and department information presented to the user

[0455] Step 6: The server stores the history of questions and answers.

[0456] The server stores user questions and their answers in a history database. This history data allows for quick matching the next time a similar question is asked. For example, the server stores the question "How do I connect my office automation equipment?" and the answer "Please contact the office automation support team" as history.

[0457] Input: Question and its answer

[0458] Output: Questions and answers stored in a history database

[0459] Step 7: The server stores the department referral history.

[0460] The server stores the history of when a user was referred to a specific department and the reason for that referral in a history database. This allows for a consistent response if the same question is asked again. For example, the server stores the history of when a user was referred to the "OA Support" department regarding "how to connect office automation equipment" and the reason for that referral.

[0461] Input: Department referred and reason

[0462] Output: History of department referrals stored in the history database

[0463] In this way, the system efficiently processes user questions and provides appropriate consultation, thereby improving business efficiency.

[0464] (Application example 1)

[0465] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0466] Conventional support systems have difficulty responding to user questions quickly and appropriately. Furthermore, when users repeatedly ask the same question, the system is unable to provide consistent responses, causing significant user frustration. Furthermore, in food delivery services, delays in responses regarding order status and problems can lead to lower customer satisfaction.

[0467] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0468] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with past consultation examples and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, and means for using a generative AI model to generate an optimal answer to the user's question. This makes it possible to provide a quick and appropriate answer to the user's question, thereby improving customer satisfaction in food delivery services.

[0469] The "means for accepting a question from a user as an input" refers to an interface or function for receiving a question that a user has input to the system.

[0470] "Means for checking the entered question against past consultation cases and a database of pre-created FAQs" refers to the process or function for comparing the question received from the user with past consultation cases in the database and pre-created FAQ data to confirm relevance.

[0471] "Means for identifying the most relevant answer and related department based on the matching results and presenting them to the user" is a function for selecting the most appropriate answer and the department responsible for it from the matching results and displaying them to the user.

[0472] "Means of using a generative AI model to generate optimal answers to user questions" refers to processes or functions that use AI technology to generate optimal answers to user questions.

[0473] This invention is a support system that aims to enable users to obtain prompt and appropriate answers to questions related to food delivery services. Specifically, this system uses AI technology to analyze questions from users, compares them with past consultation cases and an FAQ database, and generates and provides the most appropriate answers.

[0474] 1. Obtaining and inputting user questions

[0475] A user accesses the application using a smartphone and inputs a question. The smartphone acts as an interface and sends the input question to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the question is sent to the server.

[0476] 2. Database Matching

[0477] The server processes the question received from the user and compares it with past inquiries and created FAQ data in the database. The server performs this process using database management software. For example, in response to a question such as "The food I ordered hasn't arrived," the server searches to see if similar questions have been asked in the past, and finds the answer "Please contact the delivery team."

[0478] 3. Use of generative AI models

[0479] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model performs advanced calculations to appropriately respond to the user's doubts. This AI model uses natural language processing technology, for example, to understand the intent of the user's question and generate a relevant answer. An example of a prompt sentence is, "Based on the question entered by the user, please compare it with past FAQ data and provide the optimal answer and relevant department."

[0480] 4. Matching results and optimal answer presentation

[0481] The server sends the matching results and the optimal answer obtained by the generative AI model to the smartphone, which then displays it to the user. For example, the user can confirm the answer "Please contact the delivery team" along with the "delivery team" contact information.

[0482] 5. Preserving and Reusing History

[0483] The server saves the entered questions and their answers as a history in a database. This history is referenced the next time a similar question is entered, allowing for a quick response. This allows for a consistent response even if the user asks the same question multiple times.

[0484] Through the above steps, the system can provide quick and appropriate answers to users' questions and improve customer satisfaction in food delivery services.

[0485] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0486] Step 1:

[0487] A user inputs a question through a smartphone device. The input question is collected by the device's interface. The input (question text) is sent to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the text is passed from the device to the server.

[0488] Step 2:

[0489] The server checks the received question against a database, which stores past consultation cases and FAQ data. The server uses the question text to search the database and find related questions and their answers. The entered question text is used to obtain a matching result (the best answer) from the database. For example, in response to a question such as "The food I ordered hasn't arrived," the server finds the answer "Please contact the delivery team" from the past database.

[0490] Step 3:

[0491] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model uses natural language processing technology to analyze the intent of the question and generate an appropriate answer text. The input is the question text, and the output is the generated answer text. For example, in response to the question "The food I ordered hasn't arrived," the AI ​​model generates an answer such as "Please contact our delivery team immediately."

[0492] Step 4:

[0493] The server sends the generated answer and the relevant department information to the terminal, which then displays it to the user. The input is the answer text and department information from the server, and the output is what is displayed to the user. For example, the generated answer "Contact our delivery team immediately" and the contact information for the "delivery team" are displayed on the user's terminal.

[0494] Step 5:

[0495] The server stores the questions and answers received from the user in a database as history. This allows for a quick response if a similar question is entered in the future. The input is the question text and the answer text, and the output is saved in the history database. For example, the question "The food I ordered hasn't arrived" and its answer are saved in the database.

[0496] Step 6:

[0497] If the user enters the same question again, the server references the history database and quickly provides past answers. This allows the system to provide answers efficiently and consistently. The input is the question text received again, and the output is the text of the previous answer. For example, if the user asks again, "My order hasn't arrived," the previous answer "Please contact the delivery team" is immediately provided.

[0498] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0499] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0500] 1. Data preparation

[0501] The server reads the necessary information from a database that stores past consultation examples and FAQ data, and loads it into memory. This preparation creates a system that can respond quickly when a question is entered by a user.

[0502] 2. Getting questions from users

[0503] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question and sends it to the server.

[0504] 3. Recognizing User Emotions

[0505] The server analyzes the received user question and uses an emotion engine to recognize the user's emotions. This recognition is performed using text analysis and natural language processing techniques. For example, emotions such as "troubled," "angry," and "anxious" can be detected from the user's input.

[0506] 4. Database Verification

[0507] The server compares the user's question with past consultation cases and a FAQ database. This database contains past consultation history, frequently asked questions (FAQs), and their answers. The server selects the most appropriate answer and relevant department, taking into account the user's question and emotional state.

[0508] 5. Adjustment and presentation of matching results

[0509] The server identifies the most relevant answer and related department based on the matching results, and adjusts the content of the presentation taking into account the user's emotion recognition results from the emotion engine. For example, if the user is in trouble, the server will provide a more detailed and thorough explanation. The results are then sent to the terminal and presented to the user.

[0510] 6. Preserving and Reusing History

[0511] The server stores the user's questions and answers, which are used to provide a quick and appropriate answer when a similar question is entered in the future. The server also records the user's emotional state along with the history and uses it for future responses.

[0512] 7. Department introduction history management

[0513] The server also stores the history of referrals to related departments. This history includes the reasons and circumstances behind the referral, and this information is referenced when a referral is made again. This allows for consistent responses.

[0514] Specific examples

[0515] For example, if a user types the question "Check on the progress of the project" into a device, the device sends this information to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then compares past consultation cases and the FAQ database to identify the answer "Please contact the Project Management Department" and the "Project Management" department. At this time, a more detailed explanation is added, taking into account the user's emotions. This answer and information about the relevant department are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0516] As described above, this system not only provides fast and accurate answers to user questions and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, thereby improving work efficiency and the user experience.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The server loads a database containing past consultation examples and FAQ data. The server first opens the database file and loads its contents into memory. This preparation process prepares the server for quick search and matching when a question is entered.

[0520] Step 2:

[0521] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question. For example, the user enters "Check the progress of the project."

[0522] Step 3:

[0523] The terminal sends the captured question to the server, and the entered question data is transferred to the server via the network. The server receives this data.

[0524] Step 4:

[0525] The server analyzes the received question text and uses an emotion engine to recognize the user's emotions. For example, the server can detect emotions such as "I'm in trouble" or "I'm anxious" from the text.

[0526] Step 5:

[0527] The server compares the question with past consultation cases and a FAQ database, taking into account the results of emotion recognition. Specifically, it breaks down the user's question into keywords and searches for related entries in the database.

[0528] Step 6:

[0529] The server then uses the matching results to identify relevant answers and relevant departments, such as "Please contact the Project Management department," and adjusts the tone and specificity of the answer based on the emotion recognition results.

[0530] Step 7:

[0531] The server sends the identified answer and information about the relevant department to the terminal. For example, the server may package the information about the "Project Management" department with the answer "Please contact the Project Management Department" and send it to the terminal.

[0532] Step 8:

[0533] The terminal receives the response from the server and presents the relevant department information to the user. The terminal displays the information on the screen in a format that is easy for the user to understand. For example, it displays "To check the progress of the project, please contact the project management department."

[0534] Step 9:

[0535] The server stores the user's questions, their answers, and the emotion recognition results as a history, which can be used to quickly respond to similar questions in the future.

[0536] Step 10:

[0537] The server also stores a history of referrals to related departments, allowing for a consistent response when the user asks the same question again. The server also takes into account the user's past emotional state and provides an appropriate response.

[0538] Through these steps, the system not only provides users with quick and accurate answers and information on where to seek help, but also responds optimally to their emotional state, which is expected to improve both work efficiency and the user experience.

[0539] Example 2

[0540] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0541] Conventional consultation systems often respond mechanically to user questions and provide only uniform answers. Furthermore, they do not take the user's emotional state into consideration, which can lead to frustration and anxiety. Furthermore, there is no mechanism for referencing past consultation history or emotional state, making it difficult to provide a consistent response. This leads to a poor user experience and a lack of work efficiency.

[0542] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0543] In this invention, the server includes means for receiving a question from a user as input, means including an emotion engine for analyzing the input question and recognizing the user's emotion, and means for comparing the analysis results with past consultation cases and an FAQ database. This makes it possible to identify the most appropriate answer and relevant department taking into account the user's emotional state, thereby improving user satisfaction and streamlining operations.

[0544] "User" refers to an individual or organization that utilizes the system to enter questions and obtain information.

[0545] A "question" refers to text information that a user inputs to the system, requesting specific information or advice.

[0546] "Emotion engine" refers to a software module that analyzes and recognizes a user's emotional state from input text information.

[0547] "Past consultation examples" refers to records of questions previously submitted by users and the answers to those questions.

[0548] An "FAQ database" refers to a database that systematically collects and stores frequently asked questions and their answers.

[0549] "Matching" refers to the process of evaluating the relevance of the input question and emotional state by comparing it with past consultation cases and the FAQ database.

[0550] "Relevant department" refers to a department or person within an organization who has the authority and knowledge to provide an appropriate answer to a user's question.

[0551] "History" refers to a record of a user's questions, answers, and emotional state, data that is kept for future reference.

[0552] "Emotional state" refers to information that indicates the psychological state of the user when they input a question, and is recognized by the emotion engine.

[0553] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0554] Hardware and Software Configuration

[0555] The system is built using a server, a terminal, and an emotion engine that performs text analysis. Specific software includes relational database management systems such as MySQL and PostgreSQL for the database, and natural language processing (NLP) tools such as IBM Watson and Microsoft Azure Sentiment Analysis for emotion analysis.

[0556] Data preparation

[0557] The server reads the necessary information from a database that stores past consultation examples and FAQ data and loads it into memory. This prepares the server to respond quickly when a question is entered by a user. Information from the database is extracted using SQL queries and temporarily cached in memory.

[0558] Getting questions from users

[0559] The device receives a question from the user as input. The user enters the question in an input field displayed on the device screen and clicks the send button. The device then sends this question in JSON format to the server. Specifically, the device creates an input field in the user interface (UI), captures the question, and sends it to the server as an HTTP POST request.

[0560] Recognizing user emotions

[0561] The server analyzes the received user question and recognizes the user's emotion using an emotion engine. This recognition is performed using text analysis technology through the emotion engine. For example, it detects whether the user is expressing emotions such as "troubled," "angry," or "anxious."

[0562] Database Collation

[0563] The server compares the user's question and the perceived emotion with the past consultation case and FAQ database, and searches the database with the appropriate SQL query to select the most appropriate answer and relevant department, taking into account the question and emotional state.

[0564] Reconciliation and presentation of match results

[0565] The server identifies the appropriate answer and relevant department based on the matching results. If the user is having trouble, the server adds a more detailed and specific explanation based on the emotion recognition results of the emotion engine. This final answer is sent to the device in JSON format and presented to the user.

[0566] Preserving and reusing history

[0567] The server stores the history of user questions, their answers, and their emotional state, which can be used to provide immediate and appropriate answers when similar questions are entered in the future. The historical data is stored in a database using appropriate SQL queries.

[0568] Department introduction history management

[0569] The server also stores the referral history to related departments in a database. This history includes the reason for the referral and the circumstances surrounding it, and can be referenced the next time a referral is made, allowing for consistent handling.

[0570] Specific examples

[0571] Consider the case where a user types "I would like to check the progress of the project" into a device. The device sends this question to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then searches past consultation cases and a database of FAQs to identify the answer "Please contact the project management department." At this time, it adds a more detailed explanation, taking into account the user's emotions. This answer and information about the relevant departments are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0572] This system not only provides users with quick and accurate answers and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, which is expected to improve work efficiency and the user experience.

[0573] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0574] Step 1:

[0575] The server begins the process of loading past case and FAQ data from a database (e.g., MySQL, PostgreSQL). This information is used for future lookups. Specifically, the server executes SQL queries to extract the necessary data and caches it in memory.

[0576] Input: Database connection information and SQL query

[0577] Output: Cached in-memory consultation examples and FAQ data

[0578] Step 2:

[0579] The terminal accepts a user's question as input. This question is entered through an input field in the user interface and submitted by the user clicking a submit button. The terminal converts this information into JSON format and sends it to the server as an HTTP POST request.

[0580] Input: The question text that the user types into the terminal

[0581] Output: Question data in JSON format sent to the server

[0582] Step 3:

[0583] The server analyzes the question data received from the device using natural language processing (NLP) technology and an emotion engine (e.g., IBM Watson, Microsoft Azure Sentiment Analysis). This process recognizes not only the content of the user's question, but also the emotion hidden in the question (e.g., "troubled," "angry," "anxious").

[0584] Input: JSON format question data received from the terminal

[0585] Output: Question content and emotion recognition results

[0586] Step 4:

[0587] Based on the analysis results, the server compares the question and emotional state with past consultation cases and a database of FAQs. Specifically, it uses SQL queries to search the database and extract the most relevant answers. In doing so, it also takes the user's emotional state into consideration to select the most appropriate answer.

[0588] Input: Question content, emotion recognition results, past consultation examples, and FAQ data

[0589] Output: The most relevant answers as a result of matching and related department information

[0590] Step 5:

[0591] The server formats the answer and related department information based on the matching results. Taking into account the user's emotion recognition results, it adds a more detailed explanation to users who are in trouble, for example. This final response data is converted into JSON format and sent to the device.

[0592] Input: Answer as matching result, related department information, emotion recognition result

[0593] Output: Response data in JSON format to send to the device

[0594] Step 6:

[0595] The terminal displays the response data received from the server on the user interface, allowing the user to obtain an appropriate answer to their question and information on where to seek advice.

[0596] Input: JSON format response data received from the server

[0597] Output: Answers and associated department information displayed in the user interface

[0598] Step 7:

[0599] The server stores the user's question, the answer, and the emotion recognition results in a database, allowing it to respond quickly to similar questions in the future.

[0600] Input: Question, answer, emotion recognition result

[0601] Output: Historical data stored in a database

[0602] Step 8:

[0603] The server also stores the referral history to the relevant department in a database, including the reason and circumstances for the referral, so that it can be referenced the next time a referral is made.

[0604] Input: Referral information, reason for referral and background

[0605] Output: Referral history stored in a database

[0606] (Application example 2)

[0607] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0608] In modern brick-and-mortar stores, users need to be able to quickly and accurately obtain product information. However, conventional methods often fail to respond appropriately to user questions, resulting in a poor user experience. Furthermore, because they do not take into account the user's feelings regarding the question, it is difficult to improve customer satisfaction.

[0609] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question from a user as input, means for comparing the input question with past consultation cases and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, means for converting the user's question into text data using voice input and voice recognition technology, emotion recognition means for analyzing the user's emotions, and means for adjusting the presented content based on the emotion recognition results. This enables flexible responses and efficient product guidance according to the user's emotions.

[0610] The "means for accepting a question from a user as input" refers to an interface that allows a user to input a question to a terminal. This includes functions for accepting information through voice input or text input.

[0611] "Means for comparing the entered question with past consultation examples and an existing FAQ database" is a function for comparing a new question entered by a user with past questions and answers stored in an existing database.

[0612] "Means of identifying the most relevant answer and relevant department based on the matching results and presenting them to the user" is a function that uses the information obtained through matching to select the most appropriate answer and contact point for the user's question and provides them to the user.

[0613] The "means for converting a user's question into text data using voice input and voice recognition technology" is a function that allows a user to input a question by voice and automatically convert the voice data into text data.

[0614] "Emotion recognition means for analyzing user emotions" refers to algorithms or technologies that determine the user's emotions based on the text data entered by the user. For example, it can recognize emotions such as distress or anger.

[0615] The "means for adjusting the content of presentation based on the emotion recognition result" is a function for adjusting the content of answers or guidance according to the emotion of the user after the emotion of the user is determined by the emotion recognition means.

[0616] "Means for saving history and referencing it the next time" is a function that saves user questions, their answers, and the accompanying emotional data in a database, allowing for a quick response when a similar question is entered at a later date.

[0617] "A means of saving referrals to related departments as a history and taking that history into consideration when making a second referral" is a function that records the circumstances and reasons when a user is referred to a specific department, and uses that history when the same user makes another inquiry in the future.

[0618] The present invention relates to a consultation service provider system that aims to improve the user experience in brick-and-mortar stores. This system uses smart glasses and makes full use of voice input and emotion recognition technology to quickly provide appropriate answers to users' questions.

[0619] System configuration

[0620] The system consists of the following main components:

[0621] 1. Smart glasses: For example, the general term "wearable device."

[0622] 2. Server: Deployed in a cloud environment.

[0623] 3. Emotion recognition engine: For example, the generic name "emotion analysis software."

[0624] 4. Database: A data repository for storing user questions, emotional states, and answer history.

[0625] Hardware and Software Use

[0626] The wearable device (smart glasses) has a voice input function and captures the user's questions.

[0627] The server is primarily responsible for analyzing the question data and generating answers.

[0628] Sentiment analysis software recognizes emotions from user input and determines appropriate responses.

[0629] The database uses a cloud database such as AWS RDS.

[0630] Program implementation example

[0631] 1. Retrieving and submitting user questions:

[0632] The user speaks a question into the smart glasses, which then recognize the voice and convert it into text. This process is performed using a speech recognition API.

[0633] 2. Emotion Recognition and Analysis:

[0634] The received text data is sent to a server, where sentiment analysis software analyzes the user's emotions. For example, the text is tagged with "I'm in trouble" or "I'm looking for something." This allows the system to understand the user's emotional state and select an appropriate response.

[0635] 3. Historical comparison:

[0636] Based on the user's text data and emotional state, the server matches the user's past questions with a database of answers, and identifies the most relevant answers and related departments based on the matching results.

[0637] 4. Present the response:

[0638] The answer obtained through the matching is sent to the smart glasses and presented to the user, with the content of the presentation adjusted according to the user's emotions.

[0639] 5. History Preservation:

[0640] All questions, answers, and the user's emotional state are stored in a database, allowing for fast and accurate answers when similar questions are asked in the future.

[0641] Adding specific examples

[0642] Example of operation scene

[0643] A user is shopping and wearing smart glasses. The user asks, "Where is this item?"

[0644] Speak: "Where is this item?"

[0645] Emotion recognition: "I'm in trouble"

[0646] Server response: "It's on the shelf near the register. I'll show you where it is."

[0647] Example prompts to input to the generative AI model

[0648] User Question: "Where is this item?"

[0649] Emotion recognition: "I'm in trouble"

[0650] Past data collation: Product search, in-store guidance history

[0651] API usage: speech recognition API, sentiment analysis software, cloud database

[0652] This system will improve the user experience and make operations in physical stores more efficient.

[0653] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0654] Step 1:

[0655] The user speaks a question into the smart glasses. The smart glasses capture the voice data and convert it into text data using a voice recognition API. Specifically, if the user speaks "Where is this product?", the voice is converted into the text "Where is this product?" The input of this process is voice data, and the output is text data.

[0656] Step 2:

[0657] The user's question data (text data) is sent from the terminal to the server. The terminal then sends the converted text data to the server, which then receives it and prepares it for analysis. The input to this process is text data, and the output is data that can be analyzed on the server side.

[0658] Step 3:

[0659] The server uses an emotion recognition engine to analyze the received text data and recognize the user's emotions. For example, the emotion "troubled" is detected from the text data. Specifically, the emotion analysis software assigns a tag of "troubled." The input for this process is text data, and the output is data with an emotion tag.

[0660] Step 4:

[0661] The server uses emotion-tagged question data to match past consultations and an FAQ database. This matching identifies the most relevant answer and the appropriate related department. The specific operation of the matching is to use a database search to check whether a similar question has been asked in the past and find the appropriate answer. The input to this process is emotion-tagged question data, and the output is the best answer and information on the related department.

[0662] Step 5:

[0663] The server adjusts the answer based on the matching results and emotion recognition results, and prepares to present it to the user. For example, if the server recognizes that the user is "troubled," it adds a more detailed explanation. The input to this process is the optimal answer and emotion tag, and the output is the adjusted answer data.

[0664] Step 6:

[0665] The adjusted answer data is sent from the server to the device (smart glasses) and presented to the user. The smart glasses then provide the received answer data to the user via voice or screen display. Specifically, the glasses provide voice guidance such as, "It's on the shelf near the register. We'll guide you to where the product is." The input for this process is the adjusted answer data, and the output is an audio or visual presentation to the user.

[0666] Step 7:

[0667] The server stores the entire history of user questions, emotion tags, and suggested answers in a database. This allows for a quick and appropriate response when a similar question is entered in the future. The input of this process is the entire history data, and the output is an update to the history database.

[0668] 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.

[0669] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0670] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0671] [Third embodiment]

[0672] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0673] 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.

[0674] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0675] 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.

[0676] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0677] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0678] 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. 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.

[0679] 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.

[0680] 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 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.

[0681] 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.

[0682] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0683] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0684] The present invention relates to a system that provides a consultation point for efficiently advancing business operations. A specific embodiment of this system will be described below.

[0685] This system is mainly composed of a server and a terminal. Users access the system through the terminal and input a question. The server accepts the question, searches for an appropriate answer, and sends the result to the terminal.

[0686] 1. Get the user's question

[0687] The terminal accepts questions from the user as input. The user enters the question according to the system's prompts, and the question is collected by the terminal. For example, if the user asks, "How do I connect office automation equipment?", the question is entered into the terminal and sent directly to the server.

[0688] 2. Database Verification

[0689] The server receives the user's input question and compares it with past consultations and a database of frequently asked questions (FAQs) that contain past consultation history and answers. The server searches through this data to identify the answer and relevant department that is most relevant to the user's question.

[0690] 3. Presentation of matching results

[0691] The server identifies the most relevant answer and the relevant department based on the matching results and sends them to the terminal. The terminal then presents them to the user. For example, in response to a question such as "How do I connect my office automation equipment?", the server presents the answer "Please contact the office automation support team" and the relevant department "Office Automation Support."

[0692] 4. Preserving and Reusing History

[0693] The server stores a history of entered questions and their answers. This history is referenced the next time a similar question is entered, and is used to efficiently provide an appropriate answer. For example, if the question "How do I connect my office automation equipment?" was previously asked, and the answer was saved as "Please contact the office automation support team," this answer will be provided immediately the next time the same question is entered.

[0694] 5. Department introduction history management

[0695] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the user asks the same question multiple times. For example, if a user asks "how to connect office equipment" and is referred to the "Office Support" department, the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0696] Specific examples

[0697] As a specific example, suppose a user enters the question "Check on the progress of the project" into a terminal. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This answer and information about the relevant department are presented to the user via the terminal. The history of this exchange is also saved on the server and can be referenced if a similar question arises in the future.

[0698] As described above, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. This system effectively utilizes past consultation history and FAQ data to enable quick and accurate responses.

[0699] The processing flow will be explained below.

[0700] Step 1:

[0701] The server loads a database that stores past consultation cases and FAQ data. The server opens the database file and loads its contents into memory, preparing it for quick matching when a question is entered.

[0702] Step 2:

[0703] The terminal accepts as input a question from the user, who types the question in response to a prompt displayed on the terminal's screen and the question is captured by the terminal.

[0704] Step 3:

[0705] The terminal sends the captured question to the server, and the question data entered by the user is transferred from the terminal to the server via the network.

[0706] Step 4:

[0707] The server compares the received question with past consultations and FAQ data in its database. Specifically, the server breaks down the user's question into keywords and phrases and compares them with relevant entries in the database.

[0708] Step 5:

[0709] The server identifies the most relevant answers and related departments based on the matching results. The server calculates a correlation score for each entry in the database and selects the entry with the highest score.

[0710] Step 6:

[0711] The server sends the identified answer and information on the relevant department to the terminal, and then the server packages the best answer to the user's question and information on the department to be contacted, and returns it to the terminal.

[0712] Step 7:

[0713] The terminal presents the answer received from the server and the information on the relevant department to the user, who can then check the presented answer and the information on the relevant department on the screen of the terminal.

[0714] Step 8:

[0715] The server stores a history of user questions and their answers, and the history data is referenced to provide quick answers to future queries.

[0716] Step 9:

[0717] The server also stores a history of referrals to relevant departments, so that if the same question is asked again, the same department will be referred to, taking into account the history information.

[0718] Through the above steps, the system is able to provide users with prompt and accurate answers to their questions and information on where to seek advice.

[0719] Example 1

[0720] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0721] In conventional business support systems, there are many cases where users are unable to provide appropriate answers to their questions or refer them to relevant departments quickly and accurately. In addition, it is difficult to provide consistent answers to users who ask the same question multiple times, which leads to a decrease in business efficiency.

[0722] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0723] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with a past consultation history database and an FAQ database, means for identifying the most relevant answer and relevant department based on the comparison results and presenting them to the user, and means for the server to store the user's question and its answer in the history database, thereby enabling the provision of quick and accurate responses to user questions and history management for consistent response.

[0724] "User" refers to any person or entity that accesses the system and enters a query.

[0725] A "question" refers to an inquiry or consultation that a user inputs to the system.

[0726] "Terminal" refers to a device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[0727] The term "server" refers to a central processing unit that receives questions entered by users, processes them, and sends the results to the terminal.

[0728] "Means for receiving" refers to a method or function by which the system receives a question entered by a user.

[0729] "Matching method" refers to the method or algorithm used to compare and search the input query against information in the database.

[0730] "Answer" refers to a solution or piece of information provided to a user's question.

[0731] "Related departments" refers to the departments and teams involved in the user's question.

[0732] "Presentation means" refers to the method or technology used by the server to present search results or answers to the user.

[0733] "History database" refers to a database for storing previously entered questions and their answers.

[0734] "Storage means" refers to the method or technology by which the server stores received questions and their answers in a history database.

[0735] The "consultation history database" refers to a database that stores past consultations and their responses.

[0736] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0737] "Consistent response" means that the same quality of response is always provided even when the same question is entered repeatedly.

[0738] The present invention relates to a system that provides a consultation service for efficiently advancing business operations. This system is mainly composed of a server and a terminal. Here, a specific embodiment of this system will be described.

[0739] Get the user's question

[0740] The terminal accepts questions from the user as input. The user inputs the question following the system's prompts, and the question is collected by the terminal. For example, if a user asks, "How do I connect office equipment?", the question is entered into the terminal and sent directly to the server. The terminal can be a computer, smartphone, tablet, or other device.

[0741] Database Collation

[0742] The server receives questions sent from the device and compares them with an internal database. This database includes past consultation history and FAQs (frequently asked questions) and their answers. The server uses a generative AI model to search this data and identify the most relevant answer and relevant department for the user's question. For example, the server might search the database for the question "How do I connect office equipment?" to find the most relevant past consultation examples and FAQs.

[0743] Presentation of matching results

[0744] The server sends the most relevant answer and the associated department identified based on the database match to the terminal, which then displays it to the user. For example, in response to the question "How do I connect my office automation equipment?", the server displays the answer "Please contact the office automation support team" and the associated department "Office Automation Support."

[0745] Preserving and reusing history

[0746] The server stores the history of entered questions and their answers in a database. This history is used for reference the next time a question is asked. For example, if a user enters the same question again, "How do I connect to office equipment?", the server immediately provides the previously saved information.

[0747] Department introduction history management

[0748] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the same question is asked repeatedly. For example, if a user is referred to the "OA Support" department in response to a question about "how to connect office equipment," the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[0749] Specific examples

[0750] As a specific example, suppose a user types "I would like to know about the progress of the project" into their device. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This information is presented to the user via their device. The history of this exchange is also saved on the server and can be referenced the next time a similar question is asked.

[0751] Example prompts to input to the generative AI model

[0752] An example prompt might look like this:

[0753] "How do I connect my office automation equipment?"

[0754] "I want to check on the progress of a project. Which department should I contact?"

[0755] "I would like to know the steps to install new software."

[0756] In this way, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. The present invention makes it possible to respond quickly and accurately by effectively utilizing past consultation history and FAQ data.

[0757] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0758] Step 1: The user operates the terminal and inputs a question.

[0759] The user inputs a question into an input field on the terminal. For example, the user inputs "How do I connect OA equipment?" and clicks the send button. The input data is a text-format question and is obtained from the input field on the terminal.

[0760] Input: The question entered by the user

[0761] Output: The question text entered

[0762] Step 2: The terminal sends the user's input to the server.

[0763] The terminal sends the question entered by the user to the server. The transmission is performed using an HTTP request or other communication protocol. For example, the terminal sends the entered question, "How do I connect to office equipment?" to the server.

[0764] Input: Question text obtained by the device

[0765] Output: The question data sent to the server

[0766] Step 3: The server receives the query and checks it against its database.

[0767] The server receives questions sent from the device. It analyzes the questions and compares them with past consultation history and an FAQ database. This matching uses a generative AI model to find the most relevant answer. For example, the server receives the question "How do I connect office equipment?" and searches for relevant answers in the database.

[0768] Input: Question data received from the terminal

[0769] Output: Matching responses and associated department information

[0770] Step 4: The server sends the matching result to the terminal.

[0771] The server sends the answer and related department information identified as a result of the database check to the terminal, for example, the answer "Please contact the OA support team" and the "OA support" department information to the terminal.

[0772] Input: Matched answers and related department information

[0773] Output: Answers and department information sent to the terminal

[0774] Step 5: The terminal displays the results sent from the server to the user.

[0775] The terminal displays the response and department information received from the server to the user. The user can see the information on the service screen that says, "Please contact the OA support team regarding how to connect the OA equipment."

[0776] Input: Response received from the server and department information

[0777] Output: Answers and department information presented to the user

[0778] Step 6: The server stores the history of questions and answers.

[0779] The server stores user questions and their answers in a history database. This history data allows for quick matching the next time a similar question is asked. For example, the server stores the question "How do I connect my office automation equipment?" and the answer "Please contact the office automation support team" as history.

[0780] Input: Question and its answer

[0781] Output: Questions and answers stored in a history database

[0782] Step 7: The server stores the department referral history.

[0783] The server stores the history of when a user was referred to a specific department and the reason for that referral in a history database. This allows for a consistent response if the same question is asked again. For example, the server stores the history of when a user was referred to the "OA Support" department regarding "how to connect office automation equipment" and the reason for that referral.

[0784] Input: Department referred and reason

[0785] Output: History of department referrals stored in the history database

[0786] In this way, the system efficiently processes user questions and provides appropriate consultation, thereby improving business efficiency.

[0787] (Application example 1)

[0788] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0789] Conventional support systems have difficulty responding to user questions quickly and appropriately. Furthermore, when users repeatedly ask the same question, the system is unable to provide consistent responses, causing significant user frustration. Furthermore, in food delivery services, delays in responses regarding order status and problems can lead to lower customer satisfaction.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0791] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with past consultation examples and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, and means for using a generative AI model to generate an optimal answer to the user's question. This makes it possible to provide a quick and appropriate answer to the user's question, thereby improving customer satisfaction in food delivery services.

[0792] The "means for accepting a question from a user as an input" refers to an interface or function for receiving a question that a user has input to the system.

[0793] "Means for checking the entered question against past consultation cases and a database of pre-created FAQs" refers to the process or function for comparing the question received from the user with past consultation cases in the database and pre-created FAQ data to confirm relevance.

[0794] "Means for identifying the most relevant answer and related department based on the matching results and presenting them to the user" is a function for selecting the most appropriate answer and the department responsible for it from the matching results and displaying them to the user.

[0795] "Means of using a generative AI model to generate optimal answers to user questions" refers to processes or functions that use AI technology to generate optimal answers to user questions.

[0796] This invention is a support system that aims to enable users to obtain prompt and appropriate answers to questions related to food delivery services. Specifically, this system uses AI technology to analyze questions from users, compares them with past consultation cases and an FAQ database, and generates and provides the most appropriate answers.

[0797] 1. Obtaining and inputting user questions

[0798] A user accesses the application using a smartphone and inputs a question. The smartphone acts as an interface and sends the input question to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the question is sent to the server.

[0799] 2. Database Matching

[0800] The server processes the question received from the user and compares it with past inquiries and created FAQ data in the database. The server performs this process using database management software. For example, in response to a question such as "The food I ordered hasn't arrived," the server searches to see if similar questions have been asked in the past, and finds the answer "Please contact the delivery team."

[0801] 3. Use of generative AI models

[0802] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model performs advanced calculations to appropriately respond to the user's doubts. This AI model uses natural language processing technology, for example, to understand the intent of the user's question and generate a relevant answer. An example of a prompt sentence is, "Based on the question entered by the user, please compare it with past FAQ data and provide the optimal answer and relevant department."

[0803] 4. Matching results and optimal answer presentation

[0804] The server sends the matching results and the optimal answer obtained by the generative AI model to the smartphone, which then displays it to the user. For example, the user can confirm the answer "Please contact the delivery team" along with the "delivery team" contact information.

[0805] 5. Preserving and Reusing History

[0806] The server saves the entered questions and their answers as a history in a database. This history is referenced the next time a similar question is entered, allowing for a quick response. This allows for a consistent response even if the user asks the same question multiple times.

[0807] Through the above steps, the system can provide quick and appropriate answers to users' questions and improve customer satisfaction in food delivery services.

[0808] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0809] Step 1:

[0810] A user inputs a question through a smartphone device. The input question is collected by the device's interface. The input (question text) is sent to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the text is passed from the device to the server.

[0811] Step 2:

[0812] The server checks the received question against a database, which stores past consultation cases and FAQ data. The server uses the question text to search the database and find related questions and their answers. The entered question text is used to obtain a matching result (the best answer) from the database. For example, in response to a question such as "The food I ordered hasn't arrived," the server finds the answer "Please contact the delivery team" from the past database.

[0813] Step 3:

[0814] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model uses natural language processing technology to analyze the intent of the question and generate an appropriate answer text. The input is the question text, and the output is the generated answer text. For example, in response to the question "The food I ordered hasn't arrived," the AI ​​model generates an answer such as "Please contact our delivery team immediately."

[0815] Step 4:

[0816] The server sends the generated answer and the relevant department information to the terminal, which then displays it to the user. The input is the answer text and department information from the server, and the output is what is displayed to the user. For example, the generated answer "Contact our delivery team immediately" and the contact information for the "delivery team" are displayed on the user's terminal.

[0817] Step 5:

[0818] The server stores the questions and answers received from the user in a database as history. This allows for a quick response if a similar question is entered in the future. The input is the question text and the answer text, and the output is saved in the history database. For example, the question "The food I ordered hasn't arrived" and its answer are saved in the database.

[0819] Step 6:

[0820] If the user enters the same question again, the server references the history database and quickly provides past answers. This allows the system to provide answers efficiently and consistently. The input is the question text received again, and the output is the text of the previous answer. For example, if the user asks again, "My order hasn't arrived," the previous answer "Please contact the delivery team" is immediately provided.

[0821] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0822] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0823] 1. Data preparation

[0824] The server reads the necessary information from a database that stores past consultation examples and FAQ data, and loads it into memory. This preparation creates a system that can respond quickly when a question is entered by a user.

[0825] 2. Getting questions from users

[0826] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question and sends it to the server.

[0827] 3. Recognizing User Emotions

[0828] The server analyzes the received user question and uses an emotion engine to recognize the user's emotions. This recognition is performed using text analysis and natural language processing techniques. For example, emotions such as "troubled," "angry," and "anxious" can be detected from the user's input.

[0829] 4. Database Verification

[0830] The server compares the user's question with past consultation cases and a FAQ database. This database contains past consultation history, frequently asked questions (FAQs), and their answers. The server selects the most appropriate answer and relevant department, taking into account the user's question and emotional state.

[0831] 5. Adjustment and presentation of matching results

[0832] The server identifies the most relevant answer and related department based on the matching results, and adjusts the content of the presentation taking into account the user's emotion recognition results from the emotion engine. For example, if the user is in trouble, the server will provide a more detailed and thorough explanation. The results are then sent to the terminal and presented to the user.

[0833] 6. Preserving and Reusing History

[0834] The server stores the user's questions and answers, which are used to provide a quick and appropriate answer when a similar question is entered in the future. The server also records the user's emotional state along with the history and uses it for future responses.

[0835] 7. Department introduction history management

[0836] The server also stores the history of referrals to related departments. This history includes the reasons and circumstances behind the referral, and this information is referenced when a referral is made again. This allows for consistent responses.

[0837] Specific examples

[0838] For example, if a user types the question "Check on the progress of the project" into a device, the device sends this information to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then compares past consultation cases and the FAQ database to identify the answer "Please contact the Project Management Department" and the "Project Management" department. At this time, a more detailed explanation is added, taking into account the user's emotions. This answer and information about the relevant department are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0839] As described above, this system not only provides fast and accurate answers to user questions and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, thereby improving work efficiency and the user experience.

[0840] The processing flow will be explained below.

[0841] Step 1:

[0842] The server loads a database containing past consultation examples and FAQ data. The server first opens the database file and loads its contents into memory. This preparation process prepares the server for quick search and matching when a question is entered.

[0843] Step 2:

[0844] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question. For example, the user enters "Check the progress of the project."

[0845] Step 3:

[0846] The terminal sends the captured question to the server, and the entered question data is transferred to the server via the network. The server receives this data.

[0847] Step 4:

[0848] The server analyzes the received question text and uses an emotion engine to recognize the user's emotions. For example, the server can detect emotions such as "I'm in trouble" or "I'm anxious" from the text.

[0849] Step 5:

[0850] The server compares the question with past consultation cases and a FAQ database, taking into account the results of emotion recognition. Specifically, it breaks down the user's question into keywords and searches for related entries in the database.

[0851] Step 6:

[0852] The server then uses the matching results to identify relevant answers and relevant departments, such as "Please contact the Project Management department," and adjusts the tone and specificity of the answer based on the emotion recognition results.

[0853] Step 7:

[0854] The server sends the identified answer and information about the relevant department to the terminal. For example, the server may package the information about the "Project Management" department with the answer "Please contact the Project Management Department" and send it to the terminal.

[0855] Step 8:

[0856] The terminal receives the response from the server and presents the relevant department information to the user. The terminal displays the information on the screen in a format that is easy for the user to understand. For example, it displays "To check the progress of the project, please contact the project management department."

[0857] Step 9:

[0858] The server stores the user's questions, their answers, and the emotion recognition results as a history, which can be used to quickly respond to similar questions in the future.

[0859] Step 10:

[0860] The server also stores a history of referrals to related departments, allowing for a consistent response when the user asks the same question again. The server also takes into account the user's past emotional state and provides an appropriate response.

[0861] Through these steps, the system not only provides users with quick and accurate answers and information on where to seek help, but also responds optimally to their emotional state, which is expected to improve both work efficiency and the user experience.

[0862] Example 2

[0863] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0864] Conventional consultation systems often respond mechanically to user questions and provide only uniform answers. Furthermore, they do not take the user's emotional state into consideration, which can lead to frustration and anxiety. Furthermore, there is no mechanism for referencing past consultation history or emotional state, making it difficult to provide a consistent response. This leads to a poor user experience and a lack of work efficiency.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0866] In this invention, the server includes means for receiving a question from a user as input, means including an emotion engine for analyzing the input question and recognizing the user's emotion, and means for comparing the analysis results with past consultation cases and an FAQ database. This makes it possible to identify the most appropriate answer and relevant department taking into account the user's emotional state, thereby improving user satisfaction and streamlining operations.

[0867] "User" refers to an individual or organization that utilizes the system to enter questions and obtain information.

[0868] A "question" refers to text information that a user inputs to the system, requesting specific information or advice.

[0869] "Emotion engine" refers to a software module that analyzes and recognizes a user's emotional state from input text information.

[0870] "Past consultation examples" refers to records of questions previously submitted by users and the answers to those questions.

[0871] An "FAQ database" refers to a database that systematically collects and stores frequently asked questions and their answers.

[0872] "Matching" refers to the process of evaluating the relevance of the input question and emotional state by comparing it with past consultation cases and the FAQ database.

[0873] "Relevant department" refers to a department or person within an organization who has the authority and knowledge to provide an appropriate answer to a user's question.

[0874] "History" refers to a record of a user's questions, answers, and emotional state, data that is kept for future reference.

[0875] "Emotional state" refers to information that indicates the psychological state of the user when they input a question, and is recognized by the emotion engine.

[0876] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[0877] Hardware and Software Configuration

[0878] The system is built using a server, a terminal, and an emotion engine that performs text analysis. Specific software includes relational database management systems such as MySQL and PostgreSQL for the database, and natural language processing (NLP) tools such as IBM Watson and Microsoft Azure Sentiment Analysis for emotion analysis.

[0879] Data preparation

[0880] The server reads the necessary information from a database that stores past consultation examples and FAQ data and loads it into memory. This prepares the server to respond quickly when a question is entered by a user. Information from the database is extracted using SQL queries and temporarily cached in memory.

[0881] Getting questions from users

[0882] The device receives a question from the user as input. The user enters the question in an input field displayed on the device screen and clicks the send button. The device then sends this question in JSON format to the server. Specifically, the device creates an input field in the user interface (UI), captures the question, and sends it to the server as an HTTP POST request.

[0883] Recognizing user emotions

[0884] The server analyzes the received user question and recognizes the user's emotion using an emotion engine. This recognition is performed using text analysis technology through the emotion engine. For example, it detects whether the user is expressing emotions such as "troubled," "angry," or "anxious."

[0885] Database Collation

[0886] The server compares the user's question and the perceived emotion with the past consultation case and FAQ database, and searches the database with the appropriate SQL query to select the most appropriate answer and relevant department, taking into account the question and emotional state.

[0887] Reconciliation and presentation of match results

[0888] The server identifies the appropriate answer and relevant department based on the matching results. If the user is having trouble, the server adds a more detailed and specific explanation based on the emotion recognition results of the emotion engine. This final answer is sent to the device in JSON format and presented to the user.

[0889] Preserving and reusing history

[0890] The server stores the history of user questions, their answers, and their emotional state, which can be used to provide immediate and appropriate answers when similar questions are entered in the future. The historical data is stored in a database using appropriate SQL queries.

[0891] Department introduction history management

[0892] The server also stores the referral history to related departments in a database. This history includes the reason for the referral and the circumstances surrounding it, and can be referenced the next time a referral is made, allowing for consistent handling.

[0893] Specific examples

[0894] Consider the case where a user types "I would like to check the progress of the project" into a device. The device sends this question to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then searches past consultation cases and a database of FAQs to identify the answer "Please contact the project management department." At this time, it adds a more detailed explanation, taking into account the user's emotions. This answer and information about the relevant departments are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[0895] This system not only provides users with quick and accurate answers and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, which is expected to improve work efficiency and the user experience.

[0896] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0897] Step 1:

[0898] The server begins the process of loading past case and FAQ data from a database (e.g., MySQL, PostgreSQL). This information is used for future lookups. Specifically, the server executes SQL queries to extract the necessary data and caches it in memory.

[0899] Input: Database connection information and SQL query

[0900] Output: Cached in-memory consultation examples and FAQ data

[0901] Step 2:

[0902] The terminal accepts a user's question as input. This question is entered through an input field in the user interface and submitted by the user clicking a submit button. The terminal converts this information into JSON format and sends it to the server as an HTTP POST request.

[0903] Input: The question text that the user types into the terminal

[0904] Output: Question data in JSON format sent to the server

[0905] Step 3:

[0906] The server analyzes the question data received from the device using natural language processing (NLP) technology and an emotion engine (e.g., IBM Watson, Microsoft Azure Sentiment Analysis). This process recognizes not only the content of the user's question, but also the emotion hidden in the question (e.g., "troubled," "angry," "anxious").

[0907] Input: JSON format question data received from the terminal

[0908] Output: Question content and emotion recognition results

[0909] Step 4:

[0910] Based on the analysis results, the server compares the question and emotional state with past consultation cases and a database of FAQs. Specifically, it uses SQL queries to search the database and extract the most relevant answers. In doing so, it also takes the user's emotional state into consideration to select the most appropriate answer.

[0911] Input: Question content, emotion recognition results, past consultation examples, and FAQ data

[0912] Output: The most relevant answers as a result of matching and related department information

[0913] Step 5:

[0914] The server formats the answer and related department information based on the matching results. Taking into account the user's emotion recognition results, it adds a more detailed explanation to users who are in trouble, for example. This final response data is converted into JSON format and sent to the device.

[0915] Input: Answer as matching result, related department information, emotion recognition result

[0916] Output: Response data in JSON format to send to the device

[0917] Step 6:

[0918] The terminal displays the response data received from the server on the user interface, allowing the user to obtain an appropriate answer to their question and information on where to seek advice.

[0919] Input: JSON format response data received from the server

[0920] Output: Answers and associated department information displayed in the user interface

[0921] Step 7:

[0922] The server stores the user's question, the answer, and the emotion recognition results in a database, allowing it to respond quickly to similar questions in the future.

[0923] Input: Question, answer, emotion recognition result

[0924] Output: Historical data stored in a database

[0925] Step 8:

[0926] The server also stores the referral history to the relevant department in a database, including the reason and circumstances for the referral, so that it can be referenced the next time a referral is made.

[0927] Input: Referral information, reason for referral and background

[0928] Output: Referral history stored in a database

[0929] (Application example 2)

[0930] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0931] In modern brick-and-mortar stores, users need to be able to quickly and accurately obtain product information. However, conventional methods often fail to respond appropriately to user questions, resulting in a poor user experience. Furthermore, because they do not take into account the user's feelings regarding the question, it is difficult to improve customer satisfaction.

[0932] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question from a user as input, means for comparing the input question with past consultation cases and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, means for converting the user's question into text data using voice input and voice recognition technology, emotion recognition means for analyzing the user's emotions, and means for adjusting the presented content based on the emotion recognition results. This enables flexible responses and efficient product guidance according to the user's emotions.

[0933] The "means for accepting a question from a user as input" refers to an interface that allows a user to input a question to a terminal. This includes functions for accepting information through voice input or text input.

[0934] "Means for comparing the entered question with past consultation examples and an existing FAQ database" is a function for comparing a new question entered by a user with past questions and answers stored in an existing database.

[0935] "Means of identifying the most relevant answer and relevant department based on the matching results and presenting them to the user" is a function that uses the information obtained through matching to select the most appropriate answer and contact point for the user's question and provides them to the user.

[0936] The "means for converting a user's question into text data using voice input and voice recognition technology" is a function that allows a user to input a question by voice and automatically convert the voice data into text data.

[0937] "Emotion recognition means for analyzing user emotions" refers to algorithms or technologies that determine the user's emotions based on the text data entered by the user. For example, it can recognize emotions such as distress or anger.

[0938] The "means for adjusting the content of presentation based on the emotion recognition result" is a function for adjusting the content of answers or guidance according to the emotion of the user after the emotion of the user is determined by the emotion recognition means.

[0939] "Means for saving history and referencing it the next time" is a function that saves user questions, their answers, and the accompanying emotional data in a database, allowing for a quick response when a similar question is entered at a later date.

[0940] "A means of saving referrals to related departments as a history and taking that history into consideration when making a second referral" is a function that records the circumstances and reasons when a user is referred to a specific department, and uses that history when the same user makes another inquiry in the future.

[0941] The present invention relates to a consultation service provider system that aims to improve the user experience in brick-and-mortar stores. This system uses smart glasses and makes full use of voice input and emotion recognition technology to quickly provide appropriate answers to users' questions.

[0942] System configuration

[0943] The system consists of the following main components:

[0944] 1. Smart glasses: For example, the general term "wearable device."

[0945] 2. Server: Deployed in a cloud environment.

[0946] 3. Emotion recognition engine: For example, the generic name "emotion analysis software."

[0947] 4. Database: A data repository for storing user questions, emotional states, and answer history.

[0948] Hardware and Software Use

[0949] The wearable device (smart glasses) has a voice input function and captures the user's questions.

[0950] The server is primarily responsible for analyzing the question data and generating answers.

[0951] Sentiment analysis software recognizes emotions from user input and determines appropriate responses.

[0952] The database uses a cloud database such as AWS RDS.

[0953] Program implementation example

[0954] 1. Retrieving and submitting user questions:

[0955] The user speaks a question into the smart glasses, which then recognize the voice and convert it into text. This process is performed using a speech recognition API.

[0956] 2. Emotion Recognition and Analysis:

[0957] The received text data is sent to a server, where sentiment analysis software analyzes the user's emotions. For example, the text is tagged with "I'm in trouble" or "I'm looking for something." This allows the system to understand the user's emotional state and select an appropriate response.

[0958] 3. Historical comparison:

[0959] Based on the user's text data and emotional state, the server matches the user's past questions with a database of answers, and identifies the most relevant answers and related departments based on the matching results.

[0960] 4. Present the response:

[0961] The answer obtained through the matching is sent to the smart glasses and presented to the user, with the content of the presentation adjusted according to the user's emotions.

[0962] 5. History Preservation:

[0963] All questions, answers, and the user's emotional state are stored in a database, allowing for fast and accurate answers when similar questions are asked in the future.

[0964] Adding specific examples

[0965] Example of operation scene

[0966] A user is shopping and wearing smart glasses. The user asks, "Where is this item?"

[0967] Speak: "Where is this item?"

[0968] Emotion recognition: "I'm in trouble"

[0969] Server response: "It's on the shelf near the register. I'll show you where it is."

[0970] Example prompts to input to the generative AI model

[0971] User Question: "Where is this item?"

[0972] Emotion recognition: "I'm in trouble"

[0973] Past data collation: Product search, in-store guidance history

[0974] API usage: speech recognition API, sentiment analysis software, cloud database

[0975] This system will improve the user experience and make operations in physical stores more efficient.

[0976] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0977] Step 1:

[0978] The user speaks a question into the smart glasses. The smart glasses capture the voice data and convert it into text data using a voice recognition API. Specifically, if the user speaks "Where is this product?", the voice is converted into the text "Where is this product?" The input of this process is voice data, and the output is text data.

[0979] Step 2:

[0980] The user's question data (text data) is sent from the terminal to the server. The terminal then sends the converted text data to the server, which then receives it and prepares it for analysis. The input to this process is text data, and the output is data that can be analyzed on the server side.

[0981] Step 3:

[0982] The server uses an emotion recognition engine to analyze the received text data and recognize the user's emotions. For example, the emotion "troubled" is detected from the text data. Specifically, the emotion analysis software assigns a tag of "troubled." The input for this process is text data, and the output is data with an emotion tag.

[0983] Step 4:

[0984] The server uses emotion-tagged question data to match past consultations and an FAQ database. This matching identifies the most relevant answer and the appropriate related department. The specific operation of the matching is to use a database search to check whether a similar question has been asked in the past and find the appropriate answer. The input to this process is emotion-tagged question data, and the output is the best answer and information on the related department.

[0985] Step 5:

[0986] The server adjusts the answer based on the matching results and emotion recognition results, and prepares to present it to the user. For example, if the server recognizes that the user is "troubled," it adds a more detailed explanation. The input to this process is the optimal answer and emotion tag, and the output is the adjusted answer data.

[0987] Step 6:

[0988] The adjusted answer data is sent from the server to the device (smart glasses) and presented to the user. The smart glasses then provide the received answer data to the user via voice or screen display. Specifically, the glasses provide voice guidance such as, "It's on the shelf near the register. We'll guide you to where the product is." The input for this process is the adjusted answer data, and the output is an audio or visual presentation to the user.

[0989] Step 7:

[0990] The server stores the entire history of user questions, emotion tags, and suggested answers in a database. This allows for a quick and appropriate response when a similar question is entered in the future. The input of this process is the entire history data, and the output is an update to the history database.

[0991] 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.

[0992] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0993] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0994] [Fourth embodiment]

[0995] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0996] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0997] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0998] 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.

[0999] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1000] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1001] 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. 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.

[1002] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1003] 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.

[1004] 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 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.

[1005] 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.

[1006] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1007] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1008] The present invention relates to a system that provides a consultation point for efficiently advancing business operations. A specific embodiment of this system will be described below.

[1009] This system is mainly composed of a server and a terminal. Users access the system through the terminal and input a question. The server accepts the question, searches for an appropriate answer, and sends the result to the terminal.

[1010] 1. Get the user's question

[1011] The terminal accepts questions from the user as input. The user enters the question according to the system's prompts, and the question is collected by the terminal. For example, if the user asks, "How do I connect office automation equipment?", the question is entered into the terminal and sent directly to the server.

[1012] 2. Database Verification

[1013] The server receives the user's input question and compares it with past consultations and a database of frequently asked questions (FAQs) that contain past consultation history and answers. The server searches through this data to identify the answer and relevant department that is most relevant to the user's question.

[1014] 3. Presentation of matching results

[1015] The server identifies the most relevant answer and the relevant department based on the matching results and sends them to the terminal. The terminal then presents them to the user. For example, in response to a question such as "How do I connect my office automation equipment?", the server presents the answer "Please contact the office automation support team" and the relevant department "Office Automation Support."

[1016] 4. Preserving and Reusing History

[1017] The server stores a history of entered questions and their answers. This history is referenced the next time a similar question is entered, and is used to efficiently provide an appropriate answer. For example, if the question "How do I connect my office automation equipment?" was previously asked, and the answer was saved as "Please contact the office automation support team," this answer will be provided immediately the next time the same question is entered.

[1018] 5. Department introduction history management

[1019] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the user asks the same question multiple times. For example, if a user asks "how to connect office equipment" and is referred to the "Office Support" department, the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[1020] Specific examples

[1021] As a specific example, suppose a user enters the question "Check on the progress of the project" into a terminal. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This answer and information about the relevant department are presented to the user via the terminal. The history of this exchange is also saved on the server and can be referenced if a similar question arises in the future.

[1022] As described above, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. This system effectively utilizes past consultation history and FAQ data to enable quick and accurate responses.

[1023] The processing flow will be explained below.

[1024] Step 1:

[1025] The server loads a database that stores past consultation cases and FAQ data. The server opens the database file and loads its contents into memory, preparing it for quick matching when a question is entered.

[1026] Step 2:

[1027] The terminal accepts as input a question from the user, who types the question in response to a prompt displayed on the terminal's screen and the question is captured by the terminal.

[1028] Step 3:

[1029] The terminal sends the captured question to the server, and the question data entered by the user is transferred from the terminal to the server via the network.

[1030] Step 4:

[1031] The server compares the received question with past consultations and FAQ data in its database. Specifically, the server breaks down the user's question into keywords and phrases and compares them with relevant entries in the database.

[1032] Step 5:

[1033] The server identifies the most relevant answers and related departments based on the matching results. The server calculates a correlation score for each entry in the database and selects the entry with the highest score.

[1034] Step 6:

[1035] The server sends the identified answer and information on the relevant department to the terminal, and then the server packages the best answer to the user's question and information on the department to be contacted, and returns it to the terminal.

[1036] Step 7:

[1037] The terminal presents the answer received from the server and the information on the relevant department to the user, who can then check the presented answer and the information on the relevant department on the screen of the terminal.

[1038] Step 8:

[1039] The server stores a history of user questions and their answers, and the history data is referenced to provide quick answers to future queries.

[1040] Step 9:

[1041] The server also stores a history of referrals to relevant departments, so that if the same question is asked again, the same department will be referred to, taking into account the history information.

[1042] Through the above steps, the system is able to provide users with prompt and accurate answers to their questions and information on where to seek advice.

[1043] Example 1

[1044] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1045] In conventional business support systems, there are many cases where users are unable to provide appropriate answers to their questions or refer them to relevant departments quickly and accurately. In addition, it is difficult to provide consistent answers to users who ask the same question multiple times, which leads to a decrease in business efficiency.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1047] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with a past consultation history database and an FAQ database, means for identifying the most relevant answer and relevant department based on the comparison results and presenting them to the user, and means for the server to store the user's question and its answer in the history database, thereby enabling the provision of quick and accurate responses to user questions and history management for consistent response.

[1048] "User" refers to any person or entity that accesses the system and enters a query.

[1049] A "question" refers to an inquiry or consultation that a user inputs to the system.

[1050] "Terminal" refers to a device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[1051] The term "server" refers to a central processing unit that receives questions entered by users, processes them, and sends the results to the terminal.

[1052] "Means for receiving" refers to a method or function by which the system receives a question entered by a user.

[1053] "Matching method" refers to the method or algorithm used to compare and search the input query against information in the database.

[1054] "Answer" refers to a solution or piece of information provided to a user's question.

[1055] "Related departments" refers to the departments and teams involved in the user's question.

[1056] "Presentation means" refers to the method or technology used by the server to present search results or answers to the user.

[1057] "History database" refers to a database for storing previously entered questions and their answers.

[1058] "Storage means" refers to the method or technology by which the server stores received questions and their answers in a history database.

[1059] The "consultation history database" refers to a database that stores past consultations and their responses.

[1060] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1061] "Consistent response" means that the same quality of response is always provided even when the same question is entered repeatedly.

[1062] The present invention relates to a system that provides a consultation service for efficiently advancing business operations. This system is mainly composed of a server and a terminal. Here, a specific embodiment of this system will be described.

[1063] Get the user's question

[1064] The terminal accepts questions from the user as input. The user inputs the question following the system's prompts, and the question is collected by the terminal. For example, if a user asks, "How do I connect office equipment?", the question is entered into the terminal and sent directly to the server. The terminal can be a computer, smartphone, tablet, or other device.

[1065] Database Collation

[1066] The server receives questions sent from the device and compares them with an internal database. This database includes past consultation history and FAQs (frequently asked questions) and their answers. The server uses a generative AI model to search this data and identify the most relevant answer and relevant department for the user's question. For example, the server might search the database for the question "How do I connect office equipment?" to find the most relevant past consultation examples and FAQs.

[1067] Presentation of matching results

[1068] The server sends the most relevant answer and the associated department identified based on the database match to the terminal, which then displays it to the user. For example, in response to the question "How do I connect my office automation equipment?", the server displays the answer "Please contact the office automation support team" and the associated department "Office Automation Support."

[1069] Preserving and reusing history

[1070] The server stores the history of entered questions and their answers in a database. This history is used for reference the next time a question is asked. For example, if a user enters the same question again, "How do I connect to office equipment?", the server immediately provides the previously saved information.

[1071] Department introduction history management

[1072] The server also stores a history of when a user is referred to a specific department. This history includes the reason and circumstances for the referral, and is referenced when a user is referred again. This allows for consistent responses even when the same question is asked repeatedly. For example, if a user is referred to the "OA Support" department in response to a question about "how to connect office equipment," the history and reason are stored, and the user can be referred to the same department if they ask the same question again.

[1073] Specific examples

[1074] As a specific example, suppose a user types "I would like to know about the progress of the project" into their device. This question is sent to the server. The server checks past consultation cases and the FAQ database, and identifies the answer "Please contact the Project Management Department" and the "Project Management" department. This information is presented to the user via their device. The history of this exchange is also saved on the server and can be referenced the next time a similar question is asked.

[1075] Example prompts to input to the generative AI model

[1076] An example prompt might look like this:

[1077] "How do I connect my office automation equipment?"

[1078] "I want to check on the progress of a project. Which department should I contact?"

[1079] "I would like to know the steps to install new software."

[1080] In this way, this system aims to improve business efficiency by efficiently processing user questions and suggesting appropriate consultation points. The present invention makes it possible to respond quickly and accurately by effectively utilizing past consultation history and FAQ data.

[1081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1082] Step 1: The user operates the terminal and inputs a question.

[1083] The user inputs a question into an input field on the terminal. For example, the user inputs "How do I connect OA equipment?" and clicks the send button. The input data is a text-format question and is obtained from the input field on the terminal.

[1084] Input: The question entered by the user

[1085] Output: The question text entered

[1086] Step 2: The terminal sends the user's input to the server.

[1087] The terminal sends the question entered by the user to the server. The transmission is performed using an HTTP request or other communication protocol. For example, the terminal sends the entered question, "How do I connect to office equipment?" to the server.

[1088] Input: Question text obtained by the device

[1089] Output: The question data sent to the server

[1090] Step 3: The server receives the query and checks it against its database.

[1091] The server receives questions sent from the device. It analyzes the questions and compares them with past consultation history and an FAQ database. This matching uses a generative AI model to find the most relevant answer. For example, the server receives the question "How do I connect office equipment?" and searches for relevant answers in the database.

[1092] Input: Question data received from the terminal

[1093] Output: Matching responses and associated department information

[1094] Step 4: The server sends the matching result to the terminal.

[1095] The server sends the answer and related department information identified as a result of the database check to the terminal, for example, the answer "Please contact the OA support team" and the "OA support" department information to the terminal.

[1096] Input: Matched answers and related department information

[1097] Output: Answers and department information sent to the terminal

[1098] Step 5: The terminal displays the results sent from the server to the user.

[1099] The terminal displays the response and department information received from the server to the user. The user can see the information on the service screen that says, "Please contact the OA support team regarding how to connect the OA equipment."

[1100] Input: Response received from the server and department information

[1101] Output: Answers and department information presented to the user

[1102] Step 6: The server stores the history of questions and answers.

[1103] The server stores user questions and their answers in a history database. This history data allows for quick matching the next time a similar question is asked. For example, the server stores the question "How do I connect my office automation equipment?" and the answer "Please contact the office automation support team" as history.

[1104] Input: Question and its answer

[1105] Output: Questions and answers stored in a history database

[1106] Step 7: The server stores the department referral history.

[1107] The server stores the history of when a user was referred to a specific department and the reason for that referral in a history database. This allows for a consistent response if the same question is asked again. For example, the server stores the history of when a user was referred to the "OA Support" department regarding "how to connect office automation equipment" and the reason for that referral.

[1108] Input: Department referred and reason

[1109] Output: History of department referrals stored in the history database

[1110] In this way, the system efficiently processes user questions and provides appropriate consultation, thereby improving business efficiency.

[1111] (Application example 1)

[1112] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1113] Conventional support systems have difficulty responding to user questions quickly and appropriately. Furthermore, when users repeatedly ask the same question, the system is unable to provide consistent responses, causing significant user frustration. Furthermore, in food delivery services, delays in responses regarding order status and problems can lead to lower customer satisfaction.

[1114] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1115] In this invention, the server includes means for receiving a question from a user as input, means for comparing the input question with past consultation examples and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, and means for using a generative AI model to generate an optimal answer to the user's question. This makes it possible to provide a quick and appropriate answer to the user's question, thereby improving customer satisfaction in food delivery services.

[1116] The "means for accepting a question from a user as an input" refers to an interface or function for receiving a question that a user has input to the system.

[1117] "Means for checking the entered question against past consultation cases and a database of pre-created FAQs" refers to the process or function for comparing the question received from the user with past consultation cases in the database and pre-created FAQ data to confirm relevance.

[1118] "Means for identifying the most relevant answer and related department based on the matching results and presenting them to the user" is a function for selecting the most appropriate answer and the department responsible for it from the matching results and displaying them to the user.

[1119] "Means of using a generative AI model to generate optimal answers to user questions" refers to processes or functions that use AI technology to generate optimal answers to user questions.

[1120] This invention is a support system that aims to enable users to obtain prompt and appropriate answers to questions related to food delivery services. Specifically, this system uses AI technology to analyze questions from users, compares them with past consultation cases and an FAQ database, and generates and provides the most appropriate answers.

[1121] 1. Obtaining and inputting user questions

[1122] A user accesses the application using a smartphone and inputs a question. The smartphone acts as an interface and sends the input question to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the question is sent to the server.

[1123] 2. Database Matching

[1124] The server processes the question received from the user and compares it with past inquiries and created FAQ data in the database. The server performs this process using database management software. For example, in response to a question such as "The food I ordered hasn't arrived," the server searches to see if similar questions have been asked in the past, and finds the answer "Please contact the delivery team."

[1125] 3. Use of generative AI models

[1126] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model performs advanced calculations to appropriately respond to the user's doubts. This AI model uses natural language processing technology, for example, to understand the intent of the user's question and generate a relevant answer. An example of a prompt sentence is, "Based on the question entered by the user, please compare it with past FAQ data and provide the optimal answer and relevant department."

[1127] 4. Matching results and optimal answer presentation

[1128] The server sends the matching results and the optimal answer obtained by the generative AI model to the smartphone, which then displays it to the user. For example, the user can confirm the answer "Please contact the delivery team" along with the "delivery team" contact information.

[1129] 5. Preserving and Reusing History

[1130] The server saves the entered questions and their answers as a history in a database. This history is referenced the next time a similar question is entered, allowing for a quick response. This allows for a consistent response even if the user asks the same question multiple times.

[1131] Through the above steps, the system can provide quick and appropriate answers to users' questions and improve customer satisfaction in food delivery services.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] A user inputs a question through a smartphone device. The input question is collected by the device's interface. The input (question text) is sent to the server. For example, if a user inputs a question such as "The food I ordered hasn't arrived," the text is passed from the device to the server.

[1135] Step 2:

[1136] The server checks the received question against a database, which stores past consultation cases and FAQ data. The server uses the question text to search the database and find related questions and their answers. The entered question text is used to obtain a matching result (the best answer) from the database. For example, in response to a question such as "The food I ordered hasn't arrived," the server finds the answer "Please contact the delivery team" from the past database.

[1137] Step 3:

[1138] The server uses a generative AI model to generate the optimal answer to the user's question. The generative AI model uses natural language processing technology to analyze the intent of the question and generate an appropriate answer text. The input is the question text, and the output is the generated answer text. For example, in response to the question "The food I ordered hasn't arrived," the AI ​​model generates an answer such as "Please contact our delivery team immediately."

[1139] Step 4:

[1140] The server sends the generated answer and the relevant department information to the terminal, which then displays it to the user. The input is the answer text and department information from the server, and the output is what is displayed to the user. For example, the generated answer "Contact our delivery team immediately" and the contact information for the "delivery team" are displayed on the user's terminal.

[1141] Step 5:

[1142] The server stores the questions and answers received from the user in a database as history. This allows for a quick response if a similar question is entered in the future. The input is the question text and the answer text, and the output is saved in the history database. For example, the question "The food I ordered hasn't arrived" and its answer are saved in the database.

[1143] Step 6:

[1144] If the user enters the same question again, the server references the history database and quickly provides past answers. This allows the system to provide answers efficiently and consistently. The input is the question text received again, and the output is the text of the previous answer. For example, if the user asks again, "My order hasn't arrived," the previous answer "Please contact the delivery team" is immediately provided.

[1145] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1146] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[1147] 1. Data preparation

[1148] The server reads the necessary information from a database that stores past consultation examples and FAQ data, and loads it into memory. This preparation creates a system that can respond quickly when a question is entered by a user.

[1149] 2. Getting questions from users

[1150] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question and sends it to the server.

[1151] 3. Recognizing User Emotions

[1152] The server analyzes the received user question and uses an emotion engine to recognize the user's emotions. This recognition is performed using text analysis and natural language processing techniques. For example, emotions such as "troubled," "angry," and "anxious" can be detected from the user's input.

[1153] 4. Database Verification

[1154] The server compares the user's question with past consultation cases and a FAQ database. This database contains past consultation history, frequently asked questions (FAQs), and their answers. The server selects the most appropriate answer and relevant department, taking into account the user's question and emotional state.

[1155] 5. Adjustment and presentation of matching results

[1156] The server identifies the most relevant answer and related department based on the matching results, and adjusts the content of the presentation taking into account the user's emotion recognition results from the emotion engine. For example, if the user is in trouble, the server will provide a more detailed and thorough explanation. The results are then sent to the terminal and presented to the user.

[1157] 6. Preserving and Reusing History

[1158] The server stores the user's questions and answers, which are used to provide a quick and appropriate answer when a similar question is entered in the future. The server also records the user's emotional state along with the history and uses it for future responses.

[1159] 7. Department introduction history management

[1160] The server also stores the history of referrals to related departments. This history includes the reasons and circumstances behind the referral, and this information is referenced when a referral is made again. This allows for consistent responses.

[1161] Specific examples

[1162] For example, if a user types the question "Check on the progress of the project" into a device, the device sends this information to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then compares past consultation cases and the FAQ database to identify the answer "Please contact the Project Management Department" and the "Project Management" department. At this time, a more detailed explanation is added, taking into account the user's emotions. This answer and information about the relevant department are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[1163] As described above, this system not only provides fast and accurate answers to user questions and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, thereby improving work efficiency and the user experience.

[1164] The processing flow will be explained below.

[1165] Step 1:

[1166] The server loads a database containing past consultation examples and FAQ data. The server first opens the database file and loads its contents into memory. This preparation process prepares the server for quick search and matching when a question is entered.

[1167] Step 2:

[1168] The terminal accepts a question from the user as input. The user enters the question in an input field displayed on the terminal screen, and the terminal captures the question. For example, the user enters "Check the progress of the project."

[1169] Step 3:

[1170] The terminal sends the captured question to the server, and the entered question data is transferred to the server via the network. The server receives this data.

[1171] Step 4:

[1172] The server analyzes the received question text and uses an emotion engine to recognize the user's emotions. For example, the server can detect emotions such as "I'm in trouble" or "I'm anxious" from the text.

[1173] Step 5:

[1174] The server compares the question with past consultation cases and a FAQ database, taking into account the results of emotion recognition. Specifically, it breaks down the user's question into keywords and searches for related entries in the database.

[1175] Step 6:

[1176] The server then uses the matching results to identify relevant answers and relevant departments, such as "Please contact the Project Management department," and adjusts the tone and specificity of the answer based on the emotion recognition results.

[1177] Step 7:

[1178] The server sends the identified answer and information about the relevant department to the terminal. For example, the server may package the information about the "Project Management" department with the answer "Please contact the Project Management Department" and send it to the terminal.

[1179] Step 8:

[1180] The terminal receives the response from the server and presents the relevant department information to the user. The terminal displays the information on the screen in a format that is easy for the user to understand. For example, it displays "To check the progress of the project, please contact the project management department."

[1181] Step 9:

[1182] The server stores the user's questions, their answers, and the emotion recognition results as a history, which can be used to quickly respond to similar questions in the future.

[1183] Step 10:

[1184] The server also stores a history of referrals to related departments, allowing for a consistent response when the user asks the same question again. The server also takes into account the user's past emotional state and provides an appropriate response.

[1185] Through these steps, the system not only provides users with quick and accurate answers and information on where to seek help, but also responds optimally to their emotional state, which is expected to improve both work efficiency and the user experience.

[1186] Example 2

[1187] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1188] Conventional consultation systems often respond mechanically to user questions and provide only uniform answers. Furthermore, they do not take the user's emotional state into consideration, which can lead to frustration and anxiety. Furthermore, there is no mechanism for referencing past consultation history or emotional state, making it difficult to provide a consistent response. This leads to a poor user experience and a lack of work efficiency.

[1189] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1190] In this invention, the server includes means for receiving a question from a user as input, means including an emotion engine for analyzing the input question and recognizing the user's emotion, and means for comparing the analysis results with past consultation cases and an FAQ database. This makes it possible to identify the most appropriate answer and relevant department taking into account the user's emotional state, thereby improving user satisfaction and streamlining operations.

[1191] "User" refers to an individual or organization that utilizes the system to enter questions and obtain information.

[1192] A "question" refers to text information that a user inputs to the system, requesting specific information or advice.

[1193] "Emotion engine" refers to a software module that analyzes and recognizes a user's emotional state from input text information.

[1194] "Past consultation examples" refers to records of questions previously submitted by users and the answers to those questions.

[1195] An "FAQ database" refers to a database that systematically collects and stores frequently asked questions and their answers.

[1196] "Matching" refers to the process of evaluating the relevance of the input question and emotional state by comparing it with past consultation cases and the FAQ database.

[1197] "Relevant department" refers to a department or person within an organization who has the authority and knowledge to provide an appropriate answer to a user's question.

[1198] "History" refers to a record of a user's questions, answers, and emotional state, data that is kept for future reference.

[1199] "Emotional state" refers to information that indicates the psychological state of the user when they input a question, and is recognized by the emotion engine.

[1200] The present invention relates to a consultation service providing system that aims to improve business efficiency and user experience. In particular, by combining it with an emotion engine that recognizes user emotions, more advanced responses are possible. The system of the present invention is composed of a server, a terminal, and an emotion engine.

[1201] Hardware and Software Configuration

[1202] The system is built using a server, a terminal, and an emotion engine that performs text analysis. Specific software includes relational database management systems such as MySQL and PostgreSQL for the database, and natural language processing (NLP) tools such as IBM Watson and Microsoft Azure Sentiment Analysis for emotion analysis.

[1203] Data preparation

[1204] The server reads the necessary information from a database that stores past consultation examples and FAQ data and loads it into memory. This prepares the server to respond quickly when a question is entered by a user. Information from the database is extracted using SQL queries and temporarily cached in memory.

[1205] Getting questions from users

[1206] The device receives a question from the user as input. The user enters the question in an input field displayed on the device screen and clicks the send button. The device then sends this question in JSON format to the server. Specifically, the device creates an input field in the user interface (UI), captures the question, and sends it to the server as an HTTP POST request.

[1207] Recognizing user emotions

[1208] The server analyzes the received user question and recognizes the user's emotion using an emotion engine. This recognition is performed using text analysis technology through the emotion engine. For example, it detects whether the user is expressing emotions such as "troubled," "angry," or "anxious."

[1209] Database Collation

[1210] The server compares the user's question and the perceived emotion with the past consultation case and FAQ database, and searches the database with the appropriate SQL query to select the most appropriate answer and relevant department, taking into account the question and emotional state.

[1211] Reconciliation and presentation of match results

[1212] The server identifies the appropriate answer and relevant department based on the matching results. If the user is having trouble, the server adds a more detailed and specific explanation based on the emotion recognition results of the emotion engine. This final answer is sent to the device in JSON format and presented to the user.

[1213] Preserving and reusing history

[1214] The server stores the history of user questions, their answers, and their emotional state, which can be used to provide immediate and appropriate answers when similar questions are entered in the future. The historical data is stored in a database using appropriate SQL queries.

[1215] Department introduction history management

[1216] The server also stores the referral history to related departments in a database. This history includes the reason for the referral and the circumstances surrounding it, and can be referenced the next time a referral is made, allowing for consistent handling.

[1217] Specific examples

[1218] Consider the case where a user types "I would like to check the progress of the project" into a device. The device sends this question to the server. The server receives this question and uses its emotion engine to recognize that the user is "in trouble." The server then searches past consultation cases and a database of FAQs to identify the answer "Please contact the project management department." At this time, it adds a more detailed explanation, taking into account the user's emotions. This answer and information about the relevant departments are presented to the user via the device. The history of this interaction and the user's emotions are also stored on the server for future reference.

[1219] This system not only provides users with quick and accurate answers and information on where to seek advice, but also uses an emotion engine to provide optimal responses based on the user's emotional state, which is expected to improve work efficiency and the user experience.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1:

[1222] The server begins the process of loading past case and FAQ data from a database (e.g., MySQL, PostgreSQL). This information is used for future lookups. Specifically, the server executes SQL queries to extract the necessary data and caches it in memory.

[1223] Input: Database connection information and SQL query

[1224] Output: Cached in-memory consultation examples and FAQ data

[1225] Step 2:

[1226] The terminal accepts a user's question as input. This question is entered through an input field in the user interface and submitted by the user clicking a submit button. The terminal converts this information into JSON format and sends it to the server as an HTTP POST request.

[1227] Input: The question text that the user types into the terminal

[1228] Output: Question data in JSON format sent to the server

[1229] Step 3:

[1230] The server analyzes the question data received from the device using natural language processing (NLP) technology and an emotion engine (e.g., IBM Watson, Microsoft Azure Sentiment Analysis). This process recognizes not only the content of the user's question, but also the emotion hidden in the question (e.g., "troubled," "angry," "anxious").

[1231] Input: JSON format question data received from the terminal

[1232] Output: Question content and emotion recognition results

[1233] Step 4:

[1234] Based on the analysis results, the server compares the question and emotional state with past consultation cases and a database of FAQs. Specifically, it uses SQL queries to search the database and extract the most relevant answers. In doing so, it also takes the user's emotional state into consideration to select the most appropriate answer.

[1235] Input: Question content, emotion recognition results, past consultation examples, and FAQ data

[1236] Output: The most relevant answers as a result of matching and related department information

[1237] Step 5:

[1238] The server formats the answer and related department information based on the matching results. Taking into account the user's emotion recognition results, it adds a more detailed explanation to users who are in trouble, for example. This final response data is converted into JSON format and sent to the device.

[1239] Input: Answer as matching result, related department information, emotion recognition result

[1240] Output: Response data in JSON format to send to the device

[1241] Step 6:

[1242] The terminal displays the response data received from the server on the user interface, allowing the user to obtain an appropriate answer to their question and information on where to seek advice.

[1243] Input: JSON format response data received from the server

[1244] Output: Answers and associated department information displayed in the user interface

[1245] Step 7:

[1246] The server stores the user's question, the answer, and the emotion recognition results in a database, allowing it to respond quickly to similar questions in the future.

[1247] Input: Question, answer, emotion recognition result

[1248] Output: Historical data stored in a database

[1249] Step 8:

[1250] The server also stores the referral history to the relevant department in a database, including the reason and circumstances for the referral, so that it can be referenced the next time a referral is made.

[1251] Input: Referral information, reason for referral and background

[1252] Output: Referral history stored in a database

[1253] (Application example 2)

[1254] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1255] In modern brick-and-mortar stores, users need to be able to quickly and accurately obtain product information. However, conventional methods often fail to respond appropriately to user questions, resulting in a poor user experience. Furthermore, because they do not take into account the user's feelings regarding the question, it is difficult to improve customer satisfaction.

[1256] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question from a user as input, means for comparing the input question with past consultation cases and a created FAQ database, means for identifying the most relevant answer and related department based on the comparison results and presenting them to the user, means for converting the user's question into text data using voice input and voice recognition technology, emotion recognition means for analyzing the user's emotions, and means for adjusting the presented content based on the emotion recognition results. This enables flexible responses and efficient product guidance according to the user's emotions.

[1257] The "means for accepting a question from a user as input" refers to an interface that allows a user to input a question to a terminal. This includes functions for accepting information through voice input or text input.

[1258] "Means for comparing the entered question with past consultation examples and an existing FAQ database" is a function for comparing a new question entered by a user with past questions and answers stored in an existing database.

[1259] "Means of identifying the most relevant answer and relevant department based on the matching results and presenting them to the user" is a function that uses the information obtained through matching to select the most appropriate answer and contact point for the user's question and provides them to the user.

[1260] The "means for converting a user's question into text data using voice input and voice recognition technology" is a function that allows a user to input a question by voice and automatically convert the voice data into text data.

[1261] "Emotion recognition means for analyzing user emotions" refers to algorithms or technologies that determine the user's emotions based on the text data entered by the user. For example, it can recognize emotions such as distress or anger.

[1262] The "means for adjusting the content of presentation based on the emotion recognition result" is a function for adjusting the content of answers or guidance according to the emotion of the user after the emotion of the user is determined by the emotion recognition means.

[1263] "Means for saving history and referencing it the next time" is a function that saves user questions, their answers, and the accompanying emotional data in a database, allowing for a quick response when a similar question is entered at a later date.

[1264] "A means of saving referrals to related departments as a history and taking that history into consideration when making a second referral" is a function that records the circumstances and reasons when a user is referred to a specific department, and uses that history when the same user makes another inquiry in the future.

[1265] The present invention relates to a consultation service provider system that aims to improve the user experience in brick-and-mortar stores. This system uses smart glasses and makes full use of voice input and emotion recognition technology to quickly provide appropriate answers to users' questions.

[1266] System configuration

[1267] The system consists of the following main components:

[1268] 1. Smart glasses: For example, the general term "wearable device."

[1269] 2. Server: Deployed in a cloud environment.

[1270] 3. Emotion recognition engine: For example, the generic name "emotion analysis software."

[1271] 4. Database: A data repository for storing user questions, emotional states, and answer history.

[1272] Hardware and Software Use

[1273] The wearable device (smart glasses) has a voice input function and captures the user's questions.

[1274] The server is primarily responsible for analyzing the question data and generating answers.

[1275] Sentiment analysis software recognizes emotions from user input and determines appropriate responses.

[1276] The database uses a cloud database such as AWS RDS.

[1277] Program implementation example

[1278] 1. Retrieving and submitting user questions:

[1279] The user speaks a question into the smart glasses, which then recognize the voice and convert it into text. This process is performed using a speech recognition API.

[1280] 2. Emotion Recognition and Analysis:

[1281] The received text data is sent to a server, where sentiment analysis software analyzes the user's emotions. For example, the text is tagged with "I'm in trouble" or "I'm looking for something." This allows the system to understand the user's emotional state and select an appropriate response.

[1282] 3. Historical comparison:

[1283] Based on the user's text data and emotional state, the server matches the user's past questions with a database of answers, and identifies the most relevant answers and related departments based on the matching results.

[1284] 4. Present the response:

[1285] The answer obtained through the matching is sent to the smart glasses and presented to the user, with the content of the presentation adjusted according to the user's emotions.

[1286] 5. History Preservation:

[1287] All questions, answers, and the user's emotional state are stored in a database, allowing for fast and accurate answers when similar questions are asked in the future.

[1288] Adding specific examples

[1289] Example of operation scene

[1290] A user is shopping and wearing smart glasses. The user asks, "Where is this item?"

[1291] Speak: "Where is this item?"

[1292] Emotion recognition: "I'm in trouble"

[1293] Server response: "It's on the shelf near the register. I'll show you where it is."

[1294] Example prompts to input to the generative AI model

[1295] User Question: "Where is this item?"

[1296] Emotion recognition: "I'm in trouble"

[1297] Past data collation: Product search, in-store guidance history

[1298] API usage: speech recognition API, sentiment analysis software, cloud database

[1299] This system will improve the user experience and make operations in physical stores more efficient.

[1300] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1301] Step 1:

[1302] The user speaks a question into the smart glasses. The smart glasses capture the voice data and convert it into text data using a voice recognition API. Specifically, if the user speaks "Where is this product?", the voice is converted into the text "Where is this product?" The input of this process is voice data, and the output is text data.

[1303] Step 2:

[1304] The user's question data (text data) is sent from the terminal to the server. The terminal then sends the converted text data to the server, which then receives it and prepares it for analysis. The input to this process is text data, and the output is data that can be analyzed on the server side.

[1305] Step 3:

[1306] The server uses an emotion recognition engine to analyze the received text data and recognize the user's emotions. For example, the emotion "troubled" is detected from the text data. Specifically, the emotion analysis software assigns a tag of "troubled." The input for this process is text data, and the output is data with an emotion tag.

[1307] Step 4:

[1308] The server uses emotion-tagged question data to match past consultations and an FAQ database. This matching identifies the most relevant answer and the appropriate related department. The specific operation of the matching is to use a database search to check whether a similar question has been asked in the past and find the appropriate answer. The input to this process is emotion-tagged question data, and the output is the best answer and information on the related department.

[1309] Step 5:

[1310] The server adjusts the answer based on the matching results and emotion recognition results, and prepares to present it to the user. For example, if the server recognizes that the user is "troubled," it adds a more detailed explanation. The input to this process is the optimal answer and emotion tag, and the output is the adjusted answer data.

[1311] Step 6:

[1312] The adjusted answer data is sent from the server to the device (smart glasses) and presented to the user. The smart glasses then provide the received answer data to the user via voice or screen display. Specifically, the glasses provide voice guidance such as, "It's on the shelf near the register. We'll guide you to where the product is." The input for this process is the adjusted answer data, and the output is an audio or visual presentation to the user.

[1313] Step 7:

[1314] The server stores the entire history of user questions, emotion tags, and suggested answers in a database. This allows for a quick and appropriate response when a similar question is entered in the future. The input of this process is the entire history data, and the output is an update to the history database.

[1315] 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.

[1316] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1317] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1318] 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.

[1319] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1320] 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.

[1321] 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).

[1322] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1323] 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."

[1324] 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.

[1325] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1326] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1331] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] The following is further disclosed regarding the above embodiment.

[1337] (Claim 1)

[1338] means for accepting a question from a user as input;

[1339] A means of comparing the entered question with past consultation cases and a database of created FAQs;

[1340] means for identifying and presenting to the user the most relevant answers and related departments based on the matching results;

[1341] A system including:

[1342] (Claim 2)

[1343] 2. The system according to claim 1, further comprising means for retaining a history including the input questions and the reasons for the input questions, and for referring to the history the next time a check is made.

[1344] (Claim 3)

[1345] 2. The system according to claim 1, further comprising means for storing the referrals to the related departments as a history and taking the history into consideration when making a recurring referral.

[1346] "Example 1"

[1347] (Claim 1)

[1348] means for accepting a question from a user as input;

[1349] A means for checking the input question against a database of past consultation history and a database of FAQs;

[1350] means for identifying and presenting to the user the most relevant answers and associated departments based on the matching results;

[1351] a means for the server to store user questions and their answers in a history database;

[1352] A system including:

[1353] (Claim 2)

[1354] 2. The system according to claim 1, further comprising means for retaining a history including the input questions and the reasons for the input questions, and for referring to the history the next time a check is made.

[1355] (Claim 3)

[1356] 2. The system according to claim 1, further comprising means for storing a history of referrals to said related departments and taking said history into consideration when making a recurring referral.

[1357] "Application Example 1"

[1358] (Claim 1)

[1359] means for accepting a question from a user as input;

[1360] A means of comparing the entered question with past consultation cases and a database of created FAQs;

[1361] means for identifying and presenting to the user the most relevant answers and related departments based on the matching results;

[1362] a means for using the generative AI model to generate an optimal answer to a user question;

[1363] A system including:

[1364] (Claim 2)

[1365] 2. The system according to claim 1, further comprising means for retaining a history including the input questions and the reasons for the input questions, and for referring to the history the next time a check is made.

[1366] (Claim 3)

[1367] 2. The system according to claim 1, further comprising means for storing the referrals to the related departments as a history and taking the history into consideration when making a recurring referral.

[1368] "Example 2: Combining Emotion Engines"

[1369] (Claim 1)

[1370] means for accepting a question from a user as input;

[1371] means for analyzing an input question and including an emotion engine for recognizing the emotion of the user;

[1372] A means of comparing the analysis results with past consultation cases and a FAQ database,

[1373] means for identifying and presenting to the user the most relevant answers and related departments based on the matching results;

[1374] A system including:

[1375] (Claim 2)

[1376] 2. The system according to claim 1, further comprising means for retaining a history including the input question, the reason for the input question, and the emotional state of the user, and for referencing the history the next time a query is made.

[1377] (Claim 3)

[1378] 2. The system according to claim 1, further comprising means for storing the referrals to the related departments as a history, and taking into consideration the history and reasons for the referrals when making a second referral.

[1379] "Application example 2 when combining emotion engines"

[1380] (Claim 1)

[1381] means for accepting a question from a user as input;

[1382] A means of comparing the entered question with past consultation cases and a database of created FAQs;

[1383] means for identifying and presenting to the user the most relevant answers and related departments based on the matching results;

[1384] means for converting a user's question into text data using voice input and voice recognition technology;

[1385] emotion recognition means for analyzing the emotions of a user;

[1386] A means for adjusting the content presented based on the emotion recognition result;

[1387] A system including:

[1388] (Claim 2)

[1389] a means for storing a history including the input questions and the reasons for the input questions, and for referring to the history at the next verification;

[1390] 10. The system of claim 1, further comprising means for including in said history the user's emotional state.

[1391] (Claim 3)

[1392] a means for storing the introduction to the relevant department as a history and taking the history into consideration when introducing the relevant department again;

[1393] The system of claim 1 , further comprising means for including emotion recognition results in the referral history. [Explanation of symbols]

[1394] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for accepting a question from a user as input; A means of comparing the entered question with past consultation cases and a database of created FAQs; means for identifying and presenting to the user the most relevant answers and related departments based on the matching results; A system including:

2. 2. The system according to claim 1, further comprising means for retaining a history including the input questions and the reasons for the input questions, and for referring to the history at the next verification.

3. 2. The system according to claim 1, further comprising means for storing the introduction to the related department as a history and taking the history into consideration when introducing the customer again.

Images