system

Abstract

We provide the system. [Solution] A data collection means for receiving video and audio information of participants, A facial expression analysis means analyzes the facial expressions of participants based on the video information acquired by the aforementioned data collection means, Based on the audio information acquired by the aforementioned data collection means, an audio analysis means analyzes the tone of the participant's voice, Based on the analysis results of the facial expression analysis means and the voice analysis means, an evaluation means is provided to evaluate the progress of the meeting and the level of concentration of the participants. A proposal generation means that generates proposals regarding the progress of the meeting based on the evaluation results of the aforementioned evaluation means, A notification means for notifying participants of the proposals generated by the proposal generation means, 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, which is performed by at least one processor, and includes 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 a modern office environment, due to the shortage of physical meeting rooms, there is a problem that it is difficult to provide an effective communication place. Also, with the increase in online meetings, participants tend to lack concentration due to long meetings, and the productivity of meetings has decreased. Under such circumstances, a system that improves the efficiency of meetings and the concentration of participants is required.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that collects video and audio information from participants in real time and analyzes their facial expressions and voice tone based on that data. This allows the system to automatically evaluate the progress of the meeting and the level of participant engagement, and to propose breakout sessions or organize the agenda as needed. The system notifies participants of the suggestions based on the analysis results, thereby improving the efficiency of the meeting.

[0006] "Data collection means" refers to a part of a system that has the function of receiving video and audio information of participants.

[0007] "Facial expression analysis means" refers to a part of a system that has the function of analyzing the facial expressions of participants based on video information acquired by data collection means.

[0008] "Voice analysis means" refers to a part of a system that has the function of analyzing the tone of a participant's voice based on voice information acquired by data collection means.

[0009] "Evaluation means" refers to a part of a system that has the function of determining the progress of a meeting and the level of concentration of participants based on the analysis results of facial expression analysis means and voice analysis means.

[0010] The "proposal generation means" is a part of a system that has the function of creating specific proposals regarding the progress of a meeting based on the judgment results of the evaluation means.

[0011] A "notification mechanism" is a part of a system that has a function to inform participants of proposals created by the proposal generation mechanism. [Brief explanation of the drawing]

[0012] [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] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which 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 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] [[ID=四十]] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention provides a virtual meeting room that acquires video and audio information from participants and improves the efficiency of meetings based on this information. This system includes the following main functions:

[0034] First, the server collects video and audio data streams from the users (devices) participating in the meeting via their cameras and microphones. This data is processed in the cloud. The collected video information is then analyzed using facial expression analysis tools to identify the facial features of the participants. For example, it identifies whether a user is smiling or has a serious expression.

[0035] Similarly, the server analyzes the acquired audio information using voice analysis tools. Specifically, it monitors the user's voice tone, changes in voice quality, and volume to estimate their emotions and level of concentration. For example, it can determine whether the user is speaking in an energetic or tired voice.

[0036] These analysis results are aggregated by the server to evaluate the overall progress of the meeting and the level of participant engagement. Based on this evaluation, suggestions for optimizing the meeting are generated. For example, if participant engagement is low, it may suggest breakout sessions or revisit key agenda items.

[0037] Finally, the server notifies each user (device) of the generated proposals. The notified users can then take action based on those proposals. This makes it easier for participants to take necessary actions during the meeting, improving overall meeting efficiency.

[0038] For example, if it is estimated that many participants are not concentrating during a meeting, the server suggests starting breakout sessions and notifies the users. If the participants accept the suggestion, the server automatically divides them into smaller groups and sets up breakout session rooms. In this form, the present invention can promote efficient communication and improve the productivity of meetings.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user (device) joins the virtual meeting and enables their camera and microphone. This initiates the collection of video and audio data.

[0042] Step 2:

[0043] The server receives video and audio data from each user in real time. The received data is converted into a format suitable for analysis.

[0044] Step 3:

[0045] The server inputs video data into a facial expression analysis tool to detect feature points on the participants' faces. This analysis identifies changes in facial expressions, such as smiles and eyebrow movements.

[0046] Step 4:

[0047] The server inputs the audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice to estimate emotions and level of concentration.

[0048] Step 5:

[0049] The server aggregates the analyzed facial and voice data and evaluates the overall level of concentration among participants. If the level of concentration drops below a certain threshold, the process moves to the next step.

[0050] Step 6:

[0051] Based on the evaluation results, the server generates suggestions to improve meeting efficiency. For example, it might suggest breakout sessions or encourage participants to organize the agenda.

[0052] Step 7:

[0053] The server notifies each user's terminal of the generated suggestions. The notification includes instructions for specific actions.

[0054] Step 8:

[0055] The user reviews the notification from the server and chooses whether to perform the suggested action. If the user accepts the suggestion, the server performs the action based on the suggestion.

[0056] (Example 1)

[0057] 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."

[0058] In modern meetings, where many participants are increasingly joining remotely, ensuring efficient communication has become a challenging task. In particular, it's difficult to gauge participants' level of focus and emotional state in real time, which can lack the basis for optimizing meeting progress. Therefore, there is a need for new technologies that enable effective meeting management and improve participant engagement.

[0059] 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.

[0060] In this invention, the server includes information gathering means for receiving video and audio information of participants, analysis means for analyzing the facial features of participants, and analysis means for analyzing changes in participants' voices. This makes it possible to evaluate the progress of the meeting and the level of concentration of participants in real time and generate appropriate suggestions.

[0061] "Information gathering means" refers to devices or software used to acquire video and audio information of participants.

[0062] "Analysis means" refers to a device or software that has the function of analyzing the facial features and voice changes of participants based on the collected video and audio information.

[0063] "Generation means" refers to a device or software for generating suggestions to optimize the progress of a meeting based on the results obtained by the analysis means.

[0064] "Notification means" refers to a device or function for communicating the generated proposal to participants.

[0065] "Small group division" refers to a method or technique for conducting a meeting by dividing the participants into small groups.

[0066] A "proposal to re-evaluate agenda items" is a suggestion to reconfirm the agenda items during a meeting and reassess their importance.

[0067] One embodiment of this invention is a system for improving the efficiency of meetings. This system consists of a server, terminals, and users involved with them.

[0068] The server is assumed to be a group of computers operating in a cloud environment. First, the terminal acquires video and audio information from participants. Video information is captured by the camera, and audio information is captured by the microphone. The acquired raw data is sent from the terminal to the server.

[0069] The server uses several analysis tools to process the received data. For video data, a facial recognition API is used to analyze the facial features of participants. This analysis is performed to determine whether the user is smiling, surprised, or expressing other emotions. For audio data, an audio analysis tool is used to observe changes in tone, volume, and speed of the voice. Specifically, the characteristics of the audio waveform are captured to estimate whether the participant is speaking energetically or exhausted.

[0070] The analysis results are aggregated on the server and used to evaluate participants' real-time emotional states and levels of engagement. Based on the evaluation, the server generates suggestions to optimize the meeting. These suggestions may include starting breakout sessions or re-evaluating the agenda. The suggestions are notified to each user via their terminal, and users can take appropriate action based on the suggestions.

[0071] For example, if analysis reveals a decline in participant engagement during a meeting, the server proposes splitting into smaller groups and notifies the user. If the user accepts the proposal, the server automatically assigns participants to smaller groups and sets up appropriate virtual spaces.

[0072] The use of generative AI models is also being considered, and an example of a prompt message could be, "Please tell me how to measure the level of concentration from participants' facial expressions and voice, and create and notify me of suggestions to improve meeting efficiency." In this way, the system would support effective meeting management.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The terminal acquires video data from users participating in the meeting via its camera and audio data via its microphone. The video is captured as an image stream, and the audio is captured as an audio waveform. This acquired data becomes the input. The terminal processes this input data in real time and sends it directly to the server.

[0076] Step 2:

[0077] The server inputs the video data received from the terminal into a video analysis tool. Specifically, it uses a face detection algorithm to identify facial regions from the video data and performs emotion analysis. For example, it identifies smiles, serious expressions, surprise, etc., and outputs an emotion score for each expression.

[0078] Step 3:

[0079] The server inputs the audio data received from the terminal into an audio analysis tool. The audio data is processed by an audio segmentation algorithm, which analyzes the tone, volume, and pitch of the voice. This outputs the audio characteristics necessary for estimating the user's emotional state and level of concentration.

[0080] Step 4:

[0081] The server aggregates the analysis results obtained in steps 2 and 3 and inputs them into the evaluation model. This model combines facial expression scores and voice characteristics to calculate an attention index for each participant. As a result, it outputs an evaluation of the overall progress of the meeting and emotional indicators of the participants.

[0082] Step 5:

[0083] The server generates suggestions to optimize the meeting based on the evaluation results. Using a generative model, it suggests breakout sessions if the level of engagement is low. It outputs the generated suggestions and generates corresponding recommendations.

[0084] Step 6:

[0085] The server distributes the generated proposals to each terminal using a notification system. Specifically, it creates a notification message containing the proposal content and implementation steps, and sends it to the user's terminal. This notification serves as the output, prompting the user to take action.

[0086] Step 7:

[0087] The user checks the notification received on their device and selects an action based on the suggestion. Once the user approves the suggestion, the device sends a notification to the server, which may automatically adjust the meeting settings. This feedback is treated as input and used for re-evaluation to optimize the overall meeting progress.

[0088] (Application Example 1)

[0089] 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."

[0090] To provide effective customer service in physical stores, it is essential to accurately understand the customer's situation and interests and to respond immediately to the most appropriate needs. However, conventional methods often make it difficult to grasp customer emotions and interests, resulting in uniform responses. This invention aims to solve these problems and improve customer satisfaction.

[0091] 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.

[0092] In this invention, the server includes an information gathering means for receiving participant information, an analysis means for analyzing the participant's facial expressions based on the video information acquired by the information gathering means, and an analysis means for analyzing the participant's voice tone based on the audio information acquired by the information gathering means. This makes it possible to grasp customer interests in real time within the store and make optimal customer service suggestions.

[0093] "Information gathering means" refers to technical devices used to acquire video and audio information of customers.

[0094] The "analysis means" is a processing device for analyzing the customer's facial expressions and voice tone based on acquired video and audio information.

[0095] An "evaluation tool" is a system for evaluating the progress within a store and the level of customer interest based on the results of analysis performed by an analysis tool.

[0096] A "proposal generation method" is a process for generating customer response measures based on the evaluation results of the evaluation method.

[0097] "Notification means" refers to the means of reliably communicating proposals generated by the proposal generation means to the staff.

[0098] "Customer service support tools" are devices and systems that assist customer service activities by suggesting optimal actions tailored to the customer's interests and circumstances.

[0099] The system realizing this invention provides means for collecting and analyzing customer video and audio information to optimize customer service. A server collects customer information in real time within the store using devices such as smart glasses or robots. This information is processed using a cloud computing platform.

[0100] Smart glasses and robots are equipped with high-resolution cameras and high-sensitivity microphones. This allows for detailed collection of customer facial expressions and voice tones. The server processes this data using video analysis tools such as OpenCV to analyze the customer's facial expressions. Simultaneously, the audio data is converted to text using the Google Cloud Speech-to-Text API, and its tone and content are analyzed.

[0101] The analysis results are used by an evaluation algorithm powered by Google Cloud AI to estimate the customer's interests and psychological state. Based on this evaluation, the server proposes the optimal customer response. The proposed response is notified to staff via smart glasses, or a robot directly approaches the customer.

[0102] As a concrete example, if a customer in a clothing store is having trouble choosing an item and their expression is uncertain, the system can directly ask the customer, "Do you need any assistance?" via a robot. Staff members receive a suggestion notification on their smart glasses and can provide support quickly. This allows customers to have a more personalized experience and improves the store's responsiveness.

[0103] An example of a prompt message is: "Please tell me about a system that analyzes customer facial expressions and voices to recognize customer emotions in real time and suggest the most appropriate customer service approach. In particular, please provide specific examples of customer service support utilizing real-time notifications via smart glasses."

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server acquires customer video and audio data in real time from smart glasses and robots. Input comes from high-resolution cameras and high-sensitivity microphones, which the server receives as a data stream. Output is digitized video and audio data. This information is stored in a cloud-based database.

[0107] Step 2:

[0108] The server processes the collected video data using OpenCV to analyze the customer's facial expressions. The input is the video data obtained in step 1, and the server performs face recognition and expression analysis on it. The output is the analysis result, for example, whether the customer is smiling or looking troubled. This analysis result serves as an indicator of the customer's emotional state.

[0109] Step 3:

[0110] The server converts the audio data into text using the Google Cloud Speech-to-Text API and analyzes the tone and content of the speech. The input is the audio data obtained in step 1, and the output is the transcribed speech content and its tone information. Based on this, the server determines whether the customer is excited or relaxed. This information is an important factor in estimating the customer's psychological state.

[0111] Step 4:

[0112] The server analyzes the results obtained in steps 2 and 3 using an evaluation algorithm to estimate the customer's interests and psychological state. The inputs are the facial expression analysis results and the voice analysis results, and the output is an evaluation of the customer's level of interest and psychological state. The server then identifies the customer's potential needs.

[0113] Step 5:

[0114] The server uses a generative AI model to suggest the optimal customer response based on the estimated customer state. The input is the evaluation result from step 4, and the output is a specific action suggestion. For example, if the customer is in trouble, a suggestion such as "Can I help you?" will be generated.

[0115] Step 6:

[0116] The server notifies staff wearing smart glasses or robots interacting with customers of the suggested actions. The input is the suggestion generated in step 5, and the output is the notified action suggestion. This allows store staff or robots to immediately take action and provide appropriate service to customers.

[0117] 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.

[0118] The present invention provides a virtual meeting room that incorporates an emotion engine to acquire video and audio information from participants and improve the efficiency of meetings. This system includes the following main functions:

[0119] First, the user (device) provides video and audio data by enabling the camera and microphone when joining a virtual meeting. This data is sent to the server in real time.

[0120] The server inputs the collected data into facial expression analysis tools and voice analysis tools to analyze the participants' facial features and voice tone. This allows the server to estimate the participants' instantaneous emotional state and level of concentration.

[0121] Furthermore, this system integrates an emotion engine that combines analyzed facial expression data and voice data to recognize participants' emotions with high accuracy. The emotion engine determines, for example, whether a participant is feeling happy or stressed.

[0122] These analysis results are aggregated by a server to evaluate the overall progress of the meeting and the level of participant engagement. Based on these results, suggestions for improving meeting efficiency are generated. The suggestion generation system can provide customized suggestions for each participant. For example, it can offer suggestions to help a nervous participant relax.

[0123] Finally, the server notifies each user (device) of the generated suggestions. The notification includes specific actions tailored to the participant's emotional state, enabling more effective engagement.

[0124] As a concrete example, if the server detects that a participant is stressed based on their facial expressions during a meeting, it will suggest a short break for relaxation and notify the user. If the user accepts the suggestion, the server will temporarily suspend the meeting and set a break period. This approach can improve the productivity of meetings.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The user (device) joins the virtual meeting and activates their camera and microphone. This allows video and audio data of the meeting participants to be captured.

[0128] Step 2:

[0129] The server receives video and audio data from each user in real time and converts it to the appropriate format. This data is then processed into the format necessary for analysis.

[0130] Step 3:

[0131] The server inputs video data into a facial expression analysis tool to analyze the facial features of the participants. This analysis captures subtle changes in facial expressions and identifies the emotional state of those expressions.

[0132] Step 4:

[0133] The server inputs audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice. This allows it to extract emotional indicators from the audio and infer the level of concentration and emotional state.

[0134] Step 5:

[0135] The server integrates the results of facial expression and voice analysis into an emotion engine to accurately recognize the participant's overall emotional state. The emotion engine evaluates a variety of emotions, such as stress, relaxation, and excitement.

[0136] Step 6:

[0137] Based on the recognized emotional states, the server generates suggestions tailored to the progress of the meeting and the emotions of the participants. For example, if participants appear stressed, suggestions for rest or relaxation may be considered.

[0138] Step 7:

[0139] The server notifies each user (device) of the generated suggestions. The notification includes the specific details of the suggested action.

[0140] Step 8:

[0141] The user reviews the notification from the server and chooses whether to take the suggested action. If the user follows the suggestion, the server takes action accordingly.

[0142] Step 9:

[0143] The server continues to perform analysis and monitor the progress of the meeting even after the proposal has been implemented. This helps maintain an optimal state in real time at all times.

[0144] (Example 2)

[0145] 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".

[0146] Traditional online meeting systems have problems such as difficulty in real-time monitoring of participants' emotional states and attention levels, and a lack of specific advice for optimizing meeting efficiency and participant engagement. As a result, there are challenges such as decreased participant concentration and insufficient meeting effectiveness.

[0147] 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.

[0148] In this invention, the server includes a device for receiving visual and auditory information from participants, means for analyzing the emotional state of participants based on the visual information acquired by the device, and means for analyzing the vocal characteristics of participants based on the auditory information acquired by the device. This makes it possible to accurately grasp the emotional state and attention level of participants and automatically generate and provide appropriate advice according to the progress of the meeting.

[0149] "Visual and auditory information" refers to video data showing participants' facial expressions and movements, and audio data showing what participants say and the tone of their voices.

[0150] "Device" refers to the hardware used to acquire participants' visual and auditory information and transmit it to the server.

[0151] "Methods for analyzing emotional states" refers to the process of analyzing participants' emotions from their facial expressions and actions to identify emotional states such as joy, surprise, and anger.

[0152] "Methods for analyzing vocal characteristics" refers to the process of analyzing vocal characteristics such as tone, intonation, and speed in participants' speech to estimate their emotions and state of attention.

[0153] An "algorithm" refers to a series of procedures or calculation methods that analyze changes in a participant's emotional state and voice characteristics, and estimate their emotion and attention level based on that combination.

[0154] The "advice generation function" refers to the ability to automatically create specific suggestions and instructions for optimizing a meeting, based on the participants' status and the progress of the meeting.

[0155] "Means of communication" refers to methods and techniques for notifying participants of the generated advice and encouraging them to take specific actions.

[0156] The system of this invention aims to improve the efficiency of virtual meetings by evaluating the emotional state and attention levels of participants in real time. When using the system, users participate in the meeting using a terminal. The terminal is equipped with a camera and microphone, which are used to collect visual and auditory information.

[0157] The server receives video and audio data transmitted from the terminal. The received data is analyzed using facial expression analysis tools (e.g., OpenCV or a common cloud API). This detects the facial feature points of the participants and estimates their emotional state. Additionally, audio analysis tools (e.g., a common cloud speech recognition API) are used to analyze the tone and intonation of the voice data and further estimate the emotional state.

[0158] The server integrates these analysis results into an emotion engine. This emotion engine uses a generative AI model to synthesize different data points to perform highly accurate emotion recognition. For example, it can determine whether a participant is stressed or relaxed.

[0159] Based on the results of the emotion engine, the server generates suggestions to optimize the meeting's progress. Specific examples of these suggestions might include suggestions to help participants relax or to suggest short breaks. These suggestions are delivered to each participant's device via notification from the server.

[0160] For example, if analysis indicates that a participant is experiencing stress during a meeting, the server will suggest to that participant, "Let's take a break to relax." This suggestion will be displayed on the participant's device screen, prompting them to take action regarding the meeting's progress.

[0161] An example of a prompt might be, "Analyze the emotional state of participants in real time and suggest appropriate break times." By using such prompts, the generative AI model can contribute to making meetings more efficient.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The user enables the camera and microphone on their device and joins the meeting. This action allows video and audio information to be acquired in real time. The device sends this data to the server. By receiving the user's video and audio information as input and sending it to the server, the system provides basic data for understanding the user's state during the meeting.

[0165] Step 2:

[0166] The server receives video information sent from the terminal. The received video data is input into a facial expression analysis tool. The server processes this data and estimates the user's emotional state from their facial expressions by analyzing facial feature points. As output, it generates emotional state data to send to the emotion engine.

[0167] Step 3:

[0168] The server receives audio information acquired from the terminal. Next, it inputs the received audio data into an audio analysis tool. The server analyzes the tone and intonation of the voice and further estimates the emotional state from the characteristics of the user's voice. As output, it generates audio feature data to send to the emotion engine.

[0169] Step 4:

[0170] The server integrates the analyzed facial expression and voice data into the emotion engine. Using a generative AI model, it analyzes this data to accurately recognize the user's overall emotional state. As output, it generates detailed emotion analysis data to evaluate the progress of the meeting and the user's level of concentration.

[0171] Step 5:

[0172] The server uses detailed sentiment analysis data from its emotion engine to generate suggestions for improving meeting efficiency. The suggestion generation process utilizes a generative AI model to create customized action suggestions for the user (e.g., suggestions for taking breaks). The output generates advice data containing specific suggestions.

[0173] Step 6:

[0174] The server transmits the generated advice data to the user. It displays a notification message on the terminal, allowing the user to respond to the suggestions immediately. By receiving the suggestions as input and directly engaging with the user, it enhances the productivity of meetings.

[0175] (Application Example 2)

[0176] 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 device 14 will be referred to as the "terminal."

[0177] In current virtual stores, there is a challenge in accurately understanding customers' real-time emotions and making appropriate product suggestions and guidance based on those emotions, thus failing to effectively increase purchasing intent. To capture customer interest and desire to buy, more accurate emotion analysis and dynamic, personalized suggestions based on those analyses are required.

[0178] 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.

[0179] In this invention, the server includes data collection means for receiving video and audio information of participants, facial expression analysis means for analyzing the participants' facial expressions based on the video information acquired by the data collection means, and voice analysis means for analyzing the tone of the participants' voices based on the audio information acquired by the data collection means. This enables highly accurate emotion analysis and personalized product recommendations to increase purchasing intent.

[0180] "Data collection means" refers to devices or functions that receive video and audio information of participants.

[0181] "Facial expression analysis means" refers to a device or function that analyzes a participant's facial expressions based on acquired video information and understands their characteristics.

[0182] "Voice analysis means" refers to a device or function that analyzes the tone of a participant's voice based on acquired voice information and understands its characteristics.

[0183] "Evaluation means" refers to devices or functions for estimating a participant's emotional state and level of concentration based on the analysis results of facial expression analysis means and voice analysis means.

[0184] "Proposal generation means" refers to a device or function that generates proposals to increase purchasing intent based on the results of the evaluation means.

[0185] "Notification means" refers to a device or function that notifies participants of proposals generated by the proposal generation means.

[0186] The system of this invention can accurately grasp the emotional state of individual customers by collecting and analyzing real-time video and audio information of participants in order to promote purchases in virtual stores. Specifically, the system is implemented as follows.

[0187] The server uses data collection methods to receive video and audio data from participants in real time from devices such as smart glasses. This data is analyzed by facial expression analysis methods, which use OpenCV and other tools to detect facial features and estimate emotions. The audio analysis method uses the Google Speech-to-Text API to analyze the tone of the voice and supplement the emotional state.

[0188] The terminal integrates these analysis results in the evaluation system and uses an evaluation algorithm to estimate the emotional state and level of concentration necessary to promote purchases by participants. The emotion engine can integrate facial expression data and voice data using Microsoft® Azure® Emotion API and other tools to capture subtle emotional changes.

[0189] Based on the evaluation results, the suggestion generation system generates optimal product suggestions and attractive information presentations for the customer. Users receive suggestions in real time through the notification system, which can stimulate their purchasing intent.

[0190] As a concrete example, when a user is browsing fashion items in a virtual store, the system will display pop-up information suggesting new styles or sales information to customers who appear expressionless. An example of a prompt message would be, "Please use facial and voice analysis to determine the customer's emotional state in real time in order to display product information that will interest them."

[0191] This invention enriches the customer experience and effectively increases purchasing intent in virtual shopping. By understanding implicit customer needs, it enables more personalized approaches to customers.

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server receives video and audio information from the terminal in real time via data collection means. It acquires video data from the camera and audio data from the microphone as input, and processes them into a format suitable for subsequent analysis. The output becomes data usable by facial expression analysis means and audio analysis means.

[0195] Step 2:

[0196] The server processes the received video data using facial expression analysis. Using image processing libraries such as OpenCV, it extracts facial feature points from the input data and estimates emotions. This results in outputting data indicating the state of the participant's facial expression, such as whether they are smiling or expressionless.

[0197] Step 3:

[0198] The server processes the audio data using speech analysis tools. Using the Google Speech-to-Text API, it converts the given audio input into text, estimating the tone and emotion of the voice. The output provides tone information such as anger, joy, or calmness.

[0199] Step 4:

[0200] In the evaluation system, the server integrates the outputs of the facial expression analysis system and the voice analysis system, and uses a generative AI model to estimate the participant's emotional state and level of concentration with high accuracy. The input is the results of the two analyses mentioned above, and based on this data, the server quantifies the current emotional state and outputs it.

[0201] Step 5:

[0202] In the proposal generation system, the server generates optimal product suggestions based on the output of the evaluation system. It uses prompt messages to activate a generation AI model, creating personalized product and information suggestions tailored to each participant from the input data. The output consists of attractive suggestions tailored to each participant.

[0203] Step 6:

[0204] Using a notification system, users receive generated suggestions in real time. The input consists of individual suggestion information from the suggestion generation system, which is configured to be displayed on the user's screen. The output displays suggestions that enhance the participant's virtual experience.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] The present invention provides a virtual meeting room that acquires video and audio information from participants and improves the efficiency of meetings based on this information. This system includes the following main functions:

[0222] First, the server collects video and audio data streams from the users (devices) participating in the meeting via their cameras and microphones. This data is processed in the cloud. The collected video information is then analyzed using facial expression analysis tools to identify the facial features of the participants. For example, it identifies whether a user is smiling or has a serious expression.

[0223] Similarly, the server analyzes the acquired audio information using voice analysis tools. Specifically, it monitors the user's voice tone, changes in voice quality, and volume to estimate their emotions and level of concentration. For example, it can determine whether the user is speaking in an energetic or tired voice.

[0224] These analysis results are aggregated by the server to evaluate the overall progress of the meeting and the level of participant engagement. Based on this evaluation, suggestions for optimizing the meeting are generated. For example, if participant engagement is low, it may suggest breakout sessions or revisit key agenda items.

[0225] Finally, the server notifies each user (device) of the generated proposals. The notified users can then take action based on those proposals. This makes it easier for participants to take necessary actions during the meeting, improving overall meeting efficiency.

[0226] For example, if it is estimated that many participants are not concentrating during a meeting, the server suggests starting breakout sessions and notifies the users. If the participants accept the suggestion, the server automatically divides them into smaller groups and sets up breakout session rooms. In this form, the present invention can promote efficient communication and improve the productivity of meetings.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The user (device) joins the virtual meeting and enables their camera and microphone. This initiates the collection of video and audio data.

[0230] Step 2:

[0231] The server receives video and audio data from each user in real time. The received data is converted into a format suitable for analysis.

[0232] Step 3:

[0233] The server inputs video data into a facial expression analysis tool to detect feature points on the participants' faces. This analysis identifies changes in facial expressions, such as smiles and eyebrow movements.

[0234] Step 4:

[0235] The server inputs the audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice to estimate emotions and level of concentration.

[0236] Step 5:

[0237] The server aggregates the analyzed facial and voice data and evaluates the overall level of concentration among participants. If the level of concentration drops below a certain threshold, the process moves to the next step.

[0238] Step 6:

[0239] Based on the evaluation results, the server generates suggestions to improve meeting efficiency. For example, it might suggest breakout sessions or encourage participants to organize the agenda.

[0240] Step 7:

[0241] The server notifies each user's terminal of the generated suggestions. The notification includes instructions for specific actions.

[0242] Step 8:

[0243] The user reviews the notification from the server and chooses whether to perform the suggested action. If the user accepts the suggestion, the server performs the action based on the suggestion.

[0244] (Example 1)

[0245] 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."

[0246] In modern meetings, where many participants are increasingly joining remotely, ensuring efficient communication has become a challenging task. In particular, it's difficult to gauge participants' level of focus and emotional state in real time, which can lack the basis for optimizing meeting progress. Therefore, there is a need for new technologies that enable effective meeting management and improve participant engagement.

[0247] 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.

[0248] In this invention, the server includes information gathering means for receiving video and audio information of participants, analysis means for analyzing the facial features of participants, and analysis means for analyzing changes in participants' voices. This makes it possible to evaluate the progress of the meeting and the level of concentration of participants in real time and generate appropriate suggestions.

[0249] "Information gathering means" refers to devices or software used to acquire video and audio information of participants.

[0250] "Analysis means" refers to a device or software that has the function of analyzing the facial features and voice changes of participants based on the collected video and audio information.

[0251] "Generation means" refers to a device or software for generating suggestions to optimize the progress of a meeting based on the results obtained by the analysis means.

[0252] "Notification means" refers to a device or function for communicating the generated proposal to participants.

[0253] "Small group division" refers to a method or technique for conducting a meeting by dividing the participants into small groups.

[0254] A "proposal to re-evaluate agenda items" is a suggestion to reconfirm the agenda items during a meeting and reassess their importance.

[0255] One embodiment of this invention is a system for improving the efficiency of meetings. This system consists of a server, terminals, and users involved with them.

[0256] The server is assumed to be a group of computers operating in a cloud environment. First, the terminal acquires video and audio information from participants. Video information is captured by the camera, and audio information is captured by the microphone. The acquired raw data is sent from the terminal to the server.

[0257] The server uses several analysis tools to process the received data. For video data, a facial recognition API is used to analyze the facial features of participants. This analysis is performed to determine whether the user is smiling, surprised, or expressing other emotions. For audio data, an audio analysis tool is used to observe changes in tone, volume, and speed of the voice. Specifically, the characteristics of the audio waveform are captured to estimate whether the participant is speaking energetically or exhausted.

[0258] The analysis results are aggregated on the server and used to evaluate participants' real-time emotional states and levels of engagement. Based on the evaluation, the server generates suggestions to optimize the meeting. These suggestions may include starting breakout sessions or re-evaluating the agenda. The suggestions are notified to each user via their terminal, and users can take appropriate action based on the suggestions.

[0259] For example, if analysis reveals a decline in participant engagement during a meeting, the server proposes splitting into smaller groups and notifies the user. If the user accepts the proposal, the server automatically assigns participants to smaller groups and sets up appropriate virtual spaces.

[0260] The use of generative AI models is also being considered, and an example of a prompt message could be, "Please tell me how to measure the level of concentration from participants' facial expressions and voice, and create and notify me of suggestions to improve meeting efficiency." In this way, the system would support effective meeting management.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The terminal acquires video data from users participating in the meeting via its camera and audio data via its microphone. The video is captured as an image stream, and the audio is captured as an audio waveform. This acquired data becomes the input. The terminal processes this input data in real time and sends it directly to the server.

[0264] Step 2:

[0265] The server inputs the video data received from the terminal into a video analysis tool. Specifically, it uses a face detection algorithm to identify facial regions from the video data and performs emotion analysis. For example, it identifies smiles, serious expressions, surprise, etc., and outputs an emotion score for each expression.

[0266] Step 3:

[0267] The server inputs the audio data received from the terminal into an audio analysis tool. The audio data is processed by an audio segmentation algorithm, which analyzes the tone, volume, and pitch of the voice. This outputs the audio characteristics necessary for estimating the user's emotional state and level of concentration.

[0268] Step 4:

[0269] The server aggregates the analysis results obtained in steps 2 and 3 and inputs them into the evaluation model. This model combines facial expression scores and voice characteristics to calculate an attention index for each participant. As a result, it outputs an evaluation of the overall progress of the meeting and emotional indicators of the participants.

[0270] Step 5:

[0271] The server generates suggestions to optimize the meeting based on the evaluation results. Using a generative model, it suggests breakout sessions if the level of engagement is low. It outputs the generated suggestions and generates corresponding recommendations.

[0272] Step 6:

[0273] The server distributes the generated proposals to each terminal using a notification system. Specifically, it creates a notification message containing the proposal content and implementation steps, and sends it to the user's terminal. This notification serves as the output, prompting the user to take action.

[0274] Step 7:

[0275] The user checks the notification received on their device and selects an action based on the suggestion. Once the user approves the suggestion, the device sends a notification to the server, which may automatically adjust the meeting settings. This feedback is treated as input and used for re-evaluation to optimize the overall meeting progress.

[0276] (Application Example 1)

[0277] 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."

[0278] In order to achieve effective customer service in a physical store, it is necessary to accurately recognize the customer's condition and interests and immediately take the most appropriate actions. However, with conventional methods, it is difficult to grasp the customer's feelings and interests, and as a result, often only uniform responses can be made. The purpose of the present invention is to solve these problems and improve customer satisfaction.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0280] In this invention, the server includes an information collection means for receiving the information of the participants, an analysis means for analyzing the expressions of the participants based on the video information acquired by the information collection means, and an analysis means for analyzing the tone of the voices of the participants based on the audio information acquired by the information collection means. Thereby, it becomes possible to grasp the interests of customers in real time within the store and make optimal customer service proposals.

[0281] The "information collection means" is a technical device used to acquire the video and audio information of customers.

[0282] The "analysis means" is a processing device for analyzing the expressions and tones of customers' voices based on the acquired video and audio information.

[0283] The "evaluation means" is a mechanism for evaluating the progress situation within the store and the degree of customer interest based on the analysis results by the analysis means.

[0284] The "proposal generation means" is a process for generating countermeasures for customers based on the evaluation results of the evaluation means.

[0285] The "notification means" is a means for reliably transmitting the proposal generated by the proposal generation means to the staff.

[0286] The "customer service support means" is a device or system for making optimal action proposals according to the interests and conditions of customers and assisting customer service activities.

[0287] The system that realizes the present invention collects customers' video and audio information, analyzes it, and provides means for optimizing customer service. The server uses devices such as smart glasses and robots to collect customers' information in real time within the store. This information is processed using a cloud computing platform.

[0288] Smart glasses and robots are equipped with high-resolution cameras and high-sensitivity microphones. This enables detailed collection of customers' expressions and voice tones. The server processes this data using video analysis tools such as OpenCV to analyze customers' expressions. At the same time, the voice data is converted into text by the Google Cloud Speech-to-Text API, and its tone and content are analyzed.

[0289] The analysis results are used by an evaluation algorithm using Google Cloud AI to estimate customers' interests and psychological states. Based on this evaluation, the server proposes optimal customer response measures. The proposed response measures are notified to the staff through smart glasses or directly approached to the customers by the robot.

[0290] As a specific example, when a customer in a clothing store is having trouble choosing a product and has an unstable expression, the system can directly ask the customer through the robot, "Do you need any help?" The staff receives the proposal notification on the smart glasses and can quickly provide support. This enables customers to obtain a more personalized experience and improves the store's response ability.

[0291] Examples of prompt sentences include, "Please tell me about a system that recognizes customers' emotions in real time through the analysis of customers' expressions and voices and proposes optimal customer service methods. In particular, please provide specific examples of customer service support that utilizes real-time notifications using smart glasses."

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The server acquires customer video and audio data in real time from smart glasses and robots. Input comes from high-resolution cameras and high-sensitivity microphones, which the server receives as a data stream. Output is digitized video and audio data. This information is stored in a cloud-based database.

[0295] Step 2:

[0296] The server processes the collected video data using OpenCV to analyze the customer's facial expressions. The input is the video data obtained in step 1, and the server performs face recognition and expression analysis on it. The output is the analysis result, for example, whether the customer is smiling or looking troubled. This analysis result serves as an indicator of the customer's emotional state.

[0297] Step 3:

[0298] The server converts the audio data into text using the Google Cloud Speech-to-Text API and analyzes the tone and content of the speech. The input is the audio data obtained in step 1, and the output is the transcribed speech content and its tone information. Based on this, the server determines whether the customer is excited or relaxed. This information is an important factor in estimating the customer's psychological state.

[0299] Step 4:

[0300] The server analyzes the results obtained in steps 2 and 3 using an evaluation algorithm to estimate the customer's interests and psychological state. The inputs are the facial expression analysis results and the voice analysis results, and the output is an evaluation of the customer's level of interest and psychological state. The server then identifies the customer's potential needs.

[0301] Step 5:

[0302] Based on the estimated customer status, the server uses the generative AI model to propose optimal customer response strategies. The input is the evaluation result in Step 4, and the output is a specific action proposal. For example, when the customer is in trouble, a proposal to ask "Can I help you?" is generated.

[0303] Step 6:

[0304] The server notifies the proposed content to the staff wearing smart glasses or the robot that interacts with the customer. The input is the proposal generated in Step 5, and the output is the notified action proposal. As a result, the store staff or the robot can immediately execute the response strategy and provide appropriate responses to the customer.

[0305] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0306] The system of the present invention acquires the video and audio information of the participants and provides a virtual conference room incorporating an emotion engine to improve the efficiency of the conference. This system includes the following main functions.

[0307] First, when the user (terminal) participates in a virtual conference, the user enables the camera and microphone to provide video and audio data. This data is transmitted to the server in real time.

[0308] The server inputs the collected data into the facial expression analysis tool and the audio analysis tool, and analyzes the feature points of the participants' faces and the tone of their voices. Thereby, the instantaneous emotional state and concentration of the participants are estimated.

[0309] Furthermore, this system integrates an emotion engine that combines analyzed facial expression data and voice data to recognize participants' emotions with high accuracy. The emotion engine determines, for example, whether a participant is feeling happy or stressed.

[0310] These analysis results are aggregated by a server to evaluate the overall progress of the meeting and the level of participant engagement. Based on these results, suggestions for improving meeting efficiency are generated. The suggestion generation system can provide customized suggestions for each participant. For example, it can offer suggestions to help a nervous participant relax.

[0311] Finally, the server notifies each user (device) of the generated suggestions. The notification includes specific actions tailored to the participant's emotional state, enabling more effective engagement.

[0312] As a concrete example, if the server detects that a participant is stressed based on their facial expressions during a meeting, it will suggest a short break for relaxation and notify the user. If the user accepts the suggestion, the server will temporarily suspend the meeting and set a break period. This approach can improve the productivity of meetings.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The user (device) joins the virtual meeting and activates their camera and microphone. This allows video and audio data of the meeting participants to be captured.

[0316] Step 2:

[0317] The server receives video and audio data from each user in real time and converts it to the appropriate format. This data is then processed into the format necessary for analysis.

[0318] Step 3:

[0319] The server inputs video data into a facial expression analysis tool to analyze the facial features of the participants. This analysis captures subtle changes in facial expressions and identifies the emotional state of those expressions.

[0320] Step 4:

[0321] The server inputs audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice. This allows it to extract emotional indicators from the audio and infer the level of concentration and emotional state.

[0322] Step 5:

[0323] The server integrates the results of facial expression and voice analysis into an emotion engine to accurately recognize the participant's overall emotional state. The emotion engine evaluates a variety of emotions, such as stress, relaxation, and excitement.

[0324] Step 6:

[0325] Based on the recognized emotional states, the server generates suggestions tailored to the progress of the meeting and the emotions of the participants. For example, if participants appear stressed, suggestions for rest or relaxation may be considered.

[0326] Step 7:

[0327] The server notifies each user (device) of the generated suggestions. The notification includes the specific details of the suggested action.

[0328] Step 8:

[0329] The user reviews the notification from the server and chooses whether to take the suggested action. If the user follows the suggestion, the server takes action accordingly.

[0330] Step 9:

[0331] The server continues to perform analysis and monitor the progress of the meeting even after the proposal has been implemented. This helps maintain an optimal state in real time at all times.

[0332] (Example 2)

[0333] 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".

[0334] Traditional online meeting systems have problems such as difficulty in real-time monitoring of participants' emotional states and attention levels, and a lack of specific advice for optimizing meeting efficiency and participant engagement. As a result, there are challenges such as decreased participant concentration and insufficient meeting effectiveness.

[0335] 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.

[0336] In this invention, the server includes a device for receiving visual and auditory information from participants, means for analyzing the emotional state of participants based on the visual information acquired by the device, and means for analyzing the vocal characteristics of participants based on the auditory information acquired by the device. This makes it possible to accurately grasp the emotional state and attention level of participants and automatically generate and provide appropriate advice according to the progress of the meeting.

[0337] "Visual and auditory information" refers to video data showing participants' facial expressions and movements, and audio data showing what participants say and the tone of their voices.

[0338] "Device" refers to the hardware used to acquire participants' visual and auditory information and transmit it to the server.

[0339] "Methods for analyzing emotional states" refers to the process of analyzing participants' emotions from their facial expressions and actions to identify emotional states such as joy, surprise, and anger.

[0340] "Methods for analyzing vocal characteristics" refers to the process of analyzing vocal characteristics such as tone, intonation, and speed in participants' speech to estimate their emotions and state of attention.

[0341] An "algorithm" refers to a series of procedures or calculation methods that analyze changes in a participant's emotional state and voice characteristics, and estimate their emotion and attention level based on that combination.

[0342] The "advice generation function" refers to the ability to automatically create specific suggestions and instructions for optimizing a meeting, based on the participants' status and the progress of the meeting.

[0343] "Means of communication" refers to methods and techniques for notifying participants of the generated advice and encouraging them to take specific actions.

[0344] The system of this invention aims to improve the efficiency of virtual meetings by evaluating the emotional state and attention levels of participants in real time. When using the system, users participate in the meeting using a terminal. The terminal is equipped with a camera and microphone, which are used to collect visual and auditory information.

[0345] The server receives video and audio data transmitted from the terminal. The received data is analyzed using facial expression analysis tools (e.g., OpenCV or a common cloud API). This detects the facial feature points of the participants and estimates their emotional state. Additionally, audio analysis tools (e.g., a common cloud speech recognition API) are used to analyze the tone and intonation of the voice data and further estimate the emotional state.

[0346] The server integrates these analysis results into an emotion engine. This emotion engine uses a generative AI model to synthesize different data points to perform highly accurate emotion recognition. For example, it can determine whether a participant is stressed or relaxed.

[0347] Based on the results of the emotion engine, the server generates suggestions to optimize the meeting's progress. Specific examples of these suggestions might include suggestions to help participants relax or to suggest short breaks. These suggestions are delivered to each participant's device via notification from the server.

[0348] For example, if analysis indicates that a participant is experiencing stress during a meeting, the server will suggest to that participant, "Let's take a break to relax." This suggestion will be displayed on the participant's device screen, prompting them to take action regarding the meeting's progress.

[0349] An example of a prompt might be, "Analyze the emotional state of participants in real time and suggest appropriate break times." By using such prompts, the generative AI model can contribute to making meetings more efficient.

[0350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0351] Step 1:

[0352] The user enables the camera and microphone on their device and joins the meeting. This action allows video and audio information to be acquired in real time. The device sends this data to the server. By receiving the user's video and audio information as input and sending it to the server, the system provides basic data for understanding the user's state during the meeting.

[0353] Step 2:

[0354] The server receives video information sent from the terminal. The received video data is input into a facial expression analysis tool. The server processes this data and estimates the user's emotional state from their facial expressions by analyzing facial feature points. As output, it generates emotional state data to send to the emotion engine.

[0355] Step 3:

[0356] The server receives audio information acquired from the terminal. Next, it inputs the received audio data into an audio analysis tool. The server analyzes the tone and intonation of the voice and further estimates the emotional state from the characteristics of the user's voice. As output, it generates audio feature data to send to the emotion engine.

[0357] Step 4:

[0358] The server integrates the analyzed facial expression and voice data into the emotion engine. Using a generative AI model, it analyzes this data to accurately recognize the user's overall emotional state. As output, it generates detailed emotion analysis data to evaluate the progress of the meeting and the user's level of concentration.

[0359] Step 5:

[0360] The server uses detailed sentiment analysis data from its emotion engine to generate suggestions for improving meeting efficiency. The suggestion generation process utilizes a generative AI model to create customized action suggestions for the user (e.g., suggestions for taking breaks). The output generates advice data containing specific suggestions.

[0361] Step 6:

[0362] The server transmits the generated advice data to the user. It displays a notification message on the terminal, allowing the user to respond to the suggestions immediately. By receiving the suggestions as input and directly engaging with the user, it enhances the productivity of meetings.

[0363] (Application Example 2)

[0364] 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."

[0365] In current virtual stores, there is a challenge in accurately understanding customers' real-time emotions and making appropriate product suggestions and guidance based on those emotions, thus failing to effectively increase purchasing intent. To capture customer interest and desire to buy, more accurate emotion analysis and dynamic, personalized suggestions based on those analyses are required.

[0366] 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.

[0367] In this invention, the server includes data collection means for receiving video and audio information of participants, facial expression analysis means for analyzing the participants' facial expressions based on the video information acquired by the data collection means, and voice analysis means for analyzing the tone of the participants' voices based on the audio information acquired by the data collection means. This enables highly accurate emotion analysis and personalized product recommendations to increase purchasing intent.

[0368] "Data collection means" refers to devices or functions that receive video and audio information of participants.

[0369] "Facial expression analysis means" refers to a device or function that analyzes a participant's facial expressions based on acquired video information and understands their characteristics.

[0370] "Voice analysis means" refers to a device or function that analyzes the tone of a participant's voice based on acquired voice information and understands its characteristics.

[0371] "Evaluation means" refers to devices or functions for estimating a participant's emotional state and level of concentration based on the analysis results of facial expression analysis means and voice analysis means.

[0372] "Proposal generation means" refers to a device or function that generates proposals to increase purchasing intent based on the results of the evaluation means.

[0373] "Notification means" refers to a device or function that notifies participants of proposals generated by the proposal generation means.

[0374] The system of this invention can accurately grasp the emotional state of individual customers by collecting and analyzing real-time video and audio information of participants in order to promote purchases in virtual stores. Specifically, the system is implemented as follows.

[0375] The server uses data collection methods to receive video and audio data from participants in real time from devices such as smart glasses. This data is analyzed by facial expression analysis methods, which use OpenCV and other tools to detect facial features and estimate emotions. The audio analysis method uses the Google Speech-to-Text API to analyze the tone of the voice and supplement the emotional state.

[0376] The terminal integrates these analysis results in the evaluation system and uses an evaluation algorithm to estimate the emotional state and level of concentration necessary to promote purchases by participants. The emotion engine can integrate facial expression data and voice data using Microsoft Azure's Emotion API, etc., to capture subtle emotional changes.

[0377] Based on the evaluation results, the suggestion generation system generates optimal product suggestions and attractive information presentations for the customer. Users receive suggestions in real time through the notification system, which can stimulate their purchasing intent.

[0378] As a concrete example, when a user is browsing fashion items in a virtual store, the system will display pop-up information suggesting new styles or sales information to customers who appear expressionless. An example of a prompt message would be, "Please use facial and voice analysis to determine the customer's emotional state in real time in order to display product information that will interest them."

[0379] This invention enriches the customer experience and effectively increases purchasing intent in virtual shopping. By understanding implicit customer needs, it enables more personalized approaches to customers.

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The server receives video and audio information from the terminal in real time via data collection means. It acquires video data from the camera and audio data from the microphone as input, and processes them into a format suitable for subsequent analysis. The output becomes data usable by facial expression analysis means and audio analysis means.

[0383] Step 2:

[0384] The server processes the received video data using facial expression analysis. Using image processing libraries such as OpenCV, it extracts facial feature points from the input data and estimates emotions. This results in outputting data indicating the state of the participant's facial expression, such as whether they are smiling or expressionless.

[0385] Step 3:

[0386] The server processes the audio data using speech analysis tools. Using the Google Speech-to-Text API, it converts the given audio input into text, estimating the tone and emotion of the voice. The output provides tone information such as anger, joy, or calmness.

[0387] Step 4:

[0388] In the evaluation system, the server integrates the outputs of the facial expression analysis system and the voice analysis system, and uses a generative AI model to estimate the participant's emotional state and level of concentration with high accuracy. The input is the results of the two analyses mentioned above, and based on this data, the server quantifies the current emotional state and outputs it.

[0389] Step 5:

[0390] In the proposal generation system, the server generates optimal product suggestions based on the output of the evaluation system. It uses prompt messages to activate a generation AI model, creating personalized product and information suggestions tailored to each participant from the input data. The output consists of attractive suggestions tailored to each participant.

[0391] Step 6:

[0392] Using a notification system, users receive generated suggestions in real time. The input consists of individual suggestion information from the suggestion generation system, which is configured to be displayed on the user's screen. The output displays suggestions that enhance the participant's virtual experience.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] The present invention provides a virtual meeting room that acquires video and audio information from participants and improves the efficiency of meetings based on this information. This system includes the following main functions:

[0410] First, the server collects video and audio data streams from the users (devices) participating in the meeting via their cameras and microphones. This data is processed in the cloud. The collected video information is then analyzed using facial expression analysis tools to identify the facial features of the participants. For example, it identifies whether a user is smiling or has a serious expression.

[0411] Similarly, the server analyzes the acquired audio information using voice analysis tools. Specifically, it monitors the user's voice tone, changes in voice quality, and volume to estimate their emotions and level of concentration. For example, it can determine whether the user is speaking in an energetic or tired voice.

[0412] These analysis results are aggregated by the server to evaluate the overall progress of the meeting and the level of participant engagement. Based on this evaluation, suggestions for optimizing the meeting are generated. For example, if participant engagement is low, it may suggest breakout sessions or revisit key agenda items.

[0413] Finally, the server notifies each user (device) of the generated proposals. The notified users can then take action based on those proposals. This makes it easier for participants to take necessary actions during the meeting, improving overall meeting efficiency.

[0414] For example, if it is estimated that many participants are not concentrating during a meeting, the server suggests starting breakout sessions and notifies the users. If the participants accept the suggestion, the server automatically divides them into smaller groups and sets up breakout session rooms. In this form, the present invention can promote efficient communication and improve the productivity of meetings.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] The user (device) joins the virtual meeting and enables their camera and microphone. This initiates the collection of video and audio data.

[0418] Step 2:

[0419] The server receives video and audio data from each user in real time. The received data is converted into a format suitable for analysis.

[0420] Step 3:

[0421] The server inputs video data into a facial expression analysis tool to detect feature points on the participants' faces. This analysis identifies changes in facial expressions, such as smiles and eyebrow movements.

[0422] Step 4:

[0423] The server inputs the audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice to estimate emotions and level of concentration.

[0424] Step 5:

[0425] The server aggregates the analyzed facial and voice data and evaluates the overall level of concentration among participants. If the level of concentration drops below a certain threshold, the process moves to the next step.

[0426] Step 6:

[0427] Based on the evaluation results, the server generates suggestions to improve the efficiency of the meeting. For example, it might suggest breakout sessions or encourage participants to organize the agenda.

[0428] Step 7:

[0429] The server notifies each user's terminal of the generated suggestions. The notification includes instructions for specific actions.

[0430] Step 8:

[0431] The user reviews the notification from the server and chooses whether to perform the suggested action. If the user accepts the suggestion, the server performs the action based on the suggestion.

[0432] (Example 1)

[0433] 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."

[0434] In modern meetings, where many participants are increasingly joining remotely, ensuring efficient communication has become a challenging task. In particular, it's difficult to gauge participants' level of focus and emotional state in real time, which can lack the basis for optimizing meeting progress. Therefore, there is a need for new technologies that enable effective meeting management and improve participant engagement.

[0435] 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.

[0436] In this invention, the server includes information gathering means for receiving video and audio information of participants, analysis means for analyzing the facial features of participants, and analysis means for analyzing changes in participants' voices. This makes it possible to evaluate the progress of the meeting and the level of concentration of participants in real time and generate appropriate suggestions.

[0437] "Information gathering means" refers to devices or software used to acquire video and audio information of participants.

[0438] "Analysis means" refers to a device or software that has the function of analyzing the facial features and voice changes of participants based on the collected video and audio information.

[0439] "Generation means" refers to a device or software for generating suggestions to optimize the progress of a meeting based on the results obtained by the analysis means.

[0440] "Notification means" refers to a device or function for communicating the generated proposal to participants.

[0441] "Small group division" refers to a method or technique for conducting a meeting by dividing the participants into small groups.

[0442] A "proposal to re-evaluate agenda items" is a suggestion to reconfirm the agenda items during a meeting and reassess their importance.

[0443] One embodiment of this invention is a system for improving the efficiency of meetings. This system consists of a server, terminals, and users involved with them.

[0444] The server is assumed to be a group of computers operating in a cloud environment. First, the terminal acquires video and audio information from participants. Video information is captured by the camera, and audio information is captured by the microphone. The acquired raw data is sent from the terminal to the server.

[0445] The server uses several analysis tools to process the received data. For video data, a facial recognition API is used to analyze the facial features of participants. This analysis is performed to determine whether the user is smiling, surprised, or expressing other emotions. For audio data, an audio analysis tool is used to observe changes in tone, volume, and speed of the voice. Specifically, the characteristics of the audio waveform are captured to estimate whether the participant is speaking energetically or exhausted.

[0446] The analysis results are aggregated on the server and used to evaluate participants' real-time emotional states and levels of engagement. Based on the evaluation, the server generates suggestions to optimize the meeting. These suggestions may include starting breakout sessions or re-evaluating the agenda. The suggestions are notified to each user via their terminal, and users can take appropriate action based on the suggestions.

[0447] For example, if analysis reveals a decline in participant engagement during a meeting, the server proposes splitting into smaller groups and notifies the user. If the user accepts the proposal, the server automatically assigns participants to smaller groups and sets up appropriate virtual spaces.

[0448] The use of generative AI models is also being considered, and an example of a prompt message could be, "Please tell me how to measure the level of concentration from participants' facial expressions and voice, and create and notify me of suggestions to improve meeting efficiency." In this way, the system would support effective meeting management.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The terminal acquires video data from users participating in the meeting via its camera and audio data via its microphone. The video is captured as an image stream, and the audio is captured as an audio waveform. This acquired data becomes the input. The terminal processes this input data in real time and sends it directly to the server.

[0452] Step 2:

[0453] The server inputs the video data received from the terminal into a video analysis tool. Specifically, it uses a face detection algorithm to identify facial regions from the video data and performs emotion analysis. For example, it identifies smiles, serious expressions, surprise, etc., and outputs an emotion score for each expression.

[0454] Step 3:

[0455] The server inputs the audio data received from the terminal into an audio analysis tool. The audio data is processed by an audio segmentation algorithm, which analyzes the tone, volume, and pitch of the voice. This outputs the audio characteristics necessary for estimating the user's emotional state and level of concentration.

[0456] Step 4:

[0457] The server aggregates the analysis results obtained in steps 2 and 3 and inputs them into the evaluation model. This model combines facial expression scores and voice characteristics to calculate an attention index for each participant. As a result, it outputs an evaluation of the overall progress of the meeting and emotional indicators of the participants.

[0458] Step 5:

[0459] The server generates suggestions to optimize the meeting based on the evaluation results. Using a generative model, it suggests breakout sessions if the level of engagement is low. It outputs the generated suggestions and generates corresponding recommendations.

[0460] Step 6:

[0461] The server distributes the generated proposals to each terminal using a notification system. Specifically, it creates a notification message containing the proposal content and implementation steps, and sends it to the user's terminal. This notification serves as the output, prompting the user to take action.

[0462] Step 7:

[0463] The user checks the notification received on their device and selects an action based on the suggestion. Once the user approves the suggestion, the device sends a notification to the server, which may automatically adjust the meeting settings. This feedback is treated as input and used for re-evaluation to optimize the overall meeting progress.

[0464] (Application Example 1)

[0465] 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."

[0466] To provide effective customer service in physical stores, it is essential to accurately understand the customer's situation and interests and to respond immediately to the most appropriate needs. However, conventional methods often make it difficult to grasp customer emotions and interests, resulting in uniform responses. This invention aims to solve these problems and improve customer satisfaction.

[0467] 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.

[0468] In this invention, the server includes an information gathering means for receiving participant information, an analysis means for analyzing the participant's facial expressions based on the video information acquired by the information gathering means, and an analysis means for analyzing the participant's voice tone based on the audio information acquired by the information gathering means. This makes it possible to grasp customer interests in real time within the store and make optimal customer service suggestions.

[0469] "Information gathering means" refers to technical devices used to acquire video and audio information of customers.

[0470] The "analysis means" is a processing device for analyzing the customer's facial expressions and voice tone based on acquired video and audio information.

[0471] An "evaluation tool" is a system for evaluating the progress within a store and the level of customer interest based on the results of analysis performed by an analysis tool.

[0472] A "proposal generation method" is a process for generating customer response measures based on the evaluation results of the evaluation method.

[0473] "Notification means" refers to the means of reliably communicating proposals generated by the proposal generation means to the staff.

[0474] "Customer service support tools" are devices and systems that assist customer service activities by suggesting optimal actions tailored to the customer's interests and circumstances.

[0475] The system realizing this invention provides means for collecting and analyzing customer video and audio information to optimize customer service. A server collects customer information in real time within the store using devices such as smart glasses or robots. This information is processed using a cloud computing platform.

[0476] Smart glasses and robots are equipped with high-resolution cameras and high-sensitivity microphones. This allows for detailed collection of customer facial expressions and voice tones. The server processes this data using video analysis tools such as OpenCV to analyze the customer's facial expressions. Simultaneously, the audio data is converted to text using the Google Cloud Speech-to-Text API, and its tone and content are analyzed.

[0477] The analysis results are used by an evaluation algorithm powered by Google Cloud AI to estimate the customer's interests and psychological state. Based on this evaluation, the server proposes the optimal customer response. The proposed response is notified to staff via smart glasses, or a robot directly approaches the customer.

[0478] As a concrete example, if a customer in a clothing store is having trouble choosing an item and their expression is uncertain, the system can directly ask the customer, "Do you need any assistance?" via a robot. Staff members receive a suggestion notification on their smart glasses and can provide support quickly. This allows customers to have a more personalized experience and improves the store's responsiveness.

[0479] An example of a prompt message is: "Please tell me about a system that analyzes customer facial expressions and voices to recognize customer emotions in real time and suggest the most appropriate customer service approach. In particular, please provide specific examples of customer service support utilizing real-time notifications via smart glasses."

[0480] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0481] Step 1:

[0482] The server acquires customer video and audio data in real time from smart glasses and robots. Input comes from high-resolution cameras and high-sensitivity microphones, which the server receives as a data stream. Output is digitized video and audio data. This information is stored in a cloud-based database.

[0483] Step 2:

[0484] The server processes the collected video data using OpenCV to analyze the customer's facial expressions. The input is the video data obtained in step 1, and the server performs face recognition and expression analysis on it. The output is the analysis result, for example, whether the customer is smiling or looking troubled. This analysis result serves as an indicator of the customer's emotional state.

[0485] Step 3:

[0486] The server converts the audio data into text using the Google Cloud Speech-to-Text API and analyzes the tone and content of the speech. The input is the audio data obtained in step 1, and the output is the transcribed speech content and its tone information. Based on this, the server determines whether the customer is excited or relaxed. This information is an important factor in estimating the customer's psychological state.

[0487] Step 4:

[0488] The server analyzes the results obtained in steps 2 and 3 using an evaluation algorithm to estimate the customer's interests and psychological state. The inputs are the facial expression analysis results and the voice analysis results, and the output is an evaluation of the customer's level of interest and psychological state. The server then identifies the customer's potential needs.

[0489] Step 5:

[0490] The server uses a generative AI model to suggest the optimal customer response based on the estimated customer state. The input is the evaluation result from step 4, and the output is a specific action suggestion. For example, if the customer is in trouble, a suggestion such as "Can I help you?" will be generated.

[0491] Step 6:

[0492] The server notifies staff wearing smart glasses or robots interacting with customers of the suggested actions. The input is the suggestion generated in step 5, and the output is the notified action suggestion. This allows store staff or robots to immediately take action and provide appropriate service to customers.

[0493] 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.

[0494] The present invention provides a virtual meeting room that incorporates an emotion engine to acquire video and audio information from participants and improve the efficiency of meetings. This system includes the following main functions:

[0495] First, the user (device) provides video and audio data by enabling the camera and microphone when joining a virtual meeting. This data is sent to the server in real time.

[0496] The server inputs the collected data into facial expression analysis tools and voice analysis tools to analyze the participants' facial features and voice tone. This allows the server to estimate the participants' instantaneous emotional state and level of concentration.

[0497] Furthermore, this system integrates an emotion engine that combines analyzed facial expression data and voice data to recognize participants' emotions with high accuracy. The emotion engine determines, for example, whether a participant is feeling happy or stressed.

[0498] These analysis results are aggregated by a server to evaluate the overall progress of the meeting and the level of participant engagement. Based on these results, suggestions for improving meeting efficiency are generated. The suggestion generation system can provide customized suggestions for each participant. For example, it can offer suggestions to help a nervous participant relax.

[0499] Finally, the server notifies each user (device) of the generated suggestions. The notification includes specific actions tailored to the participant's emotional state, enabling more effective engagement.

[0500] As a concrete example, if the server detects that a participant is stressed based on their facial expressions during a meeting, it will suggest a short break for relaxation and notify the user. If the user accepts the suggestion, the server will temporarily suspend the meeting and set a break period. This approach can improve the productivity of meetings.

[0501] The following describes the processing flow.

[0502] Step 1:

[0503] The user (device) joins the virtual meeting and activates their camera and microphone. This allows video and audio data of the meeting participants to be captured.

[0504] Step 2:

[0505] The server receives video and audio data from each user in real time and converts it to the appropriate format. This data is then processed into the format necessary for analysis.

[0506] Step 3:

[0507] The server inputs video data into a facial expression analysis tool to analyze the facial features of the participants. This analysis captures subtle changes in facial expressions and identifies the emotional state of those expressions.

[0508] Step 4:

[0509] The server inputs audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice. This allows it to extract emotional indicators from the audio and infer the level of concentration and emotional state.

[0510] Step 5:

[0511] The server integrates the results of facial expression and voice analysis into an emotion engine to accurately recognize the participant's overall emotional state. The emotion engine evaluates a variety of emotions, such as stress, relaxation, and excitement.

[0512] Step 6:

[0513] Based on the recognized emotional states, the server generates suggestions tailored to the progress of the meeting and the emotions of the participants. For example, if participants appear stressed, suggestions for rest or relaxation may be considered.

[0514] Step 7:

[0515] The server notifies each user (device) of the generated suggestions. The notification includes the specific details of the suggested action.

[0516] Step 8:

[0517] The user reviews the notification from the server and chooses whether to take the suggested action. If the user follows the suggestion, the server takes action accordingly.

[0518] Step 9:

[0519] The server continues to perform analysis and monitor the progress of the meeting even after the proposal has been implemented. This helps maintain an optimal state in real time at all times.

[0520] (Example 2)

[0521] 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."

[0522] Traditional online meeting systems have problems such as difficulty in real-time monitoring of participants' emotional states and attention levels, and a lack of specific advice for optimizing meeting efficiency and participant engagement. As a result, there are challenges such as decreased participant concentration and insufficient meeting effectiveness.

[0523] 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.

[0524] In this invention, the server includes a device for receiving visual and auditory information from participants, means for analyzing the emotional state of participants based on the visual information acquired by the device, and means for analyzing the vocal characteristics of participants based on the auditory information acquired by the device. This makes it possible to accurately grasp the emotional state and attention level of participants and automatically generate and provide appropriate advice according to the progress of the meeting.

[0525] "Visual and auditory information" refers to video data showing participants' facial expressions and movements, and audio data showing what participants say and the tone of their voices.

[0526] "Device" refers to the hardware used to acquire participants' visual and auditory information and transmit it to the server.

[0527] "Methods for analyzing emotional states" refers to the process of analyzing participants' emotions from their facial expressions and actions to identify emotional states such as joy, surprise, and anger.

[0528] "Methods for analyzing vocal characteristics" refers to the process of analyzing vocal characteristics such as tone, intonation, and speed in participants' speech to estimate their emotions and state of attention.

[0529] An "algorithm" refers to a series of procedures or calculation methods that analyze changes in a participant's emotional state and voice characteristics, and estimate their emotion and attention level based on that combination.

[0530] The "advice generation function" refers to the ability to automatically create specific suggestions and instructions for optimizing a meeting, based on the participants' status and the progress of the meeting.

[0531] "Means of communication" refers to methods and techniques for notifying participants of the generated advice and encouraging them to take specific actions.

[0532] The system of this invention aims to improve the efficiency of virtual meetings by evaluating the emotional state and attention levels of participants in real time. When using the system, users participate in the meeting using a terminal. The terminal is equipped with a camera and microphone, which are used to collect visual and auditory information.

[0533] The server receives video and audio data transmitted from the terminal. The received data is analyzed using facial expression analysis tools (e.g., OpenCV or a common cloud API). This detects the facial feature points of the participants and estimates their emotional state. Additionally, audio analysis tools (e.g., a common cloud speech recognition API) are used to analyze the tone and intonation of the voice data and further estimate the emotional state.

[0534] The server integrates these analysis results into an emotion engine. This emotion engine uses a generative AI model to synthesize different data points to perform highly accurate emotion recognition. For example, it can determine whether a participant is stressed or relaxed.

[0535] Based on the results of the emotion engine, the server generates suggestions to optimize the meeting's progress. Specific examples of these suggestions might include suggestions to help participants relax or to suggest short breaks. These suggestions are delivered to each participant's device via notification from the server.

[0536] For example, if analysis indicates that a participant is experiencing stress during a meeting, the server will suggest to that participant, "Let's take a break to relax." This suggestion will be displayed on the participant's device screen, prompting them to take action regarding the meeting's progress.

[0537] An example of a prompt might be, "Analyze the emotional state of participants in real time and suggest appropriate break times." By using such prompts, the generative AI model can contribute to making meetings more efficient.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The user enables the camera and microphone on their device and joins the meeting. This action allows video and audio information to be acquired in real time. The device sends this data to the server. By receiving the user's video and audio information as input and sending it to the server, the system provides basic data for understanding the user's state during the meeting.

[0541] Step 2:

[0542] The server receives video information sent from the terminal. The received video data is input into a facial expression analysis tool. The server processes this data and estimates the user's emotional state from their facial expressions by analyzing facial feature points. As output, it generates emotional state data to send to the emotion engine.

[0543] Step 3:

[0544] The server receives audio information acquired from the terminal. Next, it inputs the received audio data into an audio analysis tool. The server analyzes the tone and intonation of the voice and further estimates the emotional state from the characteristics of the user's voice. As output, it generates audio feature data to send to the emotion engine.

[0545] Step 4:

[0546] The server integrates the analyzed facial expression and voice data into the emotion engine. Using a generative AI model, it analyzes this data to accurately recognize the user's overall emotional state. As output, it generates detailed emotion analysis data to evaluate the progress of the meeting and the user's level of concentration.

[0547] Step 5:

[0548] The server uses detailed sentiment analysis data from its emotion engine to generate suggestions for improving meeting efficiency. The suggestion generation process utilizes a generative AI model to create customized action suggestions for the user (e.g., suggestions for taking breaks). The output generates advice data containing specific suggestions.

[0549] Step 6:

[0550] The server transmits the generated advice data to the user. It displays a notification message on the terminal, allowing the user to respond to the suggestions immediately. By receiving the suggestions as input and directly engaging with the user, it enhances the productivity of meetings.

[0551] (Application Example 2)

[0552] 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."

[0553] In current virtual stores, there is a challenge in accurately understanding customers' real-time emotions and making appropriate product suggestions and guidance based on those emotions, thus failing to effectively increase purchasing intent. To capture customer interest and desire to buy, more accurate emotion analysis and dynamic, personalized suggestions based on those analyses are required.

[0554] 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.

[0555] In this invention, the server includes data collection means for receiving video and audio information of participants, facial expression analysis means for analyzing the participants' facial expressions based on the video information acquired by the data collection means, and voice analysis means for analyzing the tone of the participants' voices based on the audio information acquired by the data collection means. This enables highly accurate emotion analysis and personalized product recommendations to increase purchasing intent.

[0556] "Data collection means" refers to devices or functions that receive video and audio information of participants.

[0557] "Facial expression analysis means" refers to a device or function that analyzes a participant's facial expressions based on acquired video information and understands their characteristics.

[0558] "Voice analysis means" refers to a device or function that analyzes the tone of a participant's voice based on acquired voice information and understands its characteristics.

[0559] "Evaluation means" refers to devices or functions for estimating a participant's emotional state and level of concentration based on the analysis results of facial expression analysis means and voice analysis means.

[0560] "Proposal generation means" refers to a device or function that generates proposals to increase purchasing intent based on the results of the evaluation means.

[0561] "Notification means" refers to a device or function that notifies participants of proposals generated by the proposal generation means.

[0562] The system of this invention can accurately grasp the emotional state of individual customers by collecting and analyzing real-time video and audio information of participants in order to promote purchases in virtual stores. Specifically, the system is implemented as follows.

[0563] The server uses data collection methods to receive video and audio data from participants in real time from devices such as smart glasses. This data is analyzed by facial expression analysis methods, which use OpenCV and other tools to detect facial features and estimate emotions. The audio analysis method uses the Google Speech-to-Text API to analyze the tone of the voice and supplement the emotional state.

[0564] The terminal integrates these analysis results in the evaluation system and uses an evaluation algorithm to estimate the emotional state and level of concentration necessary to promote purchases by participants. The emotion engine can integrate facial expression data and voice data using Microsoft Azure's Emotion API, etc., to capture subtle emotional changes.

[0565] Based on the evaluation results, the suggestion generation system generates optimal product suggestions and attractive information presentations for the customer. Users receive suggestions in real time through the notification system, which can stimulate their purchasing intent.

[0566] As a concrete example, when a user is browsing fashion items in a virtual store, the system will display pop-up information suggesting new styles or sales information to customers who appear expressionless. An example of a prompt message would be, "Please use facial and voice analysis to determine the customer's emotional state in real time in order to display product information that will interest them."

[0567] This invention enriches the customer experience and effectively increases purchasing intent in virtual shopping. By understanding implicit customer needs, it enables more personalized approaches to customers.

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The server receives video and audio information from the terminal in real time via data collection means. It acquires video data from the camera and audio data from the microphone as input, and processes them into a format suitable for subsequent analysis. The output becomes data usable by facial expression analysis means and audio analysis means.

[0571] Step 2:

[0572] The server processes the received video data using facial expression analysis. Using image processing libraries such as OpenCV, it extracts facial feature points from the input data and estimates emotions. This results in outputting data indicating the state of the participant's facial expression, such as whether they are smiling or expressionless.

[0573] Step 3:

[0574] The server processes the audio data using speech analysis tools. Using the Google Speech-to-Text API, it converts the given audio input into text, estimating the tone and emotion of the voice. The output provides tone information such as anger, joy, or calmness.

[0575] Step 4:

[0576] In the evaluation system, the server integrates the outputs of the facial expression analysis system and the voice analysis system, and uses a generative AI model to estimate the participant's emotional state and level of concentration with high accuracy. The input is the results of the two analyses mentioned above, and based on this data, the server quantifies the current emotional state and outputs it.

[0577] Step 5:

[0578] In the proposal generation system, the server generates optimal product suggestions based on the output of the evaluation system. It uses prompt messages to activate a generation AI model, creating personalized product and information suggestions tailored to each participant from the input data. The output consists of attractive suggestions tailored to each participant.

[0579] Step 6:

[0580] Using a notification system, users receive generated suggestions in real time. The input consists of individual suggestion information from the suggestion generation system, which is configured to be displayed on the user's screen. The output displays suggestions that enhance the participant's virtual experience.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] The present invention provides a virtual meeting room that acquires video and audio information from participants and improves the efficiency of meetings based on this information. This system includes the following main functions:

[0599] First, the server collects video and audio data streams from the users (devices) participating in the meeting via their cameras and microphones. This data is processed in the cloud. The collected video information is then analyzed using facial expression analysis tools to identify the facial features of the participants. For example, it identifies whether a user is smiling or has a serious expression.

[0600] Similarly, the server analyzes the acquired audio information using voice analysis tools. Specifically, it monitors the user's voice tone, changes in voice quality, and volume to estimate their emotions and level of concentration. For example, it can determine whether the user is speaking in an energetic or tired voice.

[0601] These analysis results are aggregated by the server to evaluate the overall progress of the meeting and the level of participant engagement. Based on this evaluation, suggestions for optimizing the meeting are generated. For example, if participant engagement is low, it may suggest breakout sessions or revisit key agenda items.

[0602] Finally, the server notifies each user (device) of the generated proposals. The notified users can then take action based on those proposals. This makes it easier for participants to take necessary actions during the meeting, improving overall meeting efficiency.

[0603] For example, if it is estimated that many participants are not concentrating during a meeting, the server suggests starting breakout sessions and notifies the users. If the participants accept the suggestion, the server automatically divides them into smaller groups and sets up breakout session rooms. In this form, the present invention can promote efficient communication and improve the productivity of meetings.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The user (device) joins the virtual meeting and enables their camera and microphone. This initiates the collection of video and audio data.

[0607] Step 2:

[0608] The server receives video and audio data from each user in real time. The received data is converted into a format suitable for analysis.

[0609] Step 3:

[0610] The server inputs video data into a facial expression analysis tool to detect feature points on the participants' faces. This analysis identifies changes in facial expressions, such as smiles and eyebrow movements.

[0611] Step 4:

[0612] The server inputs the audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice to estimate emotions and level of concentration.

[0613] Step 5:

[0614] The server aggregates the analyzed facial and voice data and evaluates the overall level of concentration among participants. If the level of concentration drops below a certain threshold, the process moves to the next step.

[0615] Step 6:

[0616] Based on the evaluation results, the server generates suggestions to improve the efficiency of the meeting. For example, it might suggest breakout sessions or encourage participants to organize the agenda.

[0617] Step 7:

[0618] The server notifies each user's terminal of the generated suggestions. The notification includes instructions for specific actions.

[0619] Step 8:

[0620] The user reviews the notification from the server and chooses whether to perform the suggested action. If the user accepts the suggestion, the server performs the action based on the suggestion.

[0621] (Example 1)

[0622] 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".

[0623] In modern meetings, where many participants are increasingly joining remotely, ensuring efficient communication has become a challenging task. In particular, it's difficult to gauge participants' level of focus and emotional state in real time, which can lack the basis for optimizing meeting progress. Therefore, there is a need for new technologies that enable effective meeting management and improve participant engagement.

[0624] 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.

[0625] In this invention, the server includes information gathering means for receiving video and audio information of participants, analysis means for analyzing the facial features of participants, and analysis means for analyzing changes in participants' voices. This makes it possible to evaluate the progress of the meeting and the level of concentration of participants in real time and generate appropriate suggestions.

[0626] "Information gathering means" refers to devices or software used to acquire video and audio information of participants.

[0627] "Analysis means" refers to a device or software that has the function of analyzing the facial features and voice changes of participants based on the collected video and audio information.

[0628] "Generation means" refers to a device or software for generating suggestions to optimize the progress of a meeting based on the results obtained by the analysis means.

[0629] "Notification means" refers to a device or function for communicating the generated proposal to participants.

[0630] "Small group division" refers to a method or technique for conducting a meeting by dividing the participants into small groups.

[0631] A "proposal to re-evaluate agenda items" is a suggestion to reconfirm the agenda items during a meeting and reassess their importance.

[0632] One embodiment of this invention is a system for improving the efficiency of meetings. This system consists of a server, terminals, and users involved with them.

[0633] The server is assumed to be a group of computers operating in a cloud environment. First, the terminal acquires video and audio information from participants. Video information is captured by the camera, and audio information is captured by the microphone. The acquired raw data is sent from the terminal to the server.

[0634] The server uses several analysis tools to process the received data. For video data, a facial recognition API is used to analyze the facial features of participants. This analysis is performed to determine whether the user is smiling, surprised, or expressing other emotions. For audio data, an audio analysis tool is used to observe changes in tone, volume, and speed of the voice. Specifically, the characteristics of the audio waveform are captured to estimate whether the participant is speaking energetically or exhausted.

[0635] The analysis results are aggregated on the server and used to evaluate participants' real-time emotional states and levels of engagement. Based on the evaluation, the server generates suggestions to optimize the meeting. These suggestions may include starting breakout sessions or re-evaluating the agenda. The suggestions are notified to each user via their terminal, and users can take appropriate action based on the suggestions.

[0636] For example, if analysis reveals a decline in participant engagement during a meeting, the server proposes splitting into smaller groups and notifies the user. If the user accepts the proposal, the server automatically assigns participants to smaller groups and sets up appropriate virtual spaces.

[0637] The use of generative AI models is also being considered, and an example of a prompt message could be, "Please tell me how to measure the level of concentration from participants' facial expressions and voice, and create and notify me of suggestions to improve meeting efficiency." In this way, the system would support effective meeting management.

[0638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0639] Step 1:

[0640] The terminal acquires video data from users participating in the meeting via its camera and audio data via its microphone. The video is captured as an image stream, and the audio is captured as an audio waveform. This acquired data becomes the input. The terminal processes this input data in real time and sends it directly to the server.

[0641] Step 2:

[0642] The server inputs the video data received from the terminal into a video analysis tool. Specifically, it uses a face detection algorithm to identify facial regions from the video data and performs emotion analysis. For example, it identifies smiles, serious expressions, surprise, etc., and outputs an emotion score for each expression.

[0643] Step 3:

[0644] The server inputs the audio data received from the terminal into an audio analysis tool. The audio data is processed by an audio segmentation algorithm, which analyzes the tone, volume, and pitch of the voice. This outputs the audio characteristics necessary for estimating the user's emotional state and level of concentration.

[0645] Step 4:

[0646] The server aggregates the analysis results obtained in steps 2 and 3 and inputs them into the evaluation model. This model combines facial expression scores and voice characteristics to calculate an attention index for each participant. As a result, it outputs an evaluation of the overall progress of the meeting and emotional indicators of the participants.

[0647] Step 5:

[0648] The server generates suggestions to optimize the meeting based on the evaluation results. Using a generative model, it suggests breakout sessions if the level of engagement is low. It outputs the generated suggestions and generates corresponding recommendations.

[0649] Step 6:

[0650] The server distributes the generated proposals to each terminal using a notification system. Specifically, it creates a notification message containing the proposal content and implementation steps, and sends it to the user's terminal. This notification serves as the output, prompting the user to take action.

[0651] Step 7:

[0652] The user checks the notification received on their device and selects an action based on the suggestion. Once the user approves the suggestion, the device sends a notification to the server, which may automatically adjust the meeting settings. This feedback is treated as input and used for re-evaluation to optimize the overall meeting progress.

[0653] (Application Example 1)

[0654] 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".

[0655] To provide effective customer service in physical stores, it is essential to accurately understand the customer's situation and interests and to respond immediately to the most appropriate needs. However, conventional methods often make it difficult to grasp customer emotions and interests, resulting in uniform responses. This invention aims to solve these problems and improve customer satisfaction.

[0656] 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.

[0657] In this invention, the server includes an information gathering means for receiving participant information, an analysis means for analyzing the participant's facial expressions based on the video information acquired by the information gathering means, and an analysis means for analyzing the participant's voice tone based on the audio information acquired by the information gathering means. This makes it possible to grasp customer interests in real time within the store and make optimal customer service suggestions.

[0658] "Information gathering means" refers to technical devices used to acquire video and audio information of customers.

[0659] The "analysis means" is a processing device for analyzing the customer's facial expressions and voice tone based on acquired video and audio information.

[0660] An "evaluation tool" is a system for evaluating the progress within a store and the level of customer interest based on the results of analysis performed by an analysis tool.

[0661] A "proposal generation method" is a process for generating customer response measures based on the evaluation results of the evaluation method.

[0662] "Notification means" refers to the means of reliably communicating proposals generated by the proposal generation means to the staff.

[0663] "Customer service support tools" are devices and systems that assist customer service activities by suggesting optimal actions tailored to the customer's interests and circumstances.

[0664] The system realizing this invention provides means for collecting and analyzing customer video and audio information to optimize customer service. A server collects customer information in real time within the store using devices such as smart glasses or robots. This information is processed using a cloud computing platform.

[0665] Smart glasses and robots are equipped with high-resolution cameras and high-sensitivity microphones. This allows for detailed collection of customer facial expressions and voice tones. The server processes this data using video analysis tools such as OpenCV to analyze the customer's facial expressions. Simultaneously, the audio data is converted to text using the Google Cloud Speech-to-Text API, and its tone and content are analyzed.

[0666] The analysis results are used by an evaluation algorithm powered by Google Cloud AI to estimate the customer's interests and psychological state. Based on this evaluation, the server proposes the optimal customer response. The proposed response is notified to staff via smart glasses, or a robot directly approaches the customer.

[0667] As a concrete example, if a customer in a clothing store is having trouble choosing an item and their expression is uncertain, the system can directly ask the customer, "Do you need any assistance?" via a robot. Staff members receive a suggestion notification on their smart glasses and can provide support quickly. This allows customers to have a more personalized experience and improves the store's responsiveness.

[0668] An example of a prompt message is: "Please tell me about a system that analyzes customer facial expressions and voices to recognize customer emotions in real time and suggest the most appropriate customer service approach. In particular, please provide specific examples of customer service support utilizing real-time notifications via smart glasses."

[0669] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0670] Step 1:

[0671] The server acquires customer video and audio data in real time from smart glasses and robots. Input comes from high-resolution cameras and high-sensitivity microphones, which the server receives as a data stream. Output is digitized video and audio data. This information is stored in a cloud-based database.

[0672] Step 2:

[0673] The server processes the collected video data using OpenCV to analyze the customer's facial expressions. The input is the video data obtained in step 1, and the server performs face recognition and expression analysis on it. The output is the analysis result, for example, whether the customer is smiling or looking troubled. This analysis result serves as an indicator of the customer's emotional state.

[0674] Step 3:

[0675] The server converts the audio data into text using the Google Cloud Speech-to-Text API and analyzes the tone and content of the speech. The input is the audio data obtained in step 1, and the output is the transcribed speech content and its tone information. Based on this, the server determines whether the customer is excited or relaxed. This information is an important factor in estimating the customer's psychological state.

[0676] Step 4:

[0677] The server analyzes the results obtained in steps 2 and 3 using an evaluation algorithm to estimate the customer's interests and psychological state. The inputs are the facial expression analysis results and the voice analysis results, and the output is an evaluation of the customer's level of interest and psychological state. The server then identifies the customer's potential needs.

[0678] Step 5:

[0679] The server uses a generative AI model to suggest the optimal customer response based on the estimated customer state. The input is the evaluation result from step 4, and the output is a specific action suggestion. For example, if the customer is in trouble, a suggestion such as "Can I help you?" will be generated.

[0680] Step 6:

[0681] The server notifies staff wearing smart glasses or robots interacting with customers of the suggested actions. The input is the suggestion generated in step 5, and the output is the notified action suggestion. This allows store staff or robots to immediately take action and provide appropriate service to customers.

[0682] 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.

[0683] The present invention provides a virtual meeting room that incorporates an emotion engine to acquire video and audio information from participants and improve the efficiency of meetings. This system includes the following main functions:

[0684] First, the user (device) provides video and audio data by enabling the camera and microphone when joining a virtual meeting. This data is sent to the server in real time.

[0685] The server inputs the collected data into facial expression analysis tools and voice analysis tools to analyze the participants' facial features and voice tone. This allows the server to estimate the participants' instantaneous emotional state and level of concentration.

[0686] Furthermore, this system integrates an emotion engine that combines analyzed facial expression data and voice data to recognize participants' emotions with high accuracy. The emotion engine determines, for example, whether a participant is feeling happy or stressed.

[0687] These analysis results are aggregated by a server to evaluate the overall progress of the meeting and the level of participant engagement. Based on these results, suggestions for improving meeting efficiency are generated. The suggestion generation system can provide customized suggestions for each participant. For example, it can offer suggestions to help a nervous participant relax.

[0688] Finally, the server notifies each user (device) of the generated suggestions. The notification includes specific actions tailored to the participant's emotional state, enabling more effective engagement.

[0689] As a concrete example, if the server detects that a participant is stressed based on their facial expressions during a meeting, it will suggest a short break for relaxation and notify the user. If the user accepts the suggestion, the server will temporarily suspend the meeting and set a break period. This approach can improve the productivity of meetings.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The user (device) joins the virtual meeting and activates their camera and microphone. This allows video and audio data of the meeting participants to be captured.

[0693] Step 2:

[0694] The server receives video and audio data from each user in real time and converts it to the appropriate format. This data is then processed into the format necessary for analysis.

[0695] Step 3:

[0696] The server inputs video data into a facial expression analysis tool to analyze the facial features of the participants. This analysis captures subtle changes in facial expressions and identifies the emotional state of those expressions.

[0697] Step 4:

[0698] The server inputs audio data into a voice analysis tool, which analyzes the tone, volume, and speaking speed of the voice. This allows it to extract emotional indicators from the audio and infer the level of concentration and emotional state.

[0699] Step 5:

[0700] The server integrates the results of facial expression and voice analysis into an emotion engine to accurately recognize the participant's overall emotional state. The emotion engine evaluates a variety of emotions, such as stress, relaxation, and excitement.

[0701] Step 6:

[0702] Based on the recognized emotional states, the server generates suggestions tailored to the progress of the meeting and the emotions of the participants. For example, if participants appear stressed, suggestions for rest or relaxation may be considered.

[0703] Step 7:

[0704] The server notifies each user (device) of the generated suggestions. The notification includes the specific details of the suggested action.

[0705] Step 8:

[0706] The user reviews the notification from the server and chooses whether to take the suggested action. If the user follows the suggestion, the server takes action accordingly.

[0707] Step 9:

[0708] The server continues to perform analysis and monitor the progress of the meeting even after the proposal has been implemented. This helps maintain an optimal state in real time at all times.

[0709] (Example 2)

[0710] 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".

[0711] Traditional online meeting systems have problems such as difficulty in real-time monitoring of participants' emotional states and attention levels, and a lack of specific advice for optimizing meeting efficiency and participant engagement. As a result, there are challenges such as decreased participant concentration and insufficient meeting effectiveness.

[0712] 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.

[0713] In this invention, the server includes a device for receiving visual and auditory information from participants, means for analyzing the emotional state of participants based on the visual information acquired by the device, and means for analyzing the vocal characteristics of participants based on the auditory information acquired by the device. This makes it possible to accurately grasp the emotional state and attention level of participants and automatically generate and provide appropriate advice according to the progress of the meeting.

[0714] "Visual and auditory information" refers to video data showing participants' facial expressions and movements, and audio data showing what participants say and the tone of their voices.

[0715] "Device" refers to the hardware used to acquire participants' visual and auditory information and transmit it to the server.

[0716] "Methods for analyzing emotional states" refers to the process of analyzing participants' emotions from their facial expressions and actions to identify emotional states such as joy, surprise, and anger.

[0717] "Methods for analyzing vocal characteristics" refers to the process of analyzing vocal characteristics such as tone, intonation, and speed in participants' speech to estimate their emotions and state of attention.

[0718] An "algorithm" refers to a series of procedures or calculation methods that analyze changes in a participant's emotional state and voice characteristics, and estimate their emotion and attention level based on that combination.

[0719] The "advice generation function" refers to the ability to automatically create specific suggestions and instructions for optimizing a meeting, based on the participants' status and the progress of the meeting.

[0720] "Means of communication" refers to methods and techniques for notifying participants of the generated advice and encouraging them to take specific actions.

[0721] The system of this invention aims to improve the efficiency of virtual meetings by evaluating the emotional state and attention levels of participants in real time. When using the system, users participate in the meeting using a terminal. The terminal is equipped with a camera and microphone, which are used to collect visual and auditory information.

[0722] The server receives video and audio data transmitted from the terminal. The received data is analyzed using facial expression analysis tools (e.g., OpenCV or a common cloud API). This detects the facial feature points of the participants and estimates their emotional state. Additionally, audio analysis tools (e.g., a common cloud speech recognition API) are used to analyze the tone and intonation of the voice data and further estimate the emotional state.

[0723] The server integrates these analysis results into an emotion engine. This emotion engine uses a generative AI model to synthesize different data points to perform highly accurate emotion recognition. For example, it can determine whether a participant is stressed or relaxed.

[0724] Based on the results of the emotion engine, the server generates suggestions to optimize the meeting's progress. Specific examples of these suggestions might include suggestions to help participants relax or to suggest short breaks. These suggestions are delivered to each participant's device via notification from the server.

[0725] For example, if analysis indicates that a participant is experiencing stress during a meeting, the server will suggest to that participant, "Let's take a break to relax." This suggestion will be displayed on the participant's device screen, prompting them to take action regarding the meeting's progress.

[0726] An example of a prompt might be, "Analyze the emotional state of participants in real time and suggest appropriate break times." By using such prompts, the generative AI model can contribute to making meetings more efficient.

[0727] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0728] Step 1:

[0729] The user enables the camera and microphone on their device and joins the meeting. This action allows video and audio information to be acquired in real time. The device sends this data to the server. By receiving the user's video and audio information as input and sending it to the server, the system provides basic data for understanding the user's state during the meeting.

[0730] Step 2:

[0731] The server receives video information sent from the terminal. The received video data is input into a facial expression analysis tool. The server processes this data and estimates the user's emotional state from their facial expressions by analyzing facial feature points. As output, it generates emotional state data to send to the emotion engine.

[0732] Step 3:

[0733] The server receives audio information acquired from the terminal. Next, it inputs the received audio data into an audio analysis tool. The server analyzes the tone and intonation of the voice and further estimates the emotional state from the characteristics of the user's voice. As output, it generates audio feature data to be sent to the emotion engine.

[0734] Step 4:

[0735] The server integrates the analyzed facial expression and voice data into the emotion engine. Using a generative AI model, it analyzes this data to accurately recognize the user's overall emotional state. As output, it generates detailed emotion analysis data to evaluate the progress of the meeting and the user's level of concentration.

[0736] Step 5:

[0737] The server uses detailed sentiment analysis data from its emotion engine to generate suggestions for improving meeting efficiency. The suggestion generation process utilizes a generative AI model to create customized action suggestions for the user (e.g., suggestions for taking breaks). The output generates advice data containing specific suggestions.

[0738] Step 6:

[0739] The server transmits the generated advice data to the user. It displays a notification message on the terminal, allowing the user to respond to the suggestions immediately. By receiving the suggestions as input and directly engaging with the user, it enhances the productivity of meetings.

[0740] (Application Example 2)

[0741] 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".

[0742] In current virtual stores, there is a challenge in accurately understanding customers' real-time emotions and making appropriate product suggestions and guidance based on those emotions, thus failing to effectively increase purchasing intent. To capture customer interest and desire to buy, more accurate emotion analysis and dynamic, personalized suggestions based on those analyses are required.

[0743] 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.

[0744] In this invention, the server includes data collection means for receiving video and audio information of participants, facial expression analysis means for analyzing the participants' facial expressions based on the video information acquired by the data collection means, and voice analysis means for analyzing the tone of the participants' voices based on the audio information acquired by the data collection means. This enables highly accurate emotion analysis and personalized product recommendations to increase purchasing intent.

[0745] "Data collection means" refers to devices or functions that receive video and audio information of participants.

[0746] "Facial expression analysis means" refers to a device or function that analyzes a participant's facial expressions based on acquired video information and understands their characteristics.

[0747] "Voice analysis means" refers to a device or function that analyzes the tone of a participant's voice based on acquired voice information and understands its characteristics.

[0748] "Evaluation means" refers to devices or functions for estimating a participant's emotional state and level of concentration based on the analysis results of facial expression analysis means and voice analysis means.

[0749] "Proposal generation means" refers to a device or function that generates proposals to increase purchasing intent based on the results of the evaluation means.

[0750] "Notification means" refers to a device or function that notifies participants of proposals generated by the proposal generation means.

[0751] The system of this invention can accurately grasp the emotional state of individual customers by collecting and analyzing real-time video and audio information of participants in order to promote purchases in virtual stores. Specifically, the system is implemented as follows.

[0752] The server uses data collection methods to receive video and audio data from participants in real time from devices such as smart glasses. This data is analyzed by facial expression analysis methods, which use OpenCV and other tools to detect facial features and estimate emotions. The audio analysis method uses the Google Speech-to-Text API to analyze the tone of the voice and supplement the emotional state.

[0753] The terminal integrates these analysis results in the evaluation system and uses an evaluation algorithm to estimate the emotional state and level of concentration necessary to promote purchases by participants. The emotion engine can integrate facial expression data and voice data using Microsoft Azure's Emotion API, etc., to capture subtle emotional changes.

[0754] Based on the evaluation results, the suggestion generation system generates optimal product suggestions and attractive information presentations for the customer. Users receive suggestions in real time through the notification system, which can stimulate their purchasing intent.

[0755] As a concrete example, when a user is browsing fashion items in a virtual store, the system will display pop-up information suggesting new styles or sales information to customers who appear expressionless. An example of a prompt message would be, "Please use facial and voice analysis to determine the customer's emotional state in real time in order to display product information that will interest them."

[0756] This invention enriches the customer experience and effectively increases purchasing intent in virtual shopping. By understanding implicit customer needs, it enables more personalized approaches to customers.

[0757] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0758] Step 1:

[0759] The server receives video and audio information from the terminal in real time via data collection means. It acquires video data from the camera and audio data from the microphone as input, and processes them into a format suitable for subsequent analysis. The output becomes data usable by facial expression analysis means and audio analysis means.

[0760] Step 2:

[0761] The server processes the received video data using facial expression analysis. Using image processing libraries such as OpenCV, it extracts facial feature points from the input data and estimates emotions. This results in outputting data indicating the state of the participant's facial expression, such as whether they are smiling or expressionless.

[0762] Step 3:

[0763] The server processes the audio data using speech analysis tools. Using the Google Speech-to-Text API, it converts the given audio input into text, estimating the tone and emotion of the voice. The output provides tone information such as anger, joy, or calmness.

[0764] Step 4:

[0765] In the evaluation system, the server integrates the outputs of the facial expression analysis system and the voice analysis system, and uses a generative AI model to estimate the participant's emotional state and level of concentration with high accuracy. The input is the results of the two analyses mentioned above, and based on this data, the server quantifies the current emotional state and outputs it.

[0766] Step 5:

[0767] In the proposal generation system, the server generates optimal product suggestions based on the output of the evaluation system. It uses prompt messages to activate a generation AI model, creating personalized product and information suggestions tailored to each participant from the input data. The output consists of attractive suggestions tailored to each participant.

[0768] Step 6:

[0769] Using a notification system, users receive generated suggestions in real time. The input consists of individual suggestion information from the suggestion generation system, which is configured to be displayed on the user's screen. The output displays suggestions that enhance the participant's virtual experience.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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 as being incorporated by reference.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A data collection means for receiving video and audio information of participants,

[0794] A facial expression analysis means analyzes the facial expressions of participants based on the video information acquired by the aforementioned data collection means,

[0795] Based on the audio information acquired by the aforementioned data collection means, an audio analysis means analyzes the tone of the participant's voice,

[0796] Based on the analysis results of the facial expression analysis means and the voice analysis means, an evaluation means is provided to evaluate the progress of the meeting and the level of concentration of the participants.

[0797] A proposal generation means that generates proposals regarding the progress of the meeting based on the evaluation results of the aforementioned evaluation means,

[0798] A notification means for notifying participants of the proposals generated by the proposal generation means,

[0799] A system that includes this.

[0800] (Claim 2)

[0801] The system according to claim 1, wherein the proposal generation means includes proposals for breakout sessions or agenda organization for multiple participants.

[0802] (Claim 3)

[0803] The system according to claim 1, wherein the evaluation means includes an algorithm that analyzes the facial expressions and voice change patterns of the participants and estimates their emotions and level of concentration based on their combination.

[0804] "Example 1"

[0805] (Claim 1)

[0806] Information gathering means for receiving video and audio information of participants,

[0807] Based on the video information acquired by the aforementioned information gathering means, an analysis means analyzes the facial features of the participants,

[0808] Based on the audio information acquired by the aforementioned information gathering means, an analysis means analyzes changes in the participant's voice,

[0809] Based on the analysis results of the aforementioned analysis means, an analysis means is provided to evaluate the progress of the meeting and the level of concentration of the participants.

[0810] A generation means that generates proposals for optimizing the meeting based on the evaluation results of the analysis means,

[0811] A notification means for notifying participants of the proposals generated by the generation means,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the generating means includes proposing to multiple participants the division into small groups or proposing to re-evaluate the agenda.

[0815] (Claim 3)

[0816] The system according to claim 1, wherein the analysis means includes a method for analyzing the characteristics and voice change patterns of the participant and estimating the state and level of concentration based on the combination thereof.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] Information gathering means for receiving participant information,

[0820] Based on the video information acquired by the aforementioned information gathering means, an analysis means analyzes the facial expressions of the participants,

[0821] An analysis means for analyzing the tone of the participant's voice based on the audio information acquired by the aforementioned information gathering means,

[0822] A means for evaluating the progress of the group and the level of concentration of participants based on the analysis results of the aforementioned analysis means,

[0823] A proposal generation means that generates proposals regarding the progress of the group based on the evaluation results of the aforementioned evaluation means,

[0824] A notification means for individually notifying the proposals generated by the proposal generation means,

[0825] A customer service support tool that provides action suggestions to customers,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The customer service support means includes suggesting methods of responding based on customer interests, according to claim 1.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the evaluation means includes an algorithm that analyzes patterns of information change and estimates psychological state and concentration level based on combinations thereof.

[0831] "Example 2 of combining an emotion engine"

[0832] (Claim 1)

[0833] A device that receives visual and auditory information from participants,

[0834] A means for analyzing the emotional state of participants based on visual information acquired by the aforementioned device,

[0835] A means for analyzing the participant's voice characteristics based on auditory information acquired by the aforementioned device,

[0836] A method for evaluating the progress of a gathering and the level of attention of participants based on the analysis results of the aforementioned emotional states and vocal characteristics,

[0837] Based on the aforementioned evaluation results, a function is provided to generate advice regarding the progress of the meeting,

[0838] A means for communicating the generated advice to the participants,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the function includes proposing a group discussion or organizing the agenda for multiple participants.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the method includes an algorithm that analyzes changes in the emotional state and voice characteristics of a participant and estimates emotion and attention level based on a combination thereof.

[0844] "Application example 2 when combining with an emotional engine"

[0845] (Claim 1)

[0846] A data collection means for receiving video and audio information of participants,

[0847] A facial expression analysis means analyzes the facial expressions of participants based on the video information acquired by the aforementioned data collection means,

[0848] Based on the audio information acquired by the aforementioned data collection means, an audio analysis means analyzes the tone of the participant's voice,

[0849] Based on the analysis results of the facial expression analysis means and the voice analysis means, an evaluation means is provided to estimate the emotional state and concentration level of the participant.

[0850] Based on the evaluation results of the aforementioned evaluation means, a proposal generation means generates proposals that increase purchasing intent,

[0851] A notification means for notifying participants of the proposals generated by the proposal generation means,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the proposal generation means includes personalized product proposals or guiding proposals for multiple participants.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the evaluation means includes an algorithm that analyzes the facial expressions and voice change patterns of the participants and estimates an emotional state for promoting purchase based on their combination. [Explanation of Symbols]

[0857] 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 data collection means for receiving video and audio information of participants, A facial expression analysis means analyzes the facial expressions of participants based on the video information acquired by the aforementioned data collection means, Based on the audio information acquired by the aforementioned data collection means, an audio analysis means analyzes the tone of the participant's voice, Based on the analysis results of the facial expression analysis means and the voice analysis means, an evaluation means is provided to evaluate the progress of the meeting and the level of concentration of the participants. A proposal generation means that generates proposals regarding the progress of the meeting based on the evaluation results of the aforementioned evaluation means, A notification means for notifying participants of the proposals generated by the proposal generation means, A system that includes this.

2. The system according to claim 1, wherein the proposal generation means includes proposals for breakout sessions or proposals for organizing agenda items for multiple participants.

3. The system according to claim 1, wherein the evaluation means includes an algorithm that analyzes the facial expressions and voice change patterns of the participants and estimates their emotions and level of concentration based on their combination.

Images