system

Abstract

We provide the system. [Solution] A means by which the user inputs conditions through a generation application, Means for transmitting the above conditions to the processing unit, The processing device includes means for analyzing the conditions and extracting candidates from a relevant expert database, The means of presenting the aforementioned expert candidates, A means by which the user selects from the aforementioned candidates and makes a reservation. A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In situations where a lawyer is needed, it is difficult for ordinary users to quickly select an appropriate expert. Users have to consider conditions such as the lawyer's field of expertise, fee system, and years of experience, and it is very difficult to collect information for this in a short time. Furthermore, even when an appropriate candidate is found, there is a problem that it takes time to make and confirm an appointment for an interview. In order to address these problems, there is a need to provide a system that allows users to more efficiently find a lawyer that meets their needs and make reservations smoothly.

Means for Solving the Problems

[0005] Through a generation application, users can input their desired criteria for a lawyer and send this information to a processing unit. The processing unit analyzes the data based on the entered criteria and extracts candidates from a database of relevant professionals. The extracted candidates are evaluated, prioritized, and presented to the user. The user can then select a suitable lawyer from this presented list and proceed with the booking process. A notification is also sent to the user once the booking is complete. This system allows users to quickly find the best lawyer for them and book an appointment directly and efficiently.

[0006] A "generation application" is software that receives conditions entered by the user and transmits them to a processing unit.

[0007] "Conditions" refer to information such as budget, area of ​​expertise, years of experience, and location that users consider when selecting a professional.

[0008] A "processing device" is a device or computer system that analyzes received conditions, extracts and evaluates candidates from a relevant expert database, and presents them to the user.

[0009] A "professional database" is a collection of data containing information about lawyers, including their areas of expertise, fees, location, and career history.

[0010] "Candidates" refers to a list of lawyers in the expert database selected based on the criteria entered by the user.

[0011] "Reservation procedures" refer to a series of actions taken by a user to secure a date and time for an interview or consultation with a specialist of their choice.

[0012] A "notification" is a confirmation or guidance message sent to the user when a reservation is confirmed. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system that allows users to efficiently find a suitable lawyer and easily make an appointment. The system consists of a generation application, a processing unit, and a professional database.

[0035] First, the user uses the device's generation application to input various criteria for selecting a lawyer in natural language. These criteria include desired specialty, budget, years of experience, and location. The device then transmits this information to the processing unit.

[0036] The transmitted data is received by a processing unit on the server. The server uses natural language processing (NLP) technology to analyze the input and extract the necessary data. Based on the analyzed data, the server accesses a database of experts and extracts candidate lawyers that meet the criteria. The extracted candidates are evaluated and prioritized using an AI model. This evaluation is based on past data, and the system recommends the lawyer who best matches the user's preferences.

[0037] The resulting list of candidates is presented to the user via their device. The user can select their preferred lawyer from the presented list and make a reservation directly. Once the reservation is confirmed, the server processes the reservation information and sends a confirmation notification to the user. This notification consists of detailed information, including the date, time, and location of the meeting, and can be viewed on the LINE app.

[0038] For example, if a user enters criteria such as "a lawyer in Tokyo specializing in traffic accidents, with a budget of 50,000 yen or less, and over 10 years of experience," the server searches its expert database for lawyers who meet these criteria, evaluates them, and presents them to the user. The user can then select a lawyer and make a reservation, accessing the necessary services without complicated procedures. In this way, the system provides users with a quick and convenient means of service.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user launches a generation application on their device and enters their desired lawyer's criteria in natural language. These criteria include specialty, budget, years of experience, and location.

[0042] Step 2:

[0043] The device converts the conditions entered by the user into structured data and sends it to the server as data. Data transmission is performed using the LINE API.

[0044] Step 3:

[0045] The server analyzes the received data and uses natural language processing techniques to extract keywords that meet the specified criteria. This structures the data and transforms it into more usable information.

[0046] Step 4:

[0047] The server compares the analysis results with a database of experts and extracts lawyer candidates that meet the criteria. The extraction process uses an algorithm that evaluates the degree of match with the characteristics of each lawyer in the database.

[0048] Step 5:

[0049] The server uses an AI model to evaluate and rank the extracted candidate lawyers. This evaluation is based on how well each lawyer is suited to the user's requirements.

[0050] Step 6:

[0051] The server generates a prioritized list of candidates and sends it to the terminal. This list is organized according to the user's criteria and priority.

[0052] Step 7:

[0053] The user reviews a list of candidates displayed on their device and selects their preferred lawyer. The user can then schedule a meeting with the selected lawyer through the application.

[0054] Step 8:

[0055] The server receives the reservation information, notifies the selected lawyer, and also sends a confirmation message to the user. The notification includes details such as the date, time, and location of the meeting.

[0056] Through the above processing steps, users can efficiently and quickly search for, select, and book an appointment with a lawyer who is suitable for them.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] The challenge is to provide users with a means to quickly and efficiently find a suitable expert and easily make a reservation. In particular, there is a need for technology that automatically evaluates and selects experts using conditions entered in natural language and presents the most suitable candidates to the user.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for the user to input conditions using natural language, means for the information processing device to analyze the conditions using natural language processing technology, and means for evaluating and prioritizing candidates using a generative artificial intelligence model. This makes it possible to quickly and accurately present experts to the user and to easily make reservations.

[0062] A "user" is someone who uses the system to find and book an expert.

[0063] "Conditions" refer to a set of information that users input in natural language based on their wishes and requirements, and include parameters necessary for selecting an expert.

[0064] An "information processing device" is a computer system that receives conditions transmitted by a user and performs analysis.

[0065] "Natural language processing technology" is a technique that analyzes natural language used by humans and converts it into a format that can be processed by computers.

[0066] A "collection of expert information" is a database containing detailed data about experts, and is a searchable information source based on various criteria.

[0067] A "generative artificial intelligence model" is an artificial intelligence program that learns from past data and has the ability to understand and evaluate human intentions.

[0068] "Evaluation" refers to the process by which a generative artificial intelligence model calculates the degree of suitability of expert candidates based on the input conditions and ranks them accordingly.

[0069] Prioritization is the process of arranging potential experts in the optimal order based on evaluation results.

[0070] "Presentation" refers to the process of displaying results in a format that is easy for users to understand, and includes providing information visually.

[0071] A "reservation" is the act of confirming the date, time, and location with a designated expert, and is performed through a system.

[0072] This invention is a system that enables users to efficiently find and easily book necessary experts using a generation application installed on their own devices. The system mainly consists of client terminals, a server, an expert database, a generation AI model, and a notification application.

[0073] The user launches a generation application on their device and enters their desired expert criteria in natural language (for example, "Expert in traffic accidents in Tokyo, budget under 50,000 yen, 10+ years of experience"). This input is converted into data format on the device and sent to the server.

[0074] The server analyzes the received data using natural language processing techniques. Specifically, it uses open-source natural language processing libraries to extract important parameters from the input conditions. Based on the conditions obtained through this analysis, the server accesses an expert database and extracts candidate experts that meet the conditions.

[0075] Furthermore, the extracted candidates are evaluated by a generative artificial intelligence model. Based on past matching history, the AI ​​model selects the most suitable expert for the user and determines their priority. This AI model is built using a machine learning framework and scores experts based on their experience and user ratings.

[0076] The resulting list of potential experts is sent to the user's device and displayed through the generated application. The user can then select the desired expert from this list and proceed with the booking process. Once the booking is complete, the server uses the LINE API to send a confirmation notification to the user. The notification includes details such as the date, time, and location of the scheduled meeting.

[0077] This system allows users to easily and quickly find the expert best suited to their needs. Furthermore, intuitive input of criteria using natural language makes it easy to operate even for users without specialized knowledge, enabling efficient expert selection. As a result, user convenience is significantly improved.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user launches the generation application on their device and inputs criteria for selecting a specialist in natural language. This input includes areas of expertise, region, budget, and years of experience. Specifically, the user might input a sentence like, "A specialist in traffic accidents in Tokyo, with a budget of 50,000 yen or less and over 10 years of experience." The device parses this input, converts it into data format, and sends it to the server via the network.

[0081] Input: Natural language conditions entered by the user on the device

[0082] Output: Conditions for the data format sent to the server

[0083] Step 2:

[0084] The server analyzes the received conditional data using natural language processing techniques. This involves using open-source natural language processing libraries to extract keywords and important information from the conditions. Specifically, the data processing involves tokenizing the conditional statements and interpreting their meaning.

[0085] Input: Conditions for the data format received by the server

[0086] Output: Analyzed keywords and conditional information

[0087] Step 3:

[0088] The server accesses the expert database based on the analysis results and searches for candidate experts that match the criteria. It then executes a database query and lists the expert information that matches the criteria.

[0089] Input: Analyzed keywords and conditional information

[0090] Output: List of expert candidates that meet the criteria

[0091] Step 4:

[0092] The server uses a generative artificial intelligence model to evaluate and prioritize a list of expert candidates. Based on past matching data, the AI ​​model calculates a score to identify the candidate best suited to the user's criteria. This evaluation determines the candidate's priority.

[0093] Input: List of expert candidates

[0094] Output: List of evaluated and prioritized expert candidates

[0095] Step 5:

[0096] The server sends a list of evaluated expert candidates to the user's terminal. The terminal receives this list and presents it visually to the user on the generating application.

[0097] Input: List of evaluated and prioritized expert candidates

[0098] Output: A list of expert candidates presented to the user.

[0099] Step 6:

[0100] The user selects their preferred expert from the presented list and makes a reservation. The selected candidates are sent to the server via the generation application.

[0101] Input: User-selected expert candidates

[0102] Output: Reservation Information

[0103] Step 7:

[0104] The server processes the reservation information sent by the user and generates a confirmation notification. This notification includes details such as the date, time, and location, and is sent to the user using the LINE API. The user can then check this notification in the LINE app and confirm their reservation.

[0105] Input: Reservation Information

[0106] Output: Confirmation notification sent to the user

[0107] (Application Example 1)

[0108] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0109] Traditional expert booking systems presented a problem: finding a suitable expert was time-consuming and cumbersome for users. Furthermore, quick searches and bookings while on the go or away from the office were difficult, limiting user convenience. Additionally, a lack of effective visual information made it difficult for users to make quick decisions on the spot.

[0110] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0111] In this invention, the server includes means for the user to input conditions through a generation application, means for transmitting the conditions to a processing unit, means for extracting candidates from a relevant expert database, means for the user to receive expert information via augmented reality display through a mobile device while on the move, and means for making a reservation using voice input. As a result, the user can visually and in real time obtain information on the most suitable expert even while on the move, and quickly confirm the reservation on the spot using voice.

[0112] A "generation application" is software that allows a user to input conditions and send them to a processing unit.

[0113] A "processing device" is a computer device that analyzes input conditions and extracts candidate experts from a database of relevant experts.

[0114] A "specialist database" is a collection of data that manages information on various types of experts and provides appropriate candidates based on specific criteria.

[0115] Augmented reality is a technology that overlays visual information onto the real world, providing users with an intuitive way to convey expert information.

[0116] "Voice input" is an interface that allows users to input instructions into a system using their voice.

[0117] A "portable device" is a terminal that a user can carry with them, and includes smart glasses and smartphones.

[0118] To implement this invention, it is necessary to install a generation application on the user's mobile device. This application provides an interface that allows the user to input expert search criteria in natural language. Mobile devices such as smart glasses and smartphones are primarily used.

[0119] When a user enters conditions, those conditions are sent from the terminal to the server's processing unit. The server first uses natural language processing (NLP) techniques to analyze the conditions and extract the necessary data. This analysis utilizes specific NLP libraries and machine learning models.

[0120] Based on the analyzed data, the server accesses a database of experts and extracts candidate experts that meet the criteria. These candidates are then evaluated and prioritized using a generative AI model. This evaluation process utilizes historical data to prioritize experts who best match the user's preferences.

[0121] The evaluation results are presented to the user using augmented reality (AR) display on their mobile device. AR software and the device's built-in camera are used to intuitively visualize expert information within the real world. Users can make reservations on the spot using voice input. This feature is supported by the mobile device's voice recognition hardware and software.

[0122] For example, if a user enters the criteria "I'm looking for a lawyer specializing in traffic accidents in Tokyo," the server searches its database based on this information, prioritizes available lawyers, and presents them to the user using augmented reality. An example of a prompt might be, "I'm looking for a lawyer specializing in traffic accidents in Tokyo. I'd prefer someone with over 10 years of experience and a fee of under 50,000 yen." In this way, users can efficiently find the most suitable professional and easily complete a booking.

[0123] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0124] Step 1:

[0125] The user uses a generation application on their mobile device to enter search criteria for experts in natural language. These criteria may include specific details, such as "lawyers in Tokyo specializing in traffic accidents." The entered information is then transmitted from the terminal to the server's processing unit.

[0126] Step 2:

[0127] The server's processing unit performs natural language processing (NLP) on the received conditions. It applies NLP techniques to the received text data to extract important keywords and requirements. This analysis outputs necessary conditions such as "Tokyo," "traffic accident," and "lawyer."

[0128] Step 3:

[0129] The server uses the analyzed keywords to search the expert database. It extracts candidates that match the criteria from the lawyer information stored in the database. In this step, a database query is executed to retrieve entries that match the criteria as output.

[0130] Step 4:

[0131] The extracted candidates are evaluated using a generative AI model. To prioritize candidates based on past success stories and evaluation data, the AI ​​model receives candidate profiles as input, evaluates how well they match the user's preferences, and generates a prioritized list.

[0132] Step 5:

[0133] The server sends the evaluation results to the mobile device, where it displays them in augmented reality. Using AR software, expert information is overlaid onto the user's field of view. For example, the name and details of the most suitable lawyer might be displayed.

[0134] Step 6:

[0135] The user uses voice input to select their preferred lawyer from the presented options and make a reservation. The voice recognition function of the mobile device analyzes the user's instructions and sends them to the server. The server processes the received instructions and confirms the reservation.

[0136] Step 7:

[0137] Based on the reservation confirmation information, the server sends a final notification to the user's mobile device. This notification includes details such as the reserved time and location, and is available for the user to review.

[0138] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0139] This invention provides a system that allows users to efficiently find a lawyer suitable for them, and furthermore, takes the user's emotions into consideration during the selection process. This system consists of a combination of a generation application, a processing unit, a professional database, and an emotion engine.

[0140] The user launches a generation application using their device and enters requirements for a lawyer. These requirements include areas of expertise, budget, years of experience, and location, and the device sends this information to a server-side processing unit. Simultaneously, an emotion engine analyzes the user's emotions based on their word choice, input speed, and device operation history. This emotion analysis is used to determine the user's level of stress and anxiety.

[0141] The server, after analyzing the received conditions and sentiment data, uses natural language processing technology to extract relevant keywords and searches a database of experts. The extracted list of candidates is then prioritized, taking into account the results of the sentiment engine's analysis. For example, if the user is feeling anxious, lawyers with a strong reputation for support will be presented first.

[0142] A prioritized list is sent to the device and presented to the user. The user reviews this list, selects a lawyer that suits their needs, and makes an appointment. Once the appointment is confirmed, the server sends a notification and a confirmation message to the user regarding the date, time, and location of the meeting.

[0143] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and simultaneously indicates a high level of stress, the server will prioritize recommending lawyers with strong support systems, especially those with expertise in child custody. In this way, the system not only selects candidates based on criteria but also considers the user's psychological state when making suggestions, thereby achieving more effective matching.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The user launches a generation application on their device and enters the requirements for the lawyer they are looking for. These requirements include specialty, location, budget, and years of experience. As the user enters their information, an emotion engine analyzes their emotions based on their typing speed and word choice.

[0147] Step 2:

[0148] The terminal sends user input data and analysis data from the emotion engine to the server. This allows the server to receive both conditional and emotional information simultaneously.

[0149] Step 3:

[0150] Based on the conditions received by the server, keywords are extracted using natural language processing technology. Next, a database of experts is consulted to search for relevant lawyer candidates. Preparations are made to incorporate sentiment data during this process.

[0151] Step 4:

[0152] The server uses an AI model to evaluate and prioritize the list of candidates. This evaluation incorporates the results of an emotion engine analysis, and if it determines that the situation is urgent, the system adjusts to display lawyers who can respond more quickly at the top of the list.

[0153] Step 5:

[0154] A prioritized list of potential lawyers is sent from the server to the user's terminal. The user can then review this list on their terminal and select the most suitable candidate.

[0155] Step 6:

[0156] The user makes a reservation with a lawyer of their choice. The terminal sends the reservation information to the server, and the server notifies both the lawyer and the user of the confirmed reservation.

[0157] Step 7:

[0158] The server sends a final confirmation notification to the user. This clearly communicates the interview date and location to the user.

[0159] This process allows users not only to find a lawyer that meets their requirements, but also to receive suggestions that take their psychological state into account, enabling them to make better choices.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] Traditionally, when selecting a professional, users would only input their own criteria, and the system would select a professional based on those criteria. However, the user's emotions and psychological state were ignored, and therefore the suggested professional was not always the best fit for the user's current situation. This resulted in a problem where the efficiency and effectiveness of professional selection were not fully realized.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for inputting conditions through a generation program, means for analyzing emotions based on user behavior data, and means for determining the priority of expert candidates considering the emotion analysis results. This makes it possible to select experts that take into account not only the user's conditions but also their emotions and psychological state, enabling the presentation of experts that are more suitable for the user.

[0165] A "generator program" is software that allows users to input necessary criteria when searching for experts.

[0166] An "information processing device" is a device that analyzes the conditions entered by the user, extracts appropriate candidates from expert information sources, and presents them.

[0167] An "expert information source" is a database that accumulates and makes searchable information about various experts.

[0168] "Action data" refers to data such as the user's input speed, word choice, and operation history when entering information.

[0169] "Methods for analyzing emotions" refer to processes that determine the user's emotional state at a given time based on their behavioral data.

[0170] "Methods for determining priorities" refers to the process of determining the order in which to present the extracted expert candidates, based on the user's conditions and the results of sentiment analysis.

[0171] The system of this invention takes into account the user's psychological state in the process of efficiently selecting a suitable expert for themselves. The system consists of the following components:

[0172] 1. Terminal Usage: The user launches the generation program via the terminal and inputs the criteria necessary for selecting an expert. These criteria include area of ​​expertise, budget, years of experience, and location. The terminal is equipped with a function to collect the data entered by the user and the operation data during the input process.

[0173] 2. Analysis by the Information Processing Device: The terminal transmits the user's input conditions to the information processing device. This information processing device analyzes the conditions and extracts relevant experts from a database called the expert information source.

[0174] 3. Inclusion of emotion analysis function: The server uses an emotion analysis engine based on the user's behavior data to determine the user's emotions. A generative AI model is used here to help understand the user's level of stress and anxiety.

[0175] 4. Prioritization: The server determines the priority of expert candidates based on the user's conditions and the results of sentiment analysis. This makes it possible to present the expert best suited to the user's psychological state.

[0176] 5. Expert Selection and Booking: The user views a prioritized list of experts on their device and makes a selection. The server confirms the booking with the selected expert, and details such as the date, time, and location of the meeting are sent to the user.

[0177] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and indicates a high level of stress, the server will prioritize recommending lawyers who are strong in child custody issues and have a well-established support system. This allows users to be matched with the most suitable professional, taking into account not only their specific needs but also their psychological state.

[0178] An example of a prompt message would be, "If the user is anxious, provide a list of trustworthy lawyers," allowing the generative AI model to support the selection of an expert based on emotion.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The user launches the generation program using a terminal. The user enters information such as the lawyer's area of ​​expertise, desired budget, years of experience, and location into the on-screen input form. The entered information is saved digitally on the terminal and prepared for the next processing step.

[0182] Step 2:

[0183] The terminal sends user-inputted conditional data to the server. Simultaneously, it collects behavioral data such as the user's input speed and operation patterns. The collected behavioral data is used in subsequent processing for user sentiment analysis.

[0184] Step 3:

[0185] The server analyzes the received conditional data and generates keywords for searching expert information sources. A generative AI model is used here. Specifically, it extracts keywords related to relevant fields of expertise based on the input conditions. As output, a list of keywords necessary for the search is generated.

[0186] Step 4:

[0187] The server uses an emotion analysis engine to analyze the user's emotional state based on behavioral data received from the terminal. A generative AI model is used, and an example prompt is given: "Estimate this user's stress level." As a result, data indicating the stress level and emotional state is output.

[0188] Step 5:

[0189] The server searches for relevant lawyer candidates from expert information sources based on a keyword list. In addition, it considers data obtained from sentiment analysis to determine the priority of the lawyer candidates. Prioritization is performed by placing lawyers who provide more support higher up, for example, when the user has expressed anxiety.

[0190] Step 6:

[0191] The server sends a list of prioritized lawyers to the terminal. The terminal presents this information to the user. The user selects their preferred lawyer from the displayed list. This selection is sent to the server digitally and used for the booking process.

[0192] Step 7:

[0193] The server confirms the appointment with the lawyer selected by the user and generates detailed information about the meeting date, time, and location. The server then sends a final confirmation message to the user to notify them. This completes the booking process.

[0194] (Application Example 2)

[0195] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0196] There is a need to reliably and efficiently select the right expert for the user, and to make suggestions that take the user's emotional state into consideration during the selection process. Conventional systems simply made selections based on conditions, and lacked prioritization that took the user's emotions into account, resulting in low usability.

[0197] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0198] In this invention, the server includes means for analyzing user input conditions, means for searching a relevant expert database to extract candidates, and means for analyzing the user's emotions and adjusting the priority of candidates based on the results. This enables a more appropriate and rapid selection of experts that meet the user's individual needs and emotions.

[0199] A "generation application" is software used by users to input conditions and is responsible for sending the input data to the processing unit.

[0200] A "processing device" is a device that analyzes received conditions and extracts appropriate candidates from a related database.

[0201] A "specialist database" is a database that stores information about experts in various fields, and is used by processing units when they search for and extract candidates.

[0202] An "emotion engine" is software equipped with an algorithm that analyzes a user's emotions based on their actions and language input, and determines the degree of stress and anxiety.

[0203] "Prioritizing" refers to the process of determining the order in which the extracted candidates are presented, while taking into account the analysis results from the emotion engine.

[0204] "Method of making a reservation" refers to a system in which the user selects from the presented options and then goes through a procedure to confirm their selection.

[0205] A "final notice" is a notification that presents and confirms the details of the reservation selected by the user.

[0206] "Follow-up" refers to the process of providing additional information and support to help users assess their satisfaction and take the next steps after they have made a reservation.

[0207] The system for implementing this invention mainly consists of multiple components. The user inputs specific conditions using a generative application operable on smart glasses or other devices. During this process, the user's language use, input speed, and device operation history are tracked in real time and analyzed by an emotion engine. The analyzed emotion data is used to determine the user's stress level and urgency.

[0208] The server receives conditional and sentiment data from the user and extracts keywords using natural language processing techniques. Software libraries such as NLTK and spaCy are used for this process. The server then searches an expert database, extracts relevant candidates, and sets priorities based on the sentiment engine data.

[0209] Once a prioritized list is generated, it is notified to the user's device. This allows the user to easily select and book the expert best suited to their needs and preferences. Once the booking is confirmed, the server provides a final notification to the user and offers follow-up as needed.

[0210] For example, if a user enters "I'm looking for security measures that focus on enhanced nighttime security" and the analysis reveals a high level of anxiety, the server will prioritize presenting candidates for 24-hour security systems that can respond immediately. Through this process, suggestions are made that comprehensively consider the user's psychological state and specific needs.

[0211] Example of a prompt:

[0212] I need help choosing the right security service. My purpose is home security, especially strengthening it at night. I'm very worried about the recent increase in reports of suspicious activity. Please suggest the best service that meets these conditions.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The user launches the generation application via smart glasses or another device and enters the required information. This information includes the type of expert they want to select, their purpose, and their urgency. This data is collected along with the user's operation history and input speed. Based on the input data, the application records an operation log, and the emotion engine begins analysis.

[0216] Step 2:

[0217] The server receives user condition data sent from the generation application. Next, it extracts important keywords from the input data using a natural language processing library (e.g., spaCy). In this step, the user conditions are analyzed and a search query for the expert database is generated. It takes condition data as input and generates a search query as output.

[0218] Step 3:

[0219] The server uses user interaction data to analyze the user's emotional state with an emotion engine. The analysis considers factors such as input speed and tone of voice, and evaluates the degree of stress and anxiety. It receives interaction data as input and outputs an emotion analysis report based on that information. This analysis is used by experts for prioritizing tasks.

[0220] Step 4:

[0221] The server uses the extracted keywords to search the expert database and generate a list of relevant candidates. This database query lists experts who meet the criteria and provides data for evaluation. It accepts a query as input and outputs a list of candidates from the database that meet the criteria.

[0222] Step 5:

[0223] The server takes the sentiment analysis results into account to determine the priority of the candidate list. For users experiencing high stress levels, specialists with high levels of support and responsiveness are placed higher in the priority list. The server uses the candidate list and sentiment report as input to output a prioritized list.

[0224] Step 6:

[0225] The server sends a prioritized list of experts to the terminal and presents it to the user. The user makes a selection from this list and confirms the reservation via the generating application. It receives a prioritized list as input and outputs the final reservation information after presenting it to the user.

[0226] Step 7:

[0227] Once a reservation is confirmed, the server sends a final notification to the user and follows up as needed. This notification provides information including reservation confirmation and additional guidance, giving the user peace of mind. It receives reservation data as input and outputs a confirmation notification and follow-up information.

[0228] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0229] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0230] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0234] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0235] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0236] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0237] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0238] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0239] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0240] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0241] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0242] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0243] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0244] This invention provides a system that allows users to efficiently find a suitable lawyer and easily make an appointment. The system consists of a generation application, a processing unit, and a professional database.

[0245] First, the user uses the device's generation application to input various criteria for selecting a lawyer in natural language. These criteria include desired specialty, budget, years of experience, and location. The device then transmits this information to the processing unit.

[0246] The transmitted data is received by a processing unit on the server. The server uses natural language processing (NLP) technology to analyze the input and extract the necessary data. Based on the analyzed data, the server accesses a database of experts and extracts candidate lawyers that meet the criteria. The extracted candidates are evaluated and prioritized using an AI model. This evaluation is based on past data, and the system recommends the lawyer who best matches the user's preferences.

[0247] The resulting list of candidates is presented to the user via their device. The user can select their preferred lawyer from the presented list and make a reservation directly. Once the reservation is confirmed, the server processes the reservation information and sends a confirmation notification to the user. This notification consists of detailed information, including the date, time, and location of the meeting, and can be viewed on the LINE app.

[0248] For example, if a user enters criteria such as "a lawyer in Tokyo specializing in traffic accidents, with a budget of 50,000 yen or less, and over 10 years of experience," the server searches its expert database for lawyers who meet these criteria, evaluates them, and presents them to the user. The user can then select a lawyer and make a reservation, accessing the necessary services without complicated procedures. In this way, the system provides users with a quick and convenient means of service.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The user launches a generation application on their device and enters their desired lawyer's criteria in natural language. These criteria include specialty, budget, years of experience, and location.

[0252] Step 2:

[0253] The device converts the conditions entered by the user into structured data and sends it to the server as data. Data transmission is performed using the LINE API.

[0254] Step 3:

[0255] The server analyzes the received data and uses natural language processing techniques to extract keywords that meet the specified criteria. This structures the data and transforms it into more usable information.

[0256] Step 4:

[0257] The server compares the analysis results with a database of experts and extracts lawyer candidates that meet the criteria. The extraction process uses an algorithm that evaluates the degree of match with the characteristics of each lawyer in the database.

[0258] Step 5:

[0259] The server uses an AI model to evaluate and rank the extracted candidate lawyers. This evaluation is based on how well each lawyer is suited to the user's requirements.

[0260] Step 6:

[0261] The server generates a prioritized list of candidates and sends it to the terminal. This list is organized according to the user's criteria and priority.

[0262] Step 7:

[0263] The user reviews a list of candidates displayed on their device and selects their preferred lawyer. The user can then schedule a meeting with the selected lawyer through the application.

[0264] Step 8:

[0265] The server receives the reservation information, notifies the selected lawyer, and also sends a confirmation message to the user. The notification includes details such as the date, time, and location of the meeting.

[0266] Through the above processing steps, users can efficiently and quickly search for, select, and book an appointment with a lawyer who is suitable for them.

[0267] (Example 1)

[0268] Next, we will describe Example 1. 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."

[0269] The challenge is to provide users with a means to quickly and efficiently find a suitable expert and easily make a reservation. In particular, there is a need for technology that automatically evaluates and selects experts using conditions entered in natural language and presents the most suitable candidates to the user.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0271] In this invention, the server includes means for the user to input conditions using natural language, means for the information processing device to analyze the conditions using natural language processing technology, and means for evaluating and prioritizing candidates using a generative artificial intelligence model. This makes it possible to quickly and accurately present experts to the user and to easily make reservations.

[0272] A "user" is someone who uses the system to find and book an expert.

[0273] "Conditions" refer to a set of information that users input in natural language based on their wishes and requirements, and include parameters necessary for selecting an expert.

[0274] An "information processing device" is a computer system that receives conditions transmitted by a user and performs analysis.

[0275] "Natural language processing technology" is a technique that analyzes natural language used by humans and converts it into a format that can be processed by computers.

[0276] A "collection of expert information" is a database containing detailed data about experts, and is a searchable information source based on various criteria.

[0277] A "generative artificial intelligence model" is an artificial intelligence program that learns from past data and has the ability to understand and evaluate human intentions.

[0278] "Evaluation" refers to the process by which a generative artificial intelligence model calculates the degree of suitability of expert candidates based on the input conditions and ranks them accordingly.

[0279] Prioritization is the process of arranging potential experts in the optimal order based on evaluation results.

[0280] "Presentation" refers to the process of displaying results in a format that is easy for users to understand, and includes providing information visually.

[0281] A "reservation" is the act of confirming the date, time, and location with a designated expert, and is performed through a system.

[0282] This invention is a system that enables users to efficiently find and easily book necessary experts using a generation application installed on their own devices. The system mainly consists of client terminals, a server, an expert database, a generation AI model, and a notification application.

[0283] The user launches a generation application on their device and enters their desired expert criteria in natural language (for example, "Expert in traffic accidents in Tokyo, budget under 50,000 yen, 10+ years of experience"). This input is converted into data format on the device and sent to the server.

[0284] The server analyzes the received data by leveraging natural language processing technology. Specifically, it uses an open-source natural language processing library to extract important parameters from the input conditions. Based on the conditions obtained from this analysis, the server accesses the expert database and extracts candidate experts who meet the conditions.

[0285] Furthermore, the generated artificial intelligence model evaluates the extracted candidates. The AI model selects the most suitable expert for the user based on past matching histories and determines the priorities. This AI model is constructed using a machine learning framework and performs scoring considering the expert's experience value and the user's evaluation.

[0286] The resulting list of expert candidates is sent to the user's terminal and displayed through the generated application. The user can select the necessary expert from this list and perform the reservation procedure. When the reservation is completed, the server uses the LINE API to send a confirmation notification of the reservation details to the user. The notification includes details such as the date, time, and location of the reserved interview.

[0287] With this system, the user can easily and quickly find the expert most suitable for their conditions. Also, due to the intuitive condition input in natural language, even users without specialized knowledge can easily operate, enabling efficient selection of experts. As a result, the convenience of the user is greatly improved.

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The user launches the generation application on their device and inputs criteria for selecting a specialist in natural language. This input includes areas of expertise, region, budget, and years of experience. Specifically, the user might input a sentence like, "A specialist in traffic accidents in Tokyo, with a budget of 50,000 yen or less and over 10 years of experience." The device parses this input, converts it into data format, and sends it to the server via the network.

[0291] Input: Natural language conditions entered by the user on the device

[0292] Output: Conditions for the data format sent to the server

[0293] Step 2:

[0294] The server analyzes the received conditional data using natural language processing techniques. This involves using open-source natural language processing libraries to extract keywords and important information from the conditions. Specifically, the data processing involves tokenizing the conditional statements and interpreting their meaning.

[0295] Input: Conditions for the data format received by the server

[0296] Output: Analyzed keywords and conditional information

[0297] Step 3:

[0298] The server accesses the expert database based on the analysis results and searches for candidate experts that match the criteria. It then executes a database query and lists the expert information that matches the criteria.

[0299] Input: Analyzed keywords and conditional information

[0300] Output: List of expert candidates that meet the criteria

[0301] Step 4:

[0302] The server uses a generated artificial intelligence model to evaluate and prioritize a list of expert candidates. Based on past matching data, the AI model calculates scores to identify the candidates most suitable for the user's conditions. This evaluation determines the priority of the candidates.

[0303] Input: List of expert candidates

[0304] Output: List of evaluated and prioritized expert candidates

[0305] Step 5:

[0306] The server sends the list of evaluated expert candidates to the user's terminal. The terminal receives this list and visually presents it to the user on the generated application.

[0307] Input: List of evaluated and prioritized expert candidates

[0308] Output: List of expert candidates presented to the user

[0309] Step 6:

[0310] The user selects the desired expert from the presented list and makes a reservation. The candidate selected through the generated application is sent to the server.

[0311] Input: Expert candidate selected by the user

[0312] Output: Reservation information

[0313] Step 7:

[0314] The server processes the reservation information sent by the user and generates a confirmation notification. This notification includes details such as date, time, and location, and is sent to the user using the LINE API. The user can confirm this on the LINE app and finalize the reservation details.

[0315] Input: Reservation Information

[0316] Output: Confirmation notification sent to the user

[0317] (Application Example 1)

[0318] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0319] Traditional expert booking systems presented a problem: finding a suitable expert was time-consuming and cumbersome for users. Furthermore, quick searches and bookings while on the go or away from the office were difficult, limiting user convenience. Additionally, a lack of effective visual information made it difficult for users to make quick decisions on the spot.

[0320] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0321] In this invention, the server includes means for the user to input conditions through a generation application, means for transmitting the conditions to a processing unit, means for extracting candidates from a relevant expert database, means for the user to receive expert information via augmented reality display through a mobile device while on the move, and means for making a reservation using voice input. As a result, the user can visually and in real time obtain information on the most suitable expert even while on the move, and quickly confirm the reservation on the spot using voice.

[0322] A "generation application" is software that allows a user to input conditions and send them to a processing unit.

[0323] A "processing device" is a computer device that analyzes input conditions and extracts candidate experts from a database of relevant experts.

[0324] A "specialist database" is a collection of data that manages information on various types of experts and provides appropriate candidates based on specific criteria.

[0325] Augmented reality is a technology that overlays visual information onto the real world, providing users with an intuitive way to convey expert information.

[0326] "Voice input" is an interface that allows users to input instructions into a system using their voice.

[0327] A "portable device" is a terminal that a user can carry with them, and includes smart glasses and smartphones.

[0328] To implement this invention, it is necessary to install a generation application on the user's mobile device. This application provides an interface that allows the user to input expert search criteria in natural language. Mobile devices such as smart glasses and smartphones are primarily used.

[0329] When a user enters conditions, those conditions are sent from the terminal to the server's processing unit. The server first uses natural language processing (NLP) techniques to analyze the conditions and extract the necessary data. This analysis utilizes specific NLP libraries and machine learning models.

[0330] Based on the analyzed data, the server accesses a database of experts and extracts candidate experts that meet the criteria. These candidates are then evaluated and prioritized using a generative AI model. This evaluation process utilizes historical data to prioritize experts who best match the user's preferences.

[0331] The evaluation results are presented to the user using augmented reality (AR) display on their mobile device. AR software and the device's built-in camera are used to intuitively visualize expert information within the real world. Users can make reservations on the spot using voice input. This feature is supported by the mobile device's voice recognition hardware and software.

[0332] For example, if a user enters the criteria "I'm looking for a lawyer specializing in traffic accidents in Tokyo," the server searches its database based on this information, prioritizes available lawyers, and presents them to the user using augmented reality. An example of a prompt might be, "I'm looking for a lawyer specializing in traffic accidents in Tokyo. I'd prefer someone with over 10 years of experience and a fee of under 50,000 yen." In this way, users can efficiently find the most suitable professional and easily complete a booking.

[0333] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0334] Step 1:

[0335] The user uses a generation application on their mobile device to enter search criteria for experts in natural language. These criteria may include specific details, such as "lawyers in Tokyo specializing in traffic accidents." The entered information is then transmitted from the terminal to the server's processing unit.

[0336] Step 2:

[0337] The server's processing unit performs natural language processing (NLP) on the received conditions. It applies NLP techniques to the received text data to extract important keywords and requirements. This analysis outputs necessary conditions such as "Tokyo," "traffic accident," and "lawyer."

[0338] Step 3:

[0339] The server uses the analyzed keywords to search the expert database. It extracts candidates that match the criteria from the lawyer information stored in the database. In this step, a database query is executed to retrieve entries that match the criteria as output.

[0340] Step 4:

[0341] The extracted candidates are evaluated using a generative AI model. To prioritize candidates based on past success stories and evaluation data, the AI ​​model receives candidate profiles as input, evaluates how well they match the user's preferences, and generates a prioritized list.

[0342] Step 5:

[0343] The server sends the evaluation results to the mobile device, where it displays them in augmented reality. Using AR software, expert information is overlaid onto the user's field of view. For example, the name and details of the most suitable lawyer might be displayed.

[0344] Step 6:

[0345] The user uses voice input to select their preferred lawyer from the presented options and make a reservation. The voice recognition function of the mobile device analyzes the user's instructions and sends them to the server. The server processes the received instructions and confirms the reservation.

[0346] Step 7:

[0347] Based on the reservation confirmation information, the server sends a final notification to the user's mobile device. This notification includes details such as the reserved time and location, and is available for the user to review.

[0348] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0349] This invention provides a system that allows users to efficiently find a lawyer suitable for them, and furthermore, takes the user's emotions into consideration during the selection process. This system consists of a combination of a generation application, a processing unit, a professional database, and an emotion engine.

[0350] The user launches a generation application using their device and enters requirements for a lawyer. These requirements include areas of expertise, budget, years of experience, and location, and the device sends this information to a server-side processing unit. Simultaneously, an emotion engine analyzes the user's emotions based on their word choice, input speed, and device operation history. This emotion analysis is used to determine the user's level of stress and anxiety.

[0351] The server, after analyzing the received conditions and sentiment data, uses natural language processing technology to extract relevant keywords and searches a database of experts. The extracted list of candidates is then prioritized, taking into account the results of the sentiment engine's analysis. For example, if the user is feeling anxious, lawyers with a strong reputation for support will be presented first.

[0352] A prioritized list is sent to the device and presented to the user. The user reviews this list, selects a lawyer that suits their needs, and makes an appointment. Once the appointment is confirmed, the server sends a notification and a confirmation message to the user regarding the date, time, and location of the meeting.

[0353] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and simultaneously indicates a high level of stress, the server will prioritize recommending lawyers with strong support systems, especially those with expertise in child custody. In this way, the system not only selects candidates based on criteria but also considers the user's psychological state when making suggestions, thereby achieving more effective matching.

[0354] The following describes the processing flow.

[0355] Step 1:

[0356] The user launches a generation application on their device and enters the requirements for the lawyer they are looking for. These requirements include specialty, location, budget, and years of experience. As the user enters their information, an emotion engine analyzes their emotions based on their typing speed and word choice.

[0357] Step 2:

[0358] The terminal sends user input data and analysis data from the emotion engine to the server. This allows the server to receive both conditional and emotional information simultaneously.

[0359] Step 3:

[0360] Based on the conditions received by the server, keywords are extracted using natural language processing technology. Next, a database of experts is consulted to search for relevant lawyer candidates. Preparations are made to incorporate sentiment data during this process.

[0361] Step 4:

[0362] The server uses an AI model to evaluate and prioritize the list of candidates. This evaluation incorporates the results of an emotion engine analysis, and if it determines that the situation is urgent, the system adjusts to display lawyers who can respond more quickly at the top of the list.

[0363] Step 5:

[0364] A prioritized list of potential lawyers is sent from the server to the user's terminal. The user can then review this list on their terminal and select the most suitable candidate.

[0365] Step 6:

[0366] The user makes a reservation with a lawyer of their choice. The terminal sends the reservation information to the server, and the server notifies both the lawyer and the user of the confirmed reservation.

[0367] Step 7:

[0368] The server sends a final confirmation notification to the user. This clearly communicates the interview date and location to the user.

[0369] This process allows users not only to find a lawyer that meets their requirements, but also to receive suggestions that take their psychological state into account, enabling them to make better choices.

[0370] (Example 2)

[0371] Next, we will describe Example 2. 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".

[0372] Traditionally, when selecting a professional, users would only input their own criteria, and the system would select a professional based on those criteria. However, the user's emotions and psychological state were ignored, and therefore the suggested professional was not always the best fit for the user's current situation. This resulted in a problem where the efficiency and effectiveness of professional selection were not fully realized.

[0373] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0374] In this invention, the server includes means for inputting conditions through a generation program, means for analyzing emotions based on user behavior data, and means for determining the priority of expert candidates considering the emotion analysis results. This makes it possible to select experts that take into account not only the user's conditions but also their emotions and psychological state, enabling the presentation of experts that are more suitable for the user.

[0375] A "generator program" is software that allows users to input necessary criteria when searching for experts.

[0376] An "information processing device" is a device that analyzes the conditions entered by the user, extracts appropriate candidates from expert information sources, and presents them.

[0377] An "expert information source" is a database that accumulates and makes searchable information about various experts.

[0378] "Action data" refers to data such as the user's input speed, word choice, and operation history when entering information.

[0379] "Methods for analyzing emotions" refer to processes that determine the user's emotional state at a given time based on their behavioral data.

[0380] "Methods for determining priorities" refers to the process of determining the order in which to present the extracted expert candidates, based on the user's conditions and the results of sentiment analysis.

[0381] The system of this invention takes into account the user's psychological state in the process of efficiently selecting a suitable expert for themselves. The system consists of the following components:

[0382] 1. Terminal Usage: The user launches the generation program via the terminal and inputs the criteria necessary for selecting an expert. These criteria include area of ​​expertise, budget, years of experience, and location. The terminal is equipped with a function to collect the data entered by the user and the operation data during the input process.

[0383] 2. Analysis by the Information Processing Device: The terminal transmits the user's input conditions to the information processing device. This information processing device analyzes the conditions and extracts relevant experts from a database called the expert information source.

[0384] 3. Inclusion of emotion analysis function: The server uses an emotion analysis engine based on the user's behavior data to determine the user's emotions. A generative AI model is used here to help understand the user's level of stress and anxiety.

[0385] 4. Prioritization: The server determines the priority of expert candidates based on the user's conditions and the results of sentiment analysis. This makes it possible to present the expert best suited to the user's psychological state.

[0386] 5. Expert Selection and Booking: The user views a prioritized list of experts on their device and makes a selection. The server confirms the booking with the selected expert, and details such as the date, time, and location of the meeting are sent to the user.

[0387] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and indicates a high level of stress, the server will prioritize recommending lawyers who are strong in child custody issues and have a well-established support system. This allows users to be matched with the most suitable professional, taking into account not only their specific needs but also their psychological state.

[0388] An example of a prompt message would be, "If the user is anxious, provide a list of trustworthy lawyers," allowing the generative AI model to support the selection of an expert based on emotion.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The user launches the generation program using a terminal. The user enters information such as the lawyer's area of ​​expertise, desired budget, years of experience, and location into the on-screen input form. The entered information is saved digitally on the terminal and prepared for the next processing step.

[0392] Step 2:

[0393] The terminal sends user-inputted conditional data to the server. Simultaneously, it collects behavioral data such as the user's input speed and operation patterns. The collected behavioral data is used in subsequent processing for user sentiment analysis.

[0394] Step 3:

[0395] The server analyzes the received conditional data and generates keywords for searching expert information sources. A generative AI model is used here. Specifically, it extracts keywords related to relevant fields of expertise based on the input conditions. As output, a list of keywords necessary for the search is generated.

[0396] Step 4:

[0397] The server uses an emotion analysis engine to analyze the user's emotional state based on behavioral data received from the terminal. A generative AI model is used, and an example prompt is given: "Estimate this user's stress level." As a result, data indicating the stress level and emotional state is output.

[0398] Step 5:

[0399] The server searches for relevant lawyer candidates from expert information sources based on a keyword list. In addition, it considers data obtained from sentiment analysis to determine the priority of the lawyer candidates. Prioritization is performed by placing lawyers who provide more support higher up, for example, when the user has expressed anxiety.

[0400] Step 6:

[0401] The server sends a list of prioritized lawyers to the terminal. The terminal presents this information to the user. The user selects their preferred lawyer from the displayed list. This selection is sent to the server digitally and used for the booking process.

[0402] Step 7:

[0403] The server confirms the appointment with the lawyer selected by the user and generates detailed information about the meeting date, time, and location. The server then sends a final confirmation message to the user to notify them. This completes the booking process.

[0404] (Application Example 2)

[0405] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0406] There is a need to reliably and efficiently select the right expert for the user, and to make suggestions that take the user's emotional state into consideration during the selection process. Conventional systems simply made selections based on conditions, and lacked prioritization that took the user's emotions into account, resulting in low usability.

[0407] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0408] In this invention, the server includes means for analyzing user input conditions, means for searching a relevant expert database to extract candidates, and means for analyzing the user's emotions and adjusting the priority of candidates based on the results. This enables a more appropriate and rapid selection of experts that meet the user's individual needs and emotions.

[0409] A "generation application" is software used by users to input conditions and is responsible for sending the input data to the processing unit.

[0410] A "processing device" is a device that analyzes received conditions and extracts appropriate candidates from a related database.

[0411] A "specialist database" is a database that stores information about experts in various fields, and is used by processing units when they search for and extract candidates.

[0412] An "emotion engine" is software equipped with an algorithm that analyzes a user's emotions based on their actions and language input, and determines the degree of stress and anxiety.

[0413] "Prioritizing" refers to the process of determining the order in which the extracted candidates are presented, while taking into account the analysis results from the emotion engine.

[0414] "Method of making a reservation" refers to a system in which the user selects from the presented options and then goes through a procedure to confirm their selection.

[0415] A "final notice" is a notification that presents and confirms the details of the reservation selected by the user.

[0416] "Follow-up" refers to the process of providing additional information and support to help users assess their satisfaction and take the next steps after they have made a reservation.

[0417] The system for implementing this invention mainly consists of multiple components. The user inputs specific conditions using a generative application operable on smart glasses or other devices. During this process, the user's language use, input speed, and device operation history are tracked in real time and analyzed by an emotion engine. The analyzed emotion data is used to determine the user's stress level and urgency.

[0418] The server receives conditional and sentiment data from the user and extracts keywords using natural language processing techniques. Software libraries such as NLTK and spaCy are used for this process. The server then searches an expert database, extracts relevant candidates, and sets priorities based on the sentiment engine data.

[0419] Once a prioritized list is generated, it is notified to the user's device. This allows the user to easily select and book the expert best suited to their needs and preferences. Once the booking is confirmed, the server provides a final notification to the user and offers follow-up as needed.

[0420] For example, if a user enters "I'm looking for security measures that focus on enhanced nighttime security" and the analysis reveals a high level of anxiety, the server will prioritize presenting candidates for 24-hour security systems that can respond immediately. Through this process, suggestions are made that comprehensively consider the user's psychological state and specific needs.

[0421] Example of a prompt:

[0422] I need help choosing the right security service. My purpose is home security, especially strengthening it at night. I'm very worried about the recent increase in reports of suspicious activity. Please suggest the best service that meets these conditions.

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] The user launches the generation application via smart glasses or another device and enters the required information. This information includes the type of expert they want to select, their purpose, and their urgency. This data is collected along with the user's operation history and input speed. Based on the input data, the application records an operation log, and the emotion engine begins analysis.

[0426] Step 2:

[0427] The server receives user condition data sent from the generation application. Next, it extracts important keywords from the input data using a natural language processing library (e.g., spaCy). In this step, the user conditions are analyzed and a search query for the expert database is generated. It takes condition data as input and generates a search query as output.

[0428] Step 3:

[0429] The server uses user interaction data to analyze the user's emotional state with an emotion engine. The analysis considers factors such as input speed and tone of voice, and evaluates the degree of stress and anxiety. It receives interaction data as input and outputs an emotion analysis report based on that information. This analysis is used by experts for prioritizing tasks.

[0430] Step 4:

[0431] The server uses the extracted keywords to search the expert database and generate a list of relevant candidates. This database query lists experts who meet the criteria and provides data for evaluation. It accepts a query as input and outputs a list of candidates from the database that meet the criteria.

[0432] Step 5:

[0433] The server takes the sentiment analysis results into account to determine the priority of the candidate list. For users experiencing high stress levels, specialists with high levels of support and responsiveness are placed higher in the priority list. The server uses the candidate list and sentiment report as input to output a prioritized list.

[0434] Step 6:

[0435] The server sends a prioritized list of experts to the terminal and presents it to the user. The user makes a selection from this list and confirms the reservation via the generating application. It receives a prioritized list as input and outputs the final reservation information after presenting it to the user.

[0436] Step 7:

[0437] Once a reservation is confirmed, the server sends a final notification to the user and follows up as needed. This notification provides information including reservation confirmation and additional guidance, giving the user peace of mind. It receives reservation data as input and outputs a confirmation notification and follow-up information.

[0438] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0439] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0444] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0445] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0446] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0448] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0449] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0450] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0451] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0452] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0453] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0454] This invention provides a system that allows users to efficiently find a suitable lawyer and easily make an appointment. The system consists of a generation application, a processing unit, and a professional database.

[0455] First, the user uses the device's generation application to input various criteria for selecting a lawyer in natural language. These criteria include desired specialty, budget, years of experience, and location. The device then transmits this information to the processing unit.

[0456] The transmitted data is received by a processing unit on the server. The server uses natural language processing (NLP) technology to analyze the input and extract the necessary data. Based on the analyzed data, the server accesses a database of experts and extracts candidate lawyers that meet the criteria. The extracted candidates are evaluated and prioritized using an AI model. This evaluation is based on past data, and the system recommends the lawyer who best matches the user's preferences.

[0457] The resulting list of candidates is presented to the user via their device. The user can select their preferred lawyer from the presented list and make a reservation directly. Once the reservation is confirmed, the server processes the reservation information and sends a confirmation notification to the user. This notification consists of detailed information, including the date, time, and location of the meeting, and can be viewed on the LINE app.

[0458] For example, if a user enters criteria such as "a lawyer in Tokyo specializing in traffic accidents, with a budget of 50,000 yen or less, and over 10 years of experience," the server searches its expert database for lawyers who meet these criteria, evaluates them, and presents them to the user. The user can then select a lawyer and make a reservation, accessing the necessary services without complicated procedures. In this way, the system provides users with a quick and convenient means of service.

[0459] The following describes the processing flow.

[0460] Step 1:

[0461] The user launches a generation application on their device and enters their desired lawyer's criteria in natural language. These criteria include specialty, budget, years of experience, and location.

[0462] Step 2:

[0463] The device converts the conditions entered by the user into structured data and sends it to the server as data. Data transmission is performed using the LINE API.

[0464] Step 3:

[0465] The server analyzes the received data and uses natural language processing techniques to extract keywords that meet the specified criteria. This structures the data and transforms it into more usable information.

[0466] Step 4:

[0467] The server compares the analysis results with a database of experts and extracts lawyer candidates that meet the criteria. The extraction process uses an algorithm that evaluates the degree of match with the characteristics of each lawyer in the database.

[0468] Step 5:

[0469] The server uses an AI model to evaluate and rank the extracted candidate lawyers. This evaluation is based on how well each lawyer is suited to the user's requirements.

[0470] Step 6:

[0471] The server generates a prioritized list of candidates and sends it to the terminal. This list is organized according to the user's criteria and priority.

[0472] Step 7:

[0473] The user reviews a list of candidates displayed on their device and selects their preferred lawyer. The user can then schedule a meeting with the selected lawyer through the application.

[0474] Step 8:

[0475] The server receives the reservation information, notifies the selected lawyer, and also sends a confirmation message to the user. The notification includes details such as the date, time, and location of the meeting.

[0476] Through the above processing steps, users can efficiently and quickly search for, select, and book an appointment with a lawyer who is suitable for them.

[0477] (Example 1)

[0478] Next, we will describe Example 1. 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."

[0479] The challenge is to provide users with a means to quickly and efficiently find a suitable expert and easily make a reservation. In particular, there is a need for technology that automatically evaluates and selects experts using conditions entered in natural language and presents the most suitable candidates to the user.

[0480] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0481] In this invention, the server includes means for the user to input conditions using natural language, means for the information processing device to analyze the conditions using natural language processing technology, and means for evaluating and prioritizing candidates using a generative artificial intelligence model. This makes it possible to quickly and accurately present experts to the user and to easily make reservations.

[0482] A "user" is someone who uses the system to find and book an expert.

[0483] "Conditions" refer to a set of information that users input in natural language based on their wishes and requirements, and include parameters necessary for selecting an expert.

[0484] An "information processing device" is a computer system that receives conditions transmitted by a user and performs analysis.

[0485] "Natural language processing technology" is a technique that analyzes natural language used by humans and converts it into a format that can be processed by computers.

[0486] A "collection of expert information" is a database containing detailed data about experts, and is a searchable information source based on various criteria.

[0487] A "generative artificial intelligence model" is an artificial intelligence program that learns from past data and has the ability to understand and evaluate human intentions.

[0488] "Evaluation" refers to the process by which a generative artificial intelligence model calculates the degree of suitability of expert candidates based on the input conditions and ranks them accordingly.

[0489] Prioritization is the process of arranging potential experts in the optimal order based on evaluation results.

[0490] "Presentation" refers to the process of displaying results in a format that is easy for users to understand, and includes providing information visually.

[0491] A "reservation" is the act of confirming the date, time, and location with a designated expert, and is performed through a system.

[0492] This invention is a system that enables users to efficiently find and easily book necessary experts using a generation application installed on their own devices. The system mainly consists of client terminals, a server, an expert database, a generation AI model, and a notification application.

[0493] The user launches a generation application on their device and enters their desired expert criteria in natural language (for example, "Expert in traffic accidents in Tokyo, budget under 50,000 yen, 10+ years of experience"). This input is converted into data format on the device and sent to the server.

[0494] The server analyzes the received data using natural language processing techniques. Specifically, it uses open-source natural language processing libraries to extract important parameters from the input conditions. Based on the conditions obtained through this analysis, the server accesses an expert database and extracts candidate experts that meet the conditions.

[0495] Furthermore, the extracted candidates are evaluated by a generative artificial intelligence model. Based on past matching history, the AI ​​model selects the most suitable expert for the user and determines their priority. This AI model is built using a machine learning framework and scores experts based on their experience and user ratings.

[0496] The resulting list of potential experts is sent to the user's device and displayed through the generated application. The user can then select the desired expert from this list and proceed with the booking process. Once the booking is complete, the server uses the LINE API to send a confirmation notification to the user. The notification includes details such as the date, time, and location of the scheduled meeting.

[0497] This system allows users to easily and quickly find the expert best suited to their needs. Furthermore, intuitive input of criteria using natural language makes it easy to operate even for users without specialized knowledge, enabling efficient expert selection. As a result, user convenience is significantly improved.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The user launches the generation application on their device and inputs criteria for selecting a specialist in natural language. This input includes areas of expertise, region, budget, and years of experience. Specifically, the user might input a sentence like, "A specialist in traffic accidents in Tokyo, with a budget of 50,000 yen or less and over 10 years of experience." The device parses this input, converts it into data format, and sends it to the server via the network.

[0501] Input: Natural language conditions entered by the user on the device

[0502] Output: Conditions for the data format sent to the server

[0503] Step 2:

[0504] The server analyzes the received conditional data using natural language processing techniques. This involves using open-source natural language processing libraries to extract keywords and important information from the conditions. Specifically, the data processing involves tokenizing the conditional statements and interpreting their meaning.

[0505] Input: Conditions for the data format received by the server

[0506] Output: Analyzed keywords and conditional information

[0507] Step 3:

[0508] The server accesses the expert database based on the analysis results and searches for candidate experts that match the criteria. It then executes a database query and lists the expert information that matches the criteria.

[0509] Input: Analyzed keywords and conditional information

[0510] Output: List of expert candidates that meet the criteria

[0511] Step 4:

[0512] The server uses a generative artificial intelligence model to evaluate and prioritize a list of expert candidates. Based on past matching data, the AI ​​model calculates a score to identify the candidate best suited to the user's criteria. This evaluation determines the candidate's priority.

[0513] Input: List of expert candidates

[0514] Output: List of evaluated and prioritized expert candidates

[0515] Step 5:

[0516] The server sends a list of evaluated expert candidates to the user's terminal. The terminal receives this list and presents it visually to the user on the generating application.

[0517] Input: List of evaluated and prioritized expert candidates

[0518] Output: A list of expert candidates presented to the user.

[0519] Step 6:

[0520] The user selects their preferred expert from the presented list and makes a reservation. The selected candidates are sent to the server via the generation application.

[0521] Input: User-selected expert candidates

[0522] Output: Reservation Information

[0523] Step 7:

[0524] The server processes the reservation information sent by the user and generates a confirmation notification. This notification includes details such as the date, time, and location, and is sent to the user using the LINE API. The user can then check this notification in the LINE app and confirm their reservation.

[0525] Input: Reservation Information

[0526] Output: Confirmation notification sent to the user

[0527] (Application Example 1)

[0528] Next, we will explain Application Example 1. In the following explanation, 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."

[0529] Traditional expert booking systems presented a problem: finding a suitable expert was time-consuming and cumbersome for users. Furthermore, quick searches and bookings while on the go or away from the office were difficult, limiting user convenience. Additionally, a lack of effective visual information made it difficult for users to make quick decisions on the spot.

[0530] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0531] In this invention, the server includes means for the user to input conditions through a generation application, means for transmitting the conditions to a processing unit, means for extracting candidates from a relevant expert database, means for the user to receive expert information via augmented reality display through a mobile device while on the move, and means for making a reservation using voice input. As a result, the user can visually and in real time obtain information on the most suitable expert even while on the move, and quickly confirm the reservation on the spot using voice.

[0532] A "generation application" is software that allows a user to input conditions and send them to a processing unit.

[0533] A "processing device" is a computer device that analyzes input conditions and extracts candidate experts from a database of relevant experts.

[0534] A "specialist database" is a collection of data that manages information on various types of experts and provides appropriate candidates based on specific criteria.

[0535] Augmented reality is a technology that overlays visual information onto the real world, providing users with an intuitive way to convey expert information.

[0536] "Voice input" is an interface that allows users to input instructions into a system using their voice.

[0537] A "portable device" is a terminal that a user can carry with them, and includes smart glasses and smartphones.

[0538] To implement this invention, it is necessary to install a generation application on the user's mobile device. This application provides an interface that allows the user to input expert search criteria in natural language. Mobile devices such as smart glasses and smartphones are primarily used.

[0539] When a user enters conditions, those conditions are sent from the terminal to the server's processing unit. The server first uses natural language processing (NLP) techniques to analyze the conditions and extract the necessary data. This analysis utilizes specific NLP libraries and machine learning models.

[0540] Based on the analyzed data, the server accesses a database of experts and extracts candidate experts that meet the criteria. These candidates are then evaluated and prioritized using a generative AI model. This evaluation process utilizes historical data to prioritize experts who best match the user's preferences.

[0541] The evaluation results are presented to the user using augmented reality (AR) display on their mobile device. AR software and the device's built-in camera are used to intuitively visualize expert information within the real world. Users can make reservations on the spot using voice input. This feature is supported by the mobile device's voice recognition hardware and software.

[0542] For example, if a user enters the criteria "I'm looking for a lawyer specializing in traffic accidents in Tokyo," the server searches its database based on this information, prioritizes available lawyers, and presents them to the user using augmented reality. An example of a prompt might be, "I'm looking for a lawyer specializing in traffic accidents in Tokyo. I'd prefer someone with over 10 years of experience and a fee of under 50,000 yen." In this way, users can efficiently find the most suitable professional and easily complete a booking.

[0543] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0544] Step 1:

[0545] The user uses a generation application on their mobile device to enter search criteria for experts in natural language. These criteria may include specific details, such as "lawyers in Tokyo specializing in traffic accidents." The entered information is then transmitted from the terminal to the server's processing unit.

[0546] Step 2:

[0547] The server's processing unit performs natural language processing (NLP) on the received conditions. It applies NLP techniques to the received text data to extract important keywords and requirements. This analysis outputs necessary conditions such as "Tokyo," "traffic accident," and "lawyer."

[0548] Step 3:

[0549] The server uses the analyzed keywords to search the expert database. It extracts candidates that match the criteria from the lawyer information stored in the database. In this step, a database query is executed to retrieve entries that match the criteria as output.

[0550] Step 4:

[0551] The extracted candidates are evaluated using a generative AI model. To prioritize candidates based on past success stories and evaluation data, the AI ​​model receives candidate profiles as input, evaluates how well they match the user's preferences, and generates a prioritized list.

[0552] Step 5:

[0553] The server sends the evaluation results to the mobile device, where it displays them in augmented reality. Using AR software, expert information is overlaid onto the user's field of view. For example, the name and details of the most suitable lawyer might be displayed.

[0554] Step 6:

[0555] The user uses voice input to select their preferred lawyer from the presented options and make a reservation. The voice recognition function of the mobile device analyzes the user's instructions and sends them to the server. The server processes the received instructions and confirms the reservation.

[0556] Step 7:

[0557] Based on the reservation confirmation information, the server sends a final notification to the user's mobile device. This notification includes details such as the reserved time and location, and is available for the user to review.

[0558] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0559] This invention provides a system that allows users to efficiently find a lawyer suitable for them, and furthermore, takes the user's emotions into consideration during the selection process. This system consists of a combination of a generation application, a processing unit, a professional database, and an emotion engine.

[0560] The user launches a generation application using their device and enters requirements for a lawyer. These requirements include areas of expertise, budget, years of experience, and location, and the device sends this information to a server-side processing unit. Simultaneously, an emotion engine analyzes the user's emotions based on their word choice, input speed, and device operation history. This emotion analysis is used to determine the user's level of stress and anxiety.

[0561] The server, after analyzing the received conditions and sentiment data, uses natural language processing technology to extract relevant keywords and searches a database of experts. The extracted list of candidates is then prioritized, taking into account the results of the sentiment engine's analysis. For example, if the user is feeling anxious, lawyers with a strong reputation for support will be presented first.

[0562] A prioritized list is sent to the device and presented to the user. The user reviews this list, selects a lawyer that suits their needs, and makes an appointment. Once the appointment is confirmed, the server sends a notification and a confirmation message to the user regarding the date, time, and location of the meeting.

[0563] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and simultaneously indicates a high level of stress, the server will prioritize recommending lawyers with strong support systems, especially those with expertise in child custody. In this way, the system not only selects candidates based on criteria but also considers the user's psychological state when making suggestions, thereby achieving more effective matching.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] The user launches a generation application on their device and enters the requirements for the lawyer they are looking for. These requirements include specialty, location, budget, and years of experience. As the user enters their information, an emotion engine analyzes their emotions based on their typing speed and word choice.

[0567] Step 2:

[0568] The terminal sends user input data and analysis data from the emotion engine to the server. This allows the server to receive both conditional and emotional information simultaneously.

[0569] Step 3:

[0570] Based on the conditions received by the server, keywords are extracted using natural language processing technology. Next, a database of experts is consulted to search for relevant lawyer candidates. Preparations are made to incorporate sentiment data during this process.

[0571] Step 4:

[0572] The server uses an AI model to evaluate and prioritize the list of candidates. This evaluation incorporates the results of an emotion engine analysis, and if it determines that the situation is urgent, the system adjusts to display lawyers who can respond more quickly at the top of the list.

[0573] Step 5:

[0574] A prioritized list of potential lawyers is sent from the server to the user's terminal. The user can then review this list on their terminal and select the most suitable candidate.

[0575] Step 6:

[0576] The user makes a reservation with a lawyer of their choice. The terminal sends the reservation information to the server, and the server notifies both the lawyer and the user of the confirmed reservation.

[0577] Step 7:

[0578] The server sends a final confirmation notification to the user. This clearly communicates the interview date and location to the user.

[0579] This process allows users not only to find a lawyer that meets their requirements, but also to receive suggestions that take their psychological state into account, enabling them to make better choices.

[0580] (Example 2)

[0581] Next, we will describe Example 2. 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."

[0582] Traditionally, when selecting a professional, users would only input their own criteria, and the system would select a professional based on those criteria. However, the user's emotions and psychological state were ignored, and therefore the suggested professional was not always the best fit for the user's current situation. This resulted in a problem where the efficiency and effectiveness of professional selection were not fully realized.

[0583] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0584] In this invention, the server includes means for inputting conditions through a generation program, means for analyzing emotions based on user behavior data, and means for determining the priority of expert candidates considering the emotion analysis results. This makes it possible to select experts that take into account not only the user's conditions but also their emotions and psychological state, enabling the presentation of experts that are more suitable for the user.

[0585] A "generator program" is software that allows users to input necessary criteria when searching for experts.

[0586] An "information processing device" is a device that analyzes the conditions entered by the user, extracts appropriate candidates from expert information sources, and presents them.

[0587] An "expert information source" is a database that accumulates and makes searchable information about various experts.

[0588] "Action data" refers to data such as the user's input speed, word choice, and operation history when entering information.

[0589] "Methods for analyzing emotions" refer to processes that determine the user's emotional state at a given time based on their behavioral data.

[0590] "Methods for determining priorities" refers to the process of determining the order in which to present the extracted expert candidates, based on the user's conditions and the results of sentiment analysis.

[0591] The system of this invention takes into account the user's psychological state in the process of efficiently selecting a suitable expert for themselves. The system consists of the following components:

[0592] 1. Terminal Usage: The user launches the generation program via the terminal and inputs the criteria necessary for selecting an expert. These criteria include area of ​​expertise, budget, years of experience, and location. The terminal is equipped with a function to collect the data entered by the user and the operation data during the input process.

[0593] 2. Analysis by the Information Processing Device: The terminal transmits the user's input conditions to the information processing device. This information processing device analyzes the conditions and extracts relevant experts from a database called the expert information source.

[0594] 3. Inclusion of emotion analysis function: The server uses an emotion analysis engine based on the user's behavior data to determine the user's emotions. A generative AI model is used here to help understand the user's level of stress and anxiety.

[0595] 4. Prioritization: The server determines the priority of expert candidates based on the user's conditions and the results of sentiment analysis. This makes it possible to present the expert best suited to the user's psychological state.

[0596] 5. Expert Selection and Booking: The user views a prioritized list of experts on their device and makes a selection. The server confirms the booking with the selected expert, and details such as the date, time, and location of the meeting are sent to the user.

[0597] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and indicates a high level of stress, the server will prioritize recommending lawyers who are strong in child custody issues and have a well-established support system. This allows users to be matched with the most suitable professional, taking into account not only their specific needs but also their psychological state.

[0598] An example of a prompt message would be, "If the user is anxious, provide a list of trustworthy lawyers," allowing the generative AI model to support the selection of an expert based on emotion.

[0599] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0600] Step 1:

[0601] The user launches the generation program using a terminal. The user enters information such as the lawyer's area of ​​expertise, desired budget, years of experience, and location into the on-screen input form. The entered information is saved digitally on the terminal and prepared for the next processing step.

[0602] Step 2:

[0603] The terminal sends user-inputted conditional data to the server. Simultaneously, it collects behavioral data such as the user's input speed and operation patterns. The collected behavioral data is used in subsequent processing for user sentiment analysis.

[0604] Step 3:

[0605] The server analyzes the received conditional data and generates keywords for searching expert information sources. A generative AI model is used here. Specifically, it extracts keywords related to relevant fields of expertise based on the input conditions. As output, a list of keywords necessary for the search is generated.

[0606] Step 4:

[0607] The server uses an emotion analysis engine to analyze the user's emotional state based on behavioral data received from the terminal. A generative AI model is used, and an example prompt is given: "Estimate this user's stress level." As a result, data indicating the stress level and emotional state is output.

[0608] Step 5:

[0609] The server searches for relevant lawyer candidates from expert information sources based on a keyword list. In addition, it considers data obtained from sentiment analysis to determine the priority of the lawyer candidates. Prioritization is performed by placing lawyers who provide more support higher up, for example, when the user has expressed anxiety.

[0610] Step 6:

[0611] The server sends a list of prioritized lawyers to the terminal. The terminal presents this information to the user. The user selects their preferred lawyer from the displayed list. This selection is sent to the server digitally and used for the booking process.

[0612] Step 7:

[0613] The server confirms the appointment with the lawyer selected by the user and generates detailed information about the meeting date, time, and location. The server then sends a final confirmation message to the user to notify them. This completes the booking process.

[0614] (Application Example 2)

[0615] Next, we will explain application example 2. In the following explanation, 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."

[0616] There is a need to reliably and efficiently select the right expert for the user, and to make suggestions that take the user's emotional state into consideration during the selection process. Conventional systems simply made selections based on conditions, and lacked prioritization that took the user's emotions into account, resulting in low usability.

[0617] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0618] In this invention, the server includes means for analyzing user input conditions, means for searching a relevant expert database to extract candidates, and means for analyzing the user's emotions and adjusting the priority of candidates based on the results. This enables a more appropriate and rapid selection of experts that meet the user's individual needs and emotions.

[0619] A "generation application" is software used by users to input conditions and is responsible for sending the input data to the processing unit.

[0620] A "processing device" is a device that analyzes received conditions and extracts appropriate candidates from a related database.

[0621] A "specialist database" is a database that stores information about experts in various fields, and is used by processing units when they search for and extract candidates.

[0622] An "emotion engine" is software equipped with an algorithm that analyzes a user's emotions based on their actions and language input, and determines the degree of stress and anxiety.

[0623] "Prioritizing" refers to the process of determining the order in which the extracted candidates are presented, while taking into account the analysis results from the emotion engine.

[0624] "Method of making a reservation" refers to a system in which the user selects from the presented options and then goes through a procedure to confirm their selection.

[0625] A "final notice" is a notification that presents and confirms the details of the reservation selected by the user.

[0626] "Follow-up" refers to the process of providing additional information and support to help users assess their satisfaction and take the next steps after they have made a reservation.

[0627] The system for implementing this invention mainly consists of multiple components. The user inputs specific conditions using a generative application operable on smart glasses or other devices. During this process, the user's language use, input speed, and device operation history are tracked in real time and analyzed by an emotion engine. The analyzed emotion data is used to determine the user's stress level and urgency.

[0628] The server receives conditional and sentiment data from the user and extracts keywords using natural language processing techniques. Software libraries such as NLTK and spaCy are used for this process. The server then searches an expert database, extracts relevant candidates, and sets priorities based on the sentiment engine data.

[0629] Once a prioritized list is generated, it is notified to the user's device. This allows the user to easily select and book the expert best suited to their needs and preferences. Once the booking is confirmed, the server provides a final notification to the user and offers follow-up as needed.

[0630] For example, if a user enters "I'm looking for security measures that focus on enhanced nighttime security" and the analysis reveals a high level of anxiety, the server will prioritize presenting candidates for 24-hour security systems that can respond immediately. Through this process, suggestions are made that comprehensively consider the user's psychological state and specific needs.

[0631] Example of a prompt:

[0632] I need help choosing the right security service. My purpose is home security, especially strengthening it at night. I'm very worried about the recent increase in reports of suspicious activity. Please suggest the best service that meets these conditions.

[0633] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0634] Step 1:

[0635] The user launches the generation application via smart glasses or another device and enters the required information. This information includes the type of expert they want to select, their purpose, and their urgency. This data is collected along with the user's operation history and input speed. Based on the input data, the application records an operation log, and the emotion engine begins analysis.

[0636] Step 2:

[0637] The server receives user condition data sent from the generation application. Next, it extracts important keywords from the input data using a natural language processing library (e.g., spaCy). In this step, the user conditions are analyzed and a search query for the expert database is generated. It takes condition data as input and generates a search query as output.

[0638] Step 3:

[0639] The server uses user interaction data to analyze the user's emotional state with an emotion engine. The analysis considers factors such as input speed and tone of voice, and evaluates the degree of stress and anxiety. It receives interaction data as input and outputs an emotion analysis report based on that information. This analysis is used by experts for prioritizing tasks.

[0640] Step 4:

[0641] The server uses the extracted keywords to search the expert database and generate a list of relevant candidates. This database query lists experts who meet the criteria and provides data for evaluation. It accepts a query as input and outputs a list of candidates from the database that meet the criteria.

[0642] Step 5:

[0643] The server takes the sentiment analysis results into account to determine the priority of the candidate list. For users experiencing high stress levels, specialists with high levels of support and responsiveness are placed higher in the priority list. The server uses the candidate list and sentiment report as input to output a prioritized list.

[0644] Step 6:

[0645] The server sends a prioritized list of experts to the terminal and presents it to the user. The user makes a selection from this list and confirms the reservation via the generating application. It receives a prioritized list as input and outputs the final reservation information after presenting it to the user.

[0646] Step 7:

[0647] Once a reservation is confirmed, the server sends a final notification to the user and follows up as needed. This notification provides information including reservation confirmation and additional guidance, giving the user peace of mind. It receives reservation data as input and outputs a confirmation notification and follow-up information.

[0648] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0649] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0650] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0651] [Fourth Embodiment]

[0652] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0653] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0654] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0655] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0656] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0657] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0658] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0659] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0660] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0661] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0662] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0663] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0664] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] This invention provides a system that allows users to efficiently find a suitable lawyer and easily make an appointment. The system consists of a generation application, a processing unit, and a professional database.

[0666] First, the user uses the device's generation application to input various criteria for selecting a lawyer in natural language. These criteria include desired specialty, budget, years of experience, and location. The device then transmits this information to the processing unit.

[0667] The transmitted data is received by a processing unit on the server. The server uses natural language processing (NLP) technology to analyze the input and extract the necessary data. Based on the analyzed data, the server accesses a database of experts and extracts candidate lawyers that meet the criteria. The extracted candidates are evaluated and prioritized using an AI model. This evaluation is based on past data, and the system recommends the lawyer who best matches the user's preferences.

[0668] The resulting list of candidates is presented to the user via their device. The user can select their preferred lawyer from the presented list and make a reservation directly. Once the reservation is confirmed, the server processes the reservation information and sends a confirmation notification to the user. This notification consists of detailed information, including the date, time, and location of the meeting, and can be viewed on the LINE app.

[0669] For example, if a user enters criteria such as "a lawyer in Tokyo specializing in traffic accidents, with a budget of 50,000 yen or less, and over 10 years of experience," the server searches its expert database for lawyers who meet these criteria, evaluates them, and presents them to the user. The user can then select a lawyer and make a reservation, accessing the necessary services without complicated procedures. In this way, the system provides users with a quick and convenient means of service.

[0670] The following describes the processing flow.

[0671] Step 1:

[0672] The user launches a generation application on their device and enters their desired lawyer's criteria in natural language. These criteria include specialty, budget, years of experience, and location.

[0673] Step 2:

[0674] The device converts the conditions entered by the user into structured data and sends it to the server as data. Data transmission is performed using the LINE API.

[0675] Step 3:

[0676] The server analyzes the received data and uses natural language processing techniques to extract keywords that meet the specified criteria. This structures the data and transforms it into more usable information.

[0677] Step 4:

[0678] The server compares the analysis results with a database of experts and extracts lawyer candidates that meet the criteria. The extraction process uses an algorithm that evaluates the degree of match with the characteristics of each lawyer in the database.

[0679] Step 5:

[0680] The server uses an AI model to evaluate and rank the extracted candidate lawyers. This evaluation is based on how well each lawyer is suited to the user's requirements.

[0681] Step 6:

[0682] The server generates a prioritized list of candidates and sends it to the terminal. This list is organized according to the user's criteria and priority.

[0683] Step 7:

[0684] The user reviews a list of candidates displayed on their device and selects their preferred lawyer. The user can then schedule a meeting with the selected lawyer through the application.

[0685] Step 8:

[0686] The server receives the reservation information, notifies the selected lawyer, and also sends a confirmation message to the user. The notification includes details such as the date, time, and location of the meeting.

[0687] Through the above processing steps, users can efficiently and quickly search for, select, and book an appointment with a lawyer who is suitable for them.

[0688] (Example 1)

[0689] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0690] The challenge is to provide users with a means to quickly and efficiently find a suitable expert and easily make a reservation. In particular, there is a need for technology that automatically evaluates and selects experts using conditions entered in natural language and presents the most suitable candidates to the user.

[0691] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0692] In this invention, the server includes means for the user to input conditions using natural language, means for the information processing device to analyze the conditions using natural language processing technology, and means for evaluating and prioritizing candidates using a generative artificial intelligence model. This makes it possible to quickly and accurately present experts to the user and to easily make reservations.

[0693] A "user" is someone who uses the system to find and book an expert.

[0694] "Conditions" refer to a set of information that users input in natural language based on their wishes and requirements, and include parameters necessary for selecting an expert.

[0695] An "information processing device" is a computer system that receives conditions transmitted by a user and performs analysis.

[0696] "Natural language processing technology" is a technique that analyzes natural language used by humans and converts it into a format that can be processed by computers.

[0697] A "collection of expert information" is a database containing detailed data about experts, and is a searchable information source based on various criteria.

[0698] A "generative artificial intelligence model" is an artificial intelligence program that learns from past data and has the ability to understand and evaluate human intentions.

[0699] "Evaluation" refers to the process by which a generative artificial intelligence model calculates the degree of suitability of expert candidates based on the input conditions and ranks them accordingly.

[0700] Prioritization is the process of arranging potential experts in the optimal order based on evaluation results.

[0701] "Presentation" refers to the process of displaying results in a format that is easy for users to understand, and includes providing information visually.

[0702] A "reservation" is the act of confirming the date, time, and location with a designated expert, and is performed through a system.

[0703] This invention is a system that enables users to efficiently find and easily book necessary experts using a generation application installed on their own devices. The system mainly consists of client terminals, a server, an expert database, a generation AI model, and a notification application.

[0704] The user launches a generation application on their device and enters their desired expert criteria in natural language (for example, "Expert in traffic accidents in Tokyo, budget under 50,000 yen, 10+ years of experience"). This input is converted into data format on the device and sent to the server.

[0705] The server analyzes the received data using natural language processing techniques. Specifically, it uses open-source natural language processing libraries to extract important parameters from the input conditions. Based on the conditions obtained through this analysis, the server accesses an expert database and extracts candidate experts that meet the conditions.

[0706] Furthermore, the extracted candidates are evaluated by a generative artificial intelligence model. Based on past matching history, the AI ​​model selects the most suitable expert for the user and determines their priority. This AI model is built using a machine learning framework and scores experts based on their experience and user ratings.

[0707] The resulting list of potential experts is sent to the user's device and displayed through the generated application. The user can then select the desired expert from this list and proceed with the booking process. Once the booking is complete, the server uses the LINE API to send a confirmation notification to the user. The notification includes details such as the date, time, and location of the scheduled meeting.

[0708] This system allows users to easily and quickly find the expert best suited to their needs. Furthermore, intuitive input of criteria using natural language makes it easy to operate even for users without specialized knowledge, enabling efficient expert selection. As a result, user convenience is significantly improved.

[0709] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0710] Step 1:

[0711] The user launches the generation application on their device and inputs criteria for selecting a specialist in natural language. This input includes areas of expertise, region, budget, and years of experience. Specifically, the user might input a sentence like, "A specialist in traffic accidents in Tokyo, with a budget of 50,000 yen or less and over 10 years of experience." The device parses this input, converts it into data format, and sends it to the server via the network.

[0712] Input: Natural language conditions entered by the user on the device

[0713] Output: Conditions for the data format sent to the server

[0714] Step 2:

[0715] The server analyzes the received conditional data using natural language processing techniques. This involves using open-source natural language processing libraries to extract keywords and important information from the conditions. Specifically, the data processing involves tokenizing the conditional statements and interpreting their meaning.

[0716] Input: Conditions for the data format received by the server

[0717] Output: Analyzed keywords and conditional information

[0718] Step 3:

[0719] The server accesses the expert database based on the analysis results and searches for candidate experts that match the criteria. It then executes a database query and lists the expert information that matches the criteria.

[0720] Input: Analyzed keywords and conditional information

[0721] Output: List of expert candidates that meet the criteria

[0722] Step 4:

[0723] The server uses a generative artificial intelligence model to evaluate and prioritize a list of expert candidates. Based on past matching data, the AI ​​model calculates a score to identify the candidate best suited to the user's criteria. This evaluation determines the candidate's priority.

[0724] Input: List of expert candidates

[0725] Output: List of evaluated and prioritized expert candidates

[0726] Step 5:

[0727] The server sends a list of evaluated expert candidates to the user's terminal. The terminal receives this list and presents it visually to the user on the generating application.

[0728] Input: List of evaluated and prioritized expert candidates

[0729] Output: A list of expert candidates presented to the user.

[0730] Step 6:

[0731] The user selects their preferred expert from the presented list and makes a reservation. The selected candidates are sent to the server via the generation application.

[0732] Input: User-selected expert candidates

[0733] Output: Reservation Information

[0734] Step 7:

[0735] The server processes the reservation information sent by the user and generates a confirmation notification. This notification includes details such as the date, time, and location, and is sent to the user using the LINE API. The user can then check this notification in the LINE app and confirm their reservation.

[0736] Input: Reservation Information

[0737] Output: Confirmation notification sent to the user

[0738] (Application Example 1)

[0739] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0740] Traditional expert booking systems presented a problem: finding a suitable expert was time-consuming and cumbersome for users. Furthermore, quick searches and bookings while on the go or away from the office were difficult, limiting user convenience. Additionally, a lack of effective visual information made it difficult for users to make quick decisions on the spot.

[0741] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0742] In this invention, the server includes means for the user to input conditions through a generation application, means for transmitting the conditions to a processing unit, means for extracting candidates from a relevant expert database, means for the user to receive expert information via augmented reality display through a mobile device while on the move, and means for making a reservation using voice input. As a result, the user can visually and in real time obtain information on the most suitable expert even while on the move, and quickly confirm the reservation on the spot using voice.

[0743] A "generation application" is software that allows a user to input conditions and send them to a processing unit.

[0744] A "processing device" is a computer device that analyzes input conditions and extracts candidate experts from a database of relevant experts.

[0745] A "specialist database" is a collection of data that manages information on various types of experts and provides appropriate candidates based on specific criteria.

[0746] Augmented reality is a technology that overlays visual information onto the real world, providing users with an intuitive way to convey expert information.

[0747] "Voice input" is an interface that allows users to input instructions into a system using their voice.

[0748] A "portable device" is a terminal that a user can carry with them, and includes smart glasses and smartphones.

[0749] To implement this invention, it is necessary to install a generation application on the user's mobile device. This application provides an interface that allows the user to input expert search criteria in natural language. Mobile devices such as smart glasses and smartphones are primarily used.

[0750] When a user enters conditions, those conditions are sent from the terminal to the server's processing unit. The server first uses natural language processing (NLP) techniques to analyze the conditions and extract the necessary data. This analysis utilizes specific NLP libraries and machine learning models.

[0751] Based on the analyzed data, the server accesses a database of experts and extracts candidate experts that meet the criteria. These candidates are then evaluated and prioritized using a generative AI model. This evaluation process utilizes historical data to prioritize experts who best match the user's preferences.

[0752] The evaluation results are presented to the user using augmented reality (AR) display on their mobile device. AR software and the device's built-in camera are used to intuitively visualize expert information within the real world. Users can make reservations on the spot using voice input. This feature is supported by the mobile device's voice recognition hardware and software.

[0753] For example, if a user enters the criteria "I'm looking for a lawyer specializing in traffic accidents in Tokyo," the server searches its database based on this information, prioritizes available lawyers, and presents them to the user using augmented reality. An example of a prompt might be, "I'm looking for a lawyer specializing in traffic accidents in Tokyo. I'd prefer someone with over 10 years of experience and a fee of under 50,000 yen." In this way, users can efficiently find the most suitable professional and easily complete a booking.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] The user uses a generation application on their mobile device to enter search criteria for experts in natural language. These criteria may include specific details, such as "lawyers in Tokyo specializing in traffic accidents." The entered information is then transmitted from the terminal to the server's processing unit.

[0757] Step 2:

[0758] The server's processing unit performs natural language processing (NLP) on the received conditions. It applies NLP techniques to the received text data to extract important keywords and requirements. This analysis outputs necessary conditions such as "Tokyo," "traffic accident," and "lawyer."

[0759] Step 3:

[0760] The server uses the analyzed keywords to search the expert database. It extracts candidates that match the criteria from the lawyer information stored in the database. In this step, a database query is executed to retrieve entries that match the criteria as output.

[0761] Step 4:

[0762] The extracted candidates are evaluated using a generative AI model. To prioritize candidates based on past success stories and evaluation data, the AI ​​model receives candidate profiles as input, evaluates how well they match the user's preferences, and generates a prioritized list.

[0763] Step 5:

[0764] The server sends the evaluation results to the mobile device, where it displays them in augmented reality. Using AR software, expert information is overlaid onto the user's field of view. For example, the name and details of the most suitable lawyer might be displayed.

[0765] Step 6:

[0766] The user uses voice input to select their preferred lawyer from the presented options and make a reservation. The voice recognition function of the mobile device analyzes the user's instructions and sends them to the server. The server processes the received instructions and confirms the reservation.

[0767] Step 7:

[0768] Based on the reservation confirmation information, the server sends a final notification to the user's mobile device. This notification includes details such as the reserved time and location, and is available for the user to review.

[0769] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0770] This invention provides a system that allows users to efficiently find a lawyer suitable for them, and furthermore, takes the user's emotions into consideration during the selection process. This system consists of a combination of a generation application, a processing unit, a professional database, and an emotion engine.

[0771] The user launches a generation application using their device and enters requirements for a lawyer. These requirements include areas of expertise, budget, years of experience, and location, and the device sends this information to a server-side processing unit. Simultaneously, an emotion engine analyzes the user's emotions based on their word choice, input speed, and device operation history. This emotion analysis is used to determine the user's level of stress and anxiety.

[0772] The server, after analyzing the received conditions and sentiment data, uses natural language processing technology to extract relevant keywords and searches a database of experts. The extracted list of candidates is then prioritized, taking into account the results of the sentiment engine's analysis. For example, if the user is feeling anxious, lawyers with a strong reputation for support will be presented first.

[0773] A prioritized list is sent to the device and presented to the user. The user reviews this list, selects a lawyer that suits their needs, and makes an appointment. Once the appointment is confirmed, the server sends a notification and a confirmation message to the user regarding the date, time, and location of the meeting.

[0774] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and simultaneously indicates a high level of stress, the server will prioritize recommending lawyers with strong support systems, especially those with expertise in child custody. In this way, the system not only selects candidates based on criteria but also considers the user's psychological state when making suggestions, thereby achieving more effective matching.

[0775] The following describes the processing flow.

[0776] Step 1:

[0777] The user launches a generation application on their device and enters the requirements for the lawyer they are looking for. These requirements include specialty, location, budget, and years of experience. As the user enters their information, an emotion engine analyzes their emotions based on their typing speed and word choice.

[0778] Step 2:

[0779] The terminal sends user input data and analysis data from the emotion engine to the server. This allows the server to receive both conditional and emotional information simultaneously.

[0780] Step 3:

[0781] Based on the conditions received by the server, keywords are extracted using natural language processing technology. Next, a database of experts is consulted to search for relevant lawyer candidates. Preparations are made to incorporate sentiment data during this process.

[0782] Step 4:

[0783] The server uses an AI model to evaluate and prioritize the list of candidates. This evaluation incorporates the results of an emotion engine analysis, and if it determines that the situation is urgent, the system adjusts to display lawyers who can respond more quickly at the top of the list.

[0784] Step 5:

[0785] A prioritized list of potential lawyers is sent from the server to the user's terminal. The user can then review this list on their terminal and select the most suitable candidate.

[0786] Step 6:

[0787] The user makes a reservation with a lawyer of their choice. The terminal sends the reservation information to the server, and the server notifies both the lawyer and the user of the confirmed reservation.

[0788] Step 7:

[0789] The server sends a final confirmation notification to the user. This clearly communicates the interview date and location to the user.

[0790] This process allows users not only to find a lawyer that meets their requirements, but also to receive suggestions that take their psychological state into account, enabling them to make better choices.

[0791] (Example 2)

[0792] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0793] Traditionally, when selecting a professional, users would only input their own criteria, and the system would select a professional based on those criteria. However, the user's emotions and psychological state were ignored, and therefore the suggested professional was not always the best fit for the user's current situation. This resulted in a problem where the efficiency and effectiveness of professional selection were not fully realized.

[0794] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0795] In this invention, the server includes means for inputting conditions through a generation program, means for analyzing emotions based on user behavior data, and means for determining the priority of expert candidates considering the emotion analysis results. This makes it possible to select experts that take into account not only the user's conditions but also their emotions and psychological state, enabling the presentation of experts that are more suitable for the user.

[0796] A "generator program" is software that allows users to input necessary criteria when searching for experts.

[0797] An "information processing device" is a device that analyzes the conditions entered by the user, extracts appropriate candidates from expert information sources, and presents them.

[0798] An "expert information source" is a database that accumulates and makes searchable information about various experts.

[0799] "Action data" refers to data such as the user's input speed, word choice, and operation history when entering information.

[0800] "Methods for analyzing emotions" refer to processes that determine the user's emotional state at a given time based on their behavioral data.

[0801] "Methods for determining priorities" refers to the process of determining the order in which to present the extracted expert candidates, based on the user's conditions and the results of sentiment analysis.

[0802] The system of this invention takes into account the user's psychological state in the process of efficiently selecting a suitable expert for themselves. The system consists of the following components:

[0803] 1. Terminal Usage: The user launches the generation program via the terminal and inputs the criteria necessary for selecting an expert. These criteria include area of ​​expertise, budget, years of experience, and location. The terminal is equipped with a function to collect the data entered by the user and the operation data during the input process.

[0804] 2. Analysis by the Information Processing Device: The terminal transmits the user's input conditions to the information processing device. This information processing device analyzes the conditions and extracts relevant experts from a database called the expert information source.

[0805] 3. Inclusion of emotion analysis function: The server uses an emotion analysis engine based on the user's behavior data to determine the user's emotions. A generative AI model is used here to help understand the user's level of stress and anxiety.

[0806] 4. Prioritization: The server determines the priority of expert candidates based on the user's conditions and the results of sentiment analysis. This makes it possible to present the expert best suited to the user's psychological state.

[0807] 5. Expert Selection and Booking: The user views a prioritized list of experts on their device and makes a selection. The server confirms the booking with the selected expert, and details such as the date, time, and location of the meeting are sent to the user.

[0808] For example, if a user enters "I'm looking for a lawyer specializing in child custody in a divorce case" and indicates a high level of stress, the server will prioritize recommending lawyers who are strong in child custody issues and have a well-established support system. This allows users to be matched with the most suitable professional, taking into account not only their specific needs but also their psychological state.

[0809] An example of a prompt message would be, "If the user is anxious, provide a list of trustworthy lawyers," allowing the generative AI model to support the selection of an expert based on emotion.

[0810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0811] Step 1:

[0812] The user launches the generation program using a terminal. The user enters information such as the lawyer's area of ​​expertise, desired budget, years of experience, and location into the on-screen input form. The entered information is saved digitally on the terminal and prepared for the next processing step.

[0813] Step 2:

[0814] The terminal sends user-inputted conditional data to the server. Simultaneously, it collects behavioral data such as the user's input speed and operation patterns. The collected behavioral data is used in subsequent processing for user sentiment analysis.

[0815] Step 3:

[0816] The server analyzes the received conditional data and generates keywords for searching expert information sources. A generative AI model is used here. Specifically, it extracts keywords related to relevant fields of expertise based on the input conditions. As output, a list of keywords necessary for the search is generated.

[0817] Step 4:

[0818] The server uses an emotion analysis engine to analyze the user's emotional state based on behavioral data received from the terminal. A generative AI model is used, and an example prompt is given: "Estimate this user's stress level." As a result, data indicating the stress level and emotional state is output.

[0819] Step 5:

[0820] The server searches for relevant lawyer candidates from expert information sources based on a keyword list. In addition, it considers data obtained from sentiment analysis to determine the priority of the lawyer candidates. Prioritization is performed by placing lawyers who provide more support higher up, for example, when the user has expressed anxiety.

[0821] Step 6:

[0822] The server sends a list of prioritized lawyers to the terminal. The terminal presents this information to the user. The user selects their preferred lawyer from the displayed list. This selection is sent to the server digitally and used for the booking process.

[0823] Step 7:

[0824] The server confirms the appointment with the lawyer selected by the user and generates detailed information about the meeting date, time, and location. The server then sends a final confirmation message to the user to notify them. This completes the booking process.

[0825] (Application Example 2)

[0826] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0827] There is a need to reliably and efficiently select the right expert for the user, and to make suggestions that take the user's emotional state into consideration during the selection process. Conventional systems simply made selections based on conditions, and lacked prioritization that took the user's emotions into account, resulting in low usability.

[0828] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0829] In this invention, the server includes means for analyzing user input conditions, means for searching a relevant expert database to extract candidates, and means for analyzing the user's emotions and adjusting the priority of candidates based on the results. This enables a more appropriate and rapid selection of experts that meet the user's individual needs and emotions.

[0830] A "generation application" is software used by users to input conditions and is responsible for sending the input data to the processing unit.

[0831] A "processing device" is a device that analyzes received conditions and extracts appropriate candidates from a related database.

[0832] A "specialist database" is a database that stores information about experts in various fields, and is used by processing units when they search for and extract candidates.

[0833] An "emotion engine" is software equipped with an algorithm that analyzes a user's emotions based on their actions and language input, and determines the degree of stress and anxiety.

[0834] "Prioritizing" refers to the process of determining the order in which the extracted candidates are presented, while taking into account the analysis results from the emotion engine.

[0835] "Method of making a reservation" refers to a system in which the user selects from the presented options and then goes through a procedure to confirm their selection.

[0836] A "final notice" is a notification that presents and confirms the details of the reservation selected by the user.

[0837] "Follow-up" refers to the process of providing additional information and support to help users assess their satisfaction and take the next steps after they have made a reservation.

[0838] The system for implementing this invention mainly consists of multiple components. The user inputs specific conditions using a generative application operable on smart glasses or other devices. During this process, the user's language use, input speed, and device operation history are tracked in real time and analyzed by an emotion engine. The analyzed emotion data is used to determine the user's stress level and urgency.

[0839] The server receives conditional and sentiment data from the user and extracts keywords using natural language processing techniques. Software libraries such as NLTK and spaCy are used for this process. The server then searches an expert database, extracts relevant candidates, and sets priorities based on the sentiment engine data.

[0840] Once a prioritized list is generated, it is notified to the user's device. This allows the user to easily select and book the expert best suited to their needs and preferences. Once the booking is confirmed, the server provides a final notification to the user and offers follow-up as needed.

[0841] For example, if a user enters "I'm looking for security measures that focus on enhanced nighttime security" and the analysis reveals a high level of anxiety, the server will prioritize presenting candidates for 24-hour security systems that can respond immediately. Through this process, suggestions are made that comprehensively consider the user's psychological state and specific needs.

[0842] Example of a prompt:

[0843] I need help choosing the right security service. My purpose is home security, especially strengthening it at night. I'm very worried about the recent increase in reports of suspicious activity. Please suggest the best service that meets these conditions.

[0844] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0845] Step 1:

[0846] The user launches the generation application via smart glasses or another device and enters the required information. This information includes the type of expert they want to select, their purpose, and their urgency. This data is collected along with the user's operation history and input speed. Based on the input data, the application records an operation log, and the emotion engine begins analysis.

[0847] Step 2:

[0848] The server receives user condition data sent from the generation application. Next, it extracts important keywords from the input data using a natural language processing library (e.g., spaCy). In this step, the user conditions are analyzed and a search query for the expert database is generated. It takes condition data as input and generates a search query as output.

[0849] Step 3:

[0850] The server uses user interaction data to analyze the user's emotional state with an emotion engine. The analysis considers factors such as input speed and tone of voice, and evaluates the degree of stress and anxiety. It receives interaction data as input and outputs an emotion analysis report based on that information. This analysis is used by experts for prioritizing tasks.

[0851] Step 4:

[0852] The server uses the extracted keywords to search the expert database and generate a list of relevant candidates. This database query lists experts who meet the criteria and provides data for evaluation. It accepts a query as input and outputs a list of candidates from the database that meet the criteria.

[0853] Step 5:

[0854] The server takes the sentiment analysis results into account to determine the priority of the candidate list. For users experiencing high stress levels, specialists with high levels of support and responsiveness are placed higher in the priority list. The server uses the candidate list and sentiment report as input to output a prioritized list.

[0855] Step 6:

[0856] The server sends a prioritized list of experts to the terminal and presents it to the user. The user makes a selection from this list and confirms the reservation via the generating application. It receives a prioritized list as input and outputs the final reservation information after presenting it to the user.

[0857] Step 7:

[0858] Once a reservation is confirmed, the server sends a final notification to the user and follows up as needed. This notification provides information including reservation confirmation and additional guidance, giving the user peace of mind. It receives reservation data as input and outputs a confirmation notification and follow-up information.

[0859] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0860] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0861] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0862] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0863] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0864] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0865] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0866] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0867] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0868] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0869] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0870] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0871] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0872] 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.

[0873] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0874] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0875] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0876] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0877] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0878] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0879] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0880] The following is further disclosed regarding the embodiments described above.

[0881] (Claim 1)

[0882] A means by which the user inputs conditions through a generation application,

[0883] Means for transmitting the above conditions to the processing unit,

[0884] The processing device includes means for analyzing the conditions and extracting candidates from a relevant expert database,

[0885] The means of presenting the aforementioned expert candidates,

[0886] A means by which the user selects from the aforementioned candidates and makes a reservation.

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, characterized in that it includes means for prioritizing based on the aforementioned expert database using past data.

[0890] (Claim 3)

[0891] The system according to claim 1, characterized by comprising means for providing a final notification to the user.

[0892] "Example 1"

[0893] (Claim 1)

[0894] A means for users to input conditions using natural language,

[0895] Means for transmitting the above conditions to an information processing device,

[0896] The aforementioned information processing device includes means for analyzing the conditions using natural language processing technology and extracting candidates from a set of information on relevant experts,

[0897] A means for evaluating and prioritizing the candidates using a generative artificial intelligence model,

[0898] A means of presenting evaluated expert candidates to users,

[0899] A means by which the user selects from the aforementioned candidates and makes a reservation,

[0900] A means of notifying the user's device of the reservation details,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, characterized in that it includes means for prioritizing based on the aforementioned expert information set and using past information.

[0904] (Claim 3)

[0905] The system according to claim 1, characterized by comprising means for evaluating candidates using a generative artificial intelligence model and recommending the most suitable expert to the user.

[0906] "Application Example 1"

[0907] (Claim 1)

[0908] A means by which the user inputs conditions through a generation application,

[0909] Means for transmitting the above conditions to the processing unit,

[0910] The processing device includes means for analyzing the conditions and extracting candidates from a relevant expert database,

[0911] The means of presenting the aforementioned expert candidates,

[0912] A means by which the user selects from the aforementioned candidates and makes a reservation,

[0913] A means for users on the go to receive expert information through augmented reality displays via their mobile devices,

[0914] A method of making a reservation using voice input,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, characterized in that it includes means for prioritizing based on the aforementioned expert database using past data, and visually presents the experts.

[0918] (Claim 3)

[0919] The system according to claim 1, characterized in that it provides a means for giving a final notification to the user and notifying them of the reservation details via a mobile messaging app.

[0920] "Example 2 of combining an emotion engine"

[0921] (Claim 1)

[0922] A means by which the user inputs conditions through a generation program,

[0923] Means for transmitting the above conditions to an information processing device,

[0924] The information processing device includes means for analyzing the conditions and extracting candidates from relevant expert information sources,

[0925] A means of analyzing emotions based on behavioral data collected when the user inputs,

[0926] A means for determining the priority of the candidates in consideration of the emotion analysis results,

[0927] A means for presenting the aforementioned prioritized expert candidates,

[0928] A means by which the user selects from the aforementioned candidates and makes a reservation,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, characterized in that it comprises means for prioritizing based on the aforementioned expert information sources, using past data and sentiment analysis results.

[0932] (Claim 3)

[0933] The system according to claim 1, characterized by comprising means for providing a final notification to the user.

[0934] "Application example 2 when combining with an emotional engine"

[0935] (Claim 1)

[0936] A means by which the user inputs conditions through a generation application,

[0937] Means for transmitting the above conditions to the processing unit,

[0938] The processing device includes means for analyzing the conditions and extracting candidates from a relevant expert database,

[0939] The system includes an emotion engine for analyzing the user's emotions, and means for prioritizing candidates based on the analysis results of the emotion engine.

[0940] The means of presenting the aforementioned expert candidates,

[0941] A means by which the user selects from the aforementioned candidates and makes a reservation.

[0942] A system that includes this.

[0943] (Claim 2)

[0944] The system according to claim 1, characterized in that it includes means for prioritizing based on the aforementioned expert database using past data and further adjusting the prioritization based on user sentiment data.

[0945] (Claim 3)

[0946] The system according to claim 1, characterized in that it provides a means for giving final notice to the user and for providing follow-up as needed for an interview. [Explanation of Symbols]

[0947] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means by which the user inputs conditions through a generation application, Means for transmitting the above conditions to the processing unit, The processing device includes means for analyzing the conditions and extracting candidates from a relevant expert database, The means of presenting the aforementioned expert candidates, A means by which the user selects from the aforementioned candidates and makes a reservation. A system that includes this.

2. The system according to claim 1, characterized in that it includes means for prioritizing based on the aforementioned expert database using past data.

3. The system according to claim 1, characterized by comprising means for providing a final notification to the user.

Images