System

Abstract

To provide a system according to an embodiment that reproduces a voice of a person or the deceased living far away, and provides a natural conversation experience.SOLUTION: A system according to an embodiment comprises: a collection unit; an analysis unit; and a lip synch unit. The collection unit is configured to collect a sample of a voice. The analysis unit is configured to analyze the sample of the voice collected by the collection unit. The lip synch unit is configured to synchronize a movement of a mouth with lines on the basis of data analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to reproduce the voices of people who were far away or who had passed away, and provide a natural conversation experience.

[0005] The system according to the embodiment aims to reproduce the voices of people who are far away or who have passed away, providing a natural conversation experience. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a lip sync unit. The collection unit collects voice samples. The analysis unit analyzes the voice samples collected by the collection unit. The lip sync unit synchronizes mouth movements and dialogue based on data analyzed by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can reproduce the voices of people who are far away or who have passed away, providing a natural conversation experience. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The AI ​​chatbot system according to the embodiment of the present invention is a system that collects voice samples of family members and people who are far away and difficult to meet, and models the way the person speaks using voice analysis technology. In this system, a voice collection device is installed in a room and voice samples are collected in daily life. The voice collection device is equipped with a face tracking function and can match the mouth movement and lines using lip sync technology. This provides an experience of talking to the deceased person as if they were the person themselves. For example, a voice collection device is installed in a room. This voice collection device has a function of collecting voice samples of family members and people who are far away in daily life. For example, when family members are talking, their voices are recorded and saved as data. This data is analyzed using voice analysis technology and used to model the way the person speaks. Next, the collected voice samples are analyzed using voice analysis technology. The voice analysis technology learns the person's speaking style and voice characteristics based on the collected voice data. For example, the pronunciation of specific words, speaking speed, intonation, etc. are analyzed to model the way the person speaks. This modeled data is incorporated into the AI ​​chatbot. Furthermore, the voice collecting device is equipped with a face tracking function, and lip sync technology can be used to match the mouth movement with the dialogue. For example, when the voice collecting device speaks, the mouth movement is adjusted to match the dialogue. This allows the user to have an experience as if they were talking to the person themselves. This mechanism can provide an experience of talking to family members or people who are far away and difficult to meet. For example, it can reproduce the voice of a deceased person and talk to that person. This allows the user to look back on memories with the deceased person and gain peace of mind. This allows the AI ​​chatbot system to provide the user with a natural conversation experience.

[0029] The AI ​​chatbot system according to the embodiment includes a collection unit, an analysis unit, and a lip sync unit. The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. The collection unit collects voice samples of family members and people who are far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes voice features using, for example, a voice analysis technology. Voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit learns the person's speaking style and voice features based on the collected voice data. For example, the pronunciation of a specific word, speaking speed, intonation, etc. are analyzed to model the person's speaking style. The lip sync unit matches the mouth movement and lines based on the data analyzed by the analysis unit. The lip sync unit matches the mouth movement and lines using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit adjusts the mouth movement to match the dialogue when the voice collection device speaks. This allows the AI ​​chatbot system to provide a natural conversation experience to the user. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the dialogue.

[0030] The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. Specifically, it is desirable that the microphone is highly sensitive and has a noise canceling function for reducing ambient noise. In the case of a smartphone, it is possible to collect higher quality voice samples by connecting an external microphone in addition to using a built-in microphone. The collection unit collects voice samples of family members and people far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. This makes it possible to capture the characteristics of the voices in natural conversations. Furthermore, the collection unit is also capable of collecting voice samples according to specific scenarios and situations. For example, by collecting voice samples in emotional changes or stressful situations, it is possible to analyze more diverse voice characteristics. The collected voice data is safely stored in cloud storage or local storage and is used for subsequent processing in the analysis unit. It is important for the collection unit to perform regular maintenance and calibration in order to maintain the quality of the voice data. This allows the collection unit to consistently provide high quality voice samples, improving overall system performance.

[0031] The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes the voice features using, for example, a voice analysis technology. Voice analysis technologies include, for example, spectrum analysis and acoustic models. Specifically, in spectrum analysis, a voice signal is decomposed into frequency components and the strength of each frequency component is analyzed. This makes it possible to extract features such as the tone, pitch, and formants of the voice. An acoustic model is used to capture temporal changes in voice, and a hidden Markov model (HMM) or a recurrent neural network (RNN) is generally used. The analysis unit learns the person's speaking style and voice features based on the collected voice data. For example, the pronunciation of a specific word, the speaking speed, intonation, etc. are analyzed to model the person's speaking style. Furthermore, the analysis unit uses a machine learning algorithm to learn patterns from the collected data and can perform high-precision analysis even on unknown voice data. For example, a voice recognition model using deep learning can be trained and the collected voice data can be used as an input to extract the speaker's features with high precision. The analyzer stores the analysis results in a database for access by the lip sync unit and other system components, allowing the analyzer to efficiently analyze the collected voice data and improve overall system performance.

[0032] The lip sync unit matches the mouth movement and the lines based on the data analyzed by the analysis unit. The lip sync unit matches the mouth movement and the lines using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and sensor-based tracking. Specifically, in camera-based tracking, a high-resolution camera is used to detect facial feature points in real time and accurately track the mouth movement. In sensor-based tracking, a depth sensor or an infrared sensor can be used to capture the face movement in 3D. The lip sync unit adjusts the mouth movement so that it matches the lines when the voice collection device speaks. This allows the AI ​​chatbot system to provide the user with a natural conversation experience. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the lines. The generation AI uses, for example, a model using deep learning, and generates optimal mouth movements using voice data and face movement data as input. This allows the lip sync unit to realize more natural and realistic mouth movements and provide users with a high-quality conversation experience. Furthermore, the lip sync unit can also handle different languages ​​and dialects, making it possible to provide a consistent quality of service to users around the world.

[0033] The collection unit can collect voice samples using a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. The collection unit collects voice samples using, for example, a voice collection device. For example, the collection unit records the voices of family members when they are talking and stores them as data. The collection unit can also collect voice samples of family members and people who are far away in daily life using the voice collection device. This makes it possible to efficiently collect voice samples by using the voice collection device. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data acquired by the voice collection device to a generation AI and cause the generation AI to analyze the voice data.

[0034] The analysis unit can analyze the voice characteristics using a voice analysis technology. The voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit analyzes the voice characteristics using, for example, a voice analysis technology. For example, the analysis unit learns the person's speaking style and voice characteristics based on collected voice data. For example, the pronunciation of a specific word, speaking speed, intonation, etc. are analyzed to model the person's speaking style. In this way, the voice analysis technology can be used to accurately analyze the voice characteristics. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collected voice data to a generation AI and cause the generation AI to perform an analysis of the voice characteristics.

[0035] The lip sync unit can use a face tracking function to match the mouth movement with the dialogue. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit can use, for example, a face tracking function to match the mouth movement with the dialogue. For example, the lip sync unit adjusts the mouth movement so that it matches the dialogue when the voice collection device speaks. In this way, natural lip sync can be achieved by using the face tracking function. A part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired by the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement with the dialogue.

[0036] The collection unit can collect voice samples of family members or people far away in daily life. The collection unit, for example, collects voice samples of family members or people far away in daily life. For example, the collection unit records the voices of family members when they are talking and stores them as data. The collection unit can also collect voice samples of family members or people far away in daily life using a voice collection device. In this way, natural voice data can be obtained by collecting voice samples in daily life. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data acquired in daily life to the generation AI and have the generation AI execute analysis of the voice data.

[0037] The analysis unit can learn the person's speaking style and voice characteristics based on the collected voice data. The analysis unit learns the person's speaking style and voice characteristics based on, for example, the collected voice data. For example, the analysis unit analyzes the pronunciation of specific words, speaking speed, intonation, etc., and models the person's speaking style. This makes it possible to reproduce a more accurate speaking style and voice characteristics by learning based on the voice data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collected voice data to the generation AI and cause the generation AI to learn the speaking style and voice characteristics.

[0038] The lip sync unit can adjust the mouth movement to match the lines when the voice collecting device speaks. For example, the lip sync unit adjusts the mouth movement to match the lines when the voice collecting device speaks. For example, the lip sync unit uses a face tracking function to match the mouth movement and the lines. This makes it possible to provide a more natural conversation experience by matching the mouth movement and the lines. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired by the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the lines.

[0039] The collection unit can filter specific environmental sounds and background sounds to collect clearer voice samples. The collection unit, for example, filters specific environmental sounds and background sounds to collect clearer voice samples. For example, when there is a lot of background sound, the collection unit uses noise canceling technology to collect clear voice samples. In addition, when the environmental sound has a certain pattern, the collection unit can learn the pattern and filter it. In addition, the collection unit can remove sounds in a specific frequency band to make the voice sample clear. In this way, a clear voice sample can be collected by filtering the environmental sound and background sound. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data of the environmental sound and background sound to the generation AI and cause the generation AI to perform filtering.

[0040] When collecting a voice sample, the collection unit can detect the activity status of the collection subject and select the optimal collection method. When collecting a voice sample, the collection unit can detect the activity status of the collection subject (e.g., during a conversation, during a break, etc.) and select the optimal collection method. For example, when the collection subject is talking, the collection unit collects a natural voice sample from the conversation. When the collection subject is resting, the collection unit can also collect a voice sample in a quiet environment. When the collection subject is exercising, the collection unit can also adjust the collection method taking into account the influence of exercise. This allows the voice sample to be efficiently collected by selecting the optimal collection method according to the activity status of the collection subject. A part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can input the activity status data of the collection subject to the generation AI and cause the generation AI to select the optimal collection method.

[0041] The collection unit can preferentially collect voice samples at a specific location based on the geographical location information of the collection target. The collection unit, for example, preferentially collects voice samples at a specific location based on the geographical location information of the collection target. For example, when the collection target is in a specific location, the collection unit preferentially collects voice samples at that location. In addition, when the collection target is moving, the collection unit can also collect voice samples at the moving destination. In addition, when the collection target is participating in a specific event, the collection unit can also collect voice samples during the event. In this way, by taking the geographical location information into consideration, voice samples at a specific location can be efficiently collected. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information data of the collection target to the generation AI and cause the generation AI to perform preferential collection of voice samples.

[0042] The collection unit can analyze the social media activity of the collection target person and collect related voice samples. The collection unit, for example, analyzes the social media activity of the collection target person and collects related voice samples. For example, the collection unit collects voices transmitted by the collection target person during social media activities. The collection unit can also collect voices transmitted by the collection target person during live streaming on social media. The collection unit can also collect voice messages on social media by the collection target person. This makes it possible to efficiently collect related voice samples by analyzing social media activities. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the social media activity data of the collection target person to the generation AI and cause the generation AI to collect related voice samples.

[0043] The analysis unit can evaluate the sound quality and noise level of the voice sample and select the optimal analysis algorithm. The analysis unit, for example, evaluates the sound quality and noise level of the voice sample and selects the optimal analysis algorithm. For example, when the sound quality is high, the analysis unit applies a detailed analysis algorithm. Furthermore, when the noise level is high, the analysis unit can also perform analysis by applying noise reduction technology. Furthermore, the analysis unit can select the optimal analysis algorithm according to the sound quality and noise level. As a result, the accuracy of the analysis is improved by selecting the optimal analysis algorithm according to the sound quality and noise level. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input sound quality and noise level data of the voice sample to the generation AI and cause the generation AI to select the optimal analysis algorithm.

[0044] The analysis unit can automatically identify the language or dialect of the voice sample and apply an analysis method according to the language or dialect. The analysis unit can automatically identify the language or dialect of the voice sample and apply an analysis method according to the language or dialect. For example, the analysis unit can automatically identify the language of the voice sample and apply an analysis method suitable for the language. The analysis unit can also automatically identify the dialect of the voice sample and apply an analysis method suitable for the dialect. In addition, when multiple languages ​​or dialects are included, the analysis unit can also apply an analysis method suitable for each of them. As a result, the accuracy of the analysis is improved by applying an analysis method according to the language or dialect. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input language or dialect data of the voice sample to the generation AI and cause the generation AI to apply an appropriate analysis method.

[0045] The analysis unit can determine the priority of the analysis based on the submission time of the collected voice sample. The analysis unit determines the priority of the analysis based on, for example, the submission time of the collected voice sample. For example, if the collected voice sample is new, the analysis unit performs the analysis preferentially. Also, if the collected voice sample is old, the analysis unit can perform the analysis later. Also, the analysis unit can dynamically adjust the priority of the analysis based on the submission time. As a result, the analysis can be performed efficiently by determining the priority of the analysis based on the submission time. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission time data of the collected voice sample to the generation AI and cause the generation AI to execute the determination of the analysis priority.

[0046] The analysis unit can improve the accuracy of the analysis by referring to related literature of the collected voice samples. The analysis unit can improve the accuracy of the analysis by referring to related literature of the collected voice samples, for example. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the collected voice samples. The analysis unit can also improve the analysis algorithm based on knowledge obtained from the related literature. The analysis unit can also compare the collected voice samples with the related literature and verify the analysis results. As a result, the accuracy of the analysis is improved by referring to the related literature. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input related literature data of the collected voice samples to the generation AI and cause the generation AI to perform improvement of the accuracy of the analysis.

[0047] The lip sync unit can analyze the facial features of the collection target in detail and reproduce more natural mouth movements. The lip sync unit can, for example, analyze the facial features of the collection target in detail and perform lip sync based on the features. For example, the lip sync unit can analyze the facial movements of the collection target in real time and reproduce natural mouth movements. The lip sync unit can also learn the facial features of the collection target and improve the accuracy of lip sync. As a result, more natural mouth movements can be reproduced by analyzing the facial features of the collection target in detail. A part or all of the above-mentioned processing in the lip sync unit can be performed using, for example, AI or without AI. For example, the lip sync unit can input facial feature data of the collection target to the generation AI and cause the generation AI to reproduce natural mouth movements.

[0048] The lip sync unit can detect facial expression changes of the collection subject in real time and adjust the mouth movement accordingly. The lip sync unit can, for example, detect facial expression changes of the collection subject in real time and adjust the mouth movement according to the changes. For example, the lip sync unit learns facial expression changes of the collection subject and improves the accuracy of lip sync. The lip sync unit can also analyze facial expression changes of the collection subject and reproduce natural mouth movement. As a result, more natural lip sync can be realized by detecting facial expression changes in real time. A part or all of the above-mentioned processing in the lip sync unit may be performed using, for example, AI, or may be performed without using AI. For example, the lip sync unit can input facial expression change data of the collection subject to the generation AI and cause the generation AI to adjust the mouth movement.

[0049] The lip sync unit can improve the accuracy of lip sync at a specific location by taking into account the geographical location information of the collection target. The lip sync unit can improve the accuracy of lip sync at a specific location by taking into account, for example, the geographical location information of the collection target. For example, when the collection target is in a specific location, the lip sync unit can improve the accuracy of lip sync at that location. In addition, when the collection target is moving, the lip sync unit can also improve the accuracy of lip sync at the destination. In addition, when the collection target is participating in a specific event, the lip sync unit can also improve the accuracy of lip sync during the event. In this way, by taking into account the geographical location information, the accuracy of lip sync at a specific location can be improved. Part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI, or may be performed without using AI. For example, the lip sync unit can input the geographical location information data of the collection target to the generation AI and cause the generation AI to improve the accuracy of lip sync.

[0050] The lip sync unit can analyze the social media activity of the collection subject and reproduce the related facial expressions and mouth movements. The lip sync unit, for example, analyzes the social media activity of the collection subject and reproduces the related facial expressions and mouth movements. For example, the lip sync unit reproduces the facial expressions and mouth movements transmitted by the collection subject during social media activities. The lip sync unit can also reproduce the facial expressions and mouth movements transmitted by the collection subject during live streaming on social media. The lip sync unit can also reproduce the voice messages on social media by the collection subject. In this way, by analyzing social media activities, the related facial expressions and mouth movements can be reproduced. A part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI, or may be performed without using AI. For example, the lip sync unit can input the social media activity data of the collection subject to the generation AI and cause the generation AI to reproduce the facial expressions and mouth movements.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] When collecting a voice sample of a collection subject, the collection unit can monitor the health condition of the collection subject and adjust the collection method according to the health condition. For example, if the collection subject has a cold, the collection unit can reduce the frequency of collection and try collection again after the health condition has recovered. Also, if the collection subject is tired, the collection unit can adjust the collection timing and collect after resting. Furthermore, if the collection subject is feeling stressed, the collection unit can prioritize collection when the collection subject is in a relaxed state. This makes it possible to collect samples while taking into consideration the health condition of the collection subject.

[0053] The lip sync unit can reproduce not only the mouth movements of the collection subject but also the entire facial expression based on the voice sample of the collection subject. For example, if the collection subject is smiling, the lip sync unit reproduces the smile along with the mouth movements. If the collection subject is surprised, the lip sync unit can also reproduce a surprised facial expression. Furthermore, if the collection subject is sad, the lip sync unit can also reproduce a sad facial expression. This allows for more natural and emotional lip sync.

[0054] When collecting a voice sample of a collection subject, the collection unit can adjust the collection timing taking into account the activity history of the collection subject. For example, if the collection subject is tired after exercise, the collection unit can collect after the collection subject has rested. Also, if the collection subject is at work, the collection unit can collect after the collection subject has finished work. Furthermore, if the collection subject is traveling, the collection unit can attempt to collect at the travel destination. This makes it possible to provide an appropriate collection timing according to the activity history of the collection subject.

[0055] The lip sync unit can reproduce not only the mouth movements of the collection subject, but also gestures and body movements based on a sample of the collection subject's voice. For example, if the collection subject moves his / her hands when speaking, the lip sync unit reproduces the gestures. Also, if the collection subject moves his / her body, the lip sync unit can reproduce the movement. Furthermore, if the collection subject makes a specific movement when making a particular expression, the lip sync unit can reproduce the movement. This makes it possible to provide a more natural and realistic conversation experience.

[0056] When collecting a voice sample of the collection subject, the collection unit can analyze the environmental sounds around the collection subject and adjust the collection method according to the environmental sounds. For example, if the collection subject is in a noisy place, the collection unit can collect a clear voice sample using noise canceling technology. Also, if the collection subject is in a quiet place, the collection unit can collect a detailed voice sample using a highly sensitive microphone. Furthermore, if the collection subject is outdoors, the collection unit can also perform collection using technology to remove wind noise. This makes it possible to provide an appropriate collection method according to the surrounding environmental sounds.

[0057] The lip sync unit can reproduce not only the mouth movements of the collection subject, but also the eye and eyebrow movements based on a sample of the collection subject's voice. For example, if the collection subject opens his or her eyes when speaking, the lip sync unit reproduces the eye movements. Also, if the collection subject raises his or her eyebrows when expressing surprise, the lip sync unit can also reproduce the eyebrow movements. Furthermore, if the collection subject lowers the corners of their eyes when laughing, the lip sync unit can also reproduce the eye movements. This makes it possible to achieve more natural and expressive lip sync.

[0058] The process flow of the first embodiment will be briefly described below.

[0059] Step 1: The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone or a smartphone. The collection unit collects voice samples of family members and people who are far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. Step 2: The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes the voice characteristics using, for example, voice analysis technology. Voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit learns the person's speaking style and voice characteristics based on the collected voice data. For example, the analysis unit analyzes the pronunciation of specific words, speaking speed, intonation, etc., and models the person's speaking style. Step 3: The lip sync unit aligns the mouth movement and the dialogue based on the data analyzed by the analysis unit. The lip sync unit aligns the mouth movement and the dialogue using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit adjusts the mouth movement to match the dialogue when the voice collection device speaks. This allows the AI ​​chatbot system to provide a natural conversation experience to the user. Some or all of the above-mentioned processing in the lip sync unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the dialogue.

[0060] (Example 2) The AI ​​chatbot system according to the embodiment of the present invention is a system that collects voice samples of family members and people who are far away and difficult to meet, and models the way the person speaks using voice analysis technology. In this system, a voice collection device is installed in a room and voice samples are collected in daily life. The voice collection device is equipped with a face tracking function and can match the mouth movement and lines using lip sync technology. This provides an experience of talking to the deceased person as if they were the person themselves. For example, a voice collection device is installed in a room. This voice collection device has a function of collecting voice samples of family members and people who are far away in daily life. For example, when family members are talking, their voices are recorded and saved as data. This data is analyzed using voice analysis technology and used to model the way the person speaks. Next, the collected voice samples are analyzed using voice analysis technology. The voice analysis technology learns the person's speaking style and voice characteristics based on the collected voice data. For example, the pronunciation of specific words, speaking speed, intonation, etc. are analyzed to model the way the person speaks. This modeled data is incorporated into the AI ​​chatbot. Furthermore, the voice collecting device is equipped with a face tracking function, and lip sync technology can be used to match the mouth movement with the dialogue. For example, when the voice collecting device speaks, the mouth movement is adjusted to match the dialogue. This allows the user to have an experience as if they were talking to the person themselves. This mechanism can provide an experience of talking to family members or people who are far away and difficult to meet. For example, it can reproduce the voice of a deceased person and talk to that person. This allows the user to look back on memories with the deceased person and gain peace of mind. This allows the AI ​​chatbot system to provide the user with a natural conversation experience.

[0061] The AI ​​chatbot system according to the embodiment includes a collection unit, an analysis unit, and a lip sync unit. The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. The collection unit collects voice samples of family members and people who are far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes voice features using, for example, a voice analysis technology. Voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit learns the person's speaking style and voice features based on the collected voice data. For example, the pronunciation of a specific word, speaking speed, intonation, etc. are analyzed to model the person's speaking style. The lip sync unit matches the mouth movement and lines based on the data analyzed by the analysis unit. The lip sync unit matches the mouth movement and lines using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit adjusts the mouth movement to match the dialogue when the voice collection device speaks. This allows the AI ​​chatbot system to provide a natural conversation experience to the user. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the dialogue.

[0062] The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. Specifically, it is desirable that the microphone is highly sensitive and has a noise canceling function for reducing ambient noise. In the case of a smartphone, it is possible to collect higher quality voice samples by connecting an external microphone in addition to using a built-in microphone. The collection unit collects voice samples of family members and people far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. This makes it possible to capture the characteristics of the voices in natural conversations. Furthermore, the collection unit is also capable of collecting voice samples according to specific scenarios and situations. For example, by collecting voice samples in emotional changes or stressful situations, it is possible to analyze more diverse voice characteristics. The collected voice data is safely stored in cloud storage or local storage and is used for subsequent processing in the analysis unit. It is important for the collection unit to perform regular maintenance and calibration in order to maintain the quality of the voice data. This allows the collection unit to consistently provide high quality voice samples, improving overall system performance.

[0063] The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes the voice features using, for example, a voice analysis technology. Voice analysis technologies include, for example, spectrum analysis and acoustic models. Specifically, in spectrum analysis, a voice signal is decomposed into frequency components and the strength of each frequency component is analyzed. This makes it possible to extract features such as the tone, pitch, and formants of the voice. An acoustic model is used to capture temporal changes in voice, and a hidden Markov model (HMM) or a recurrent neural network (RNN) is generally used. The analysis unit learns the person's speaking style and voice features based on the collected voice data. For example, the pronunciation of a specific word, the speaking speed, intonation, etc. are analyzed to model the person's speaking style. Furthermore, the analysis unit uses a machine learning algorithm to learn patterns from the collected data and can perform high-precision analysis even on unknown voice data. For example, a voice recognition model using deep learning can be trained and the collected voice data can be used as an input to extract the speaker's features with high precision. The analyzer stores the analysis results in a database for access by the lip sync unit and other system components, allowing the analyzer to efficiently analyze the collected voice data and improve overall system performance.

[0064] The lip sync unit matches the mouth movement and the lines based on the data analyzed by the analysis unit. The lip sync unit matches the mouth movement and the lines using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and sensor-based tracking. Specifically, in camera-based tracking, a high-resolution camera is used to detect facial feature points in real time and accurately track the mouth movement. In sensor-based tracking, a depth sensor or an infrared sensor can be used to capture the face movement in 3D. The lip sync unit adjusts the mouth movement so that it matches the lines when the voice collection device speaks. This allows the AI ​​chatbot system to provide the user with a natural conversation experience. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the lines. The generation AI uses, for example, a model using deep learning, and generates optimal mouth movements using voice data and face movement data as input. This allows the lip sync unit to realize more natural and realistic mouth movements and provide users with a high-quality conversation experience. Furthermore, the lip sync unit can also handle different languages ​​and dialects, making it possible to provide a consistent quality of service to users around the world.

[0065] The collection unit can collect voice samples using a voice collection device. The voice collection device includes, for example, a microphone and a smartphone. The collection unit collects voice samples using, for example, a voice collection device. For example, the collection unit records the voices of family members when they are talking and stores them as data. The collection unit can also collect voice samples of family members and people who are far away in daily life using the voice collection device. This makes it possible to efficiently collect voice samples by using the voice collection device. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data acquired by the voice collection device to a generation AI and cause the generation AI to analyze the voice data.

[0066] The analysis unit can analyze the voice characteristics using a voice analysis technology. The voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit analyzes the voice characteristics using, for example, a voice analysis technology. For example, the analysis unit learns the person's speaking style and voice characteristics based on collected voice data. For example, the pronunciation of a specific word, speaking speed, intonation, etc. are analyzed to model the person's speaking style. In this way, the voice analysis technology can be used to accurately analyze the voice characteristics. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collected voice data to a generation AI and cause the generation AI to perform an analysis of the voice characteristics.

[0067] The lip sync unit can use a face tracking function to match the mouth movement with the dialogue. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit can use, for example, a face tracking function to match the mouth movement with the dialogue. For example, the lip sync unit adjusts the mouth movement so that it matches the dialogue when the voice collection device speaks. In this way, natural lip sync can be achieved by using the face tracking function. A part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired by the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement with the dialogue.

[0068] The collection unit can collect voice samples of family members or people far away in daily life. The collection unit, for example, collects voice samples of family members or people far away in daily life. For example, the collection unit records the voices of family members when they are talking and stores them as data. The collection unit can also collect voice samples of family members or people far away in daily life using a voice collection device. In this way, natural voice data can be obtained by collecting voice samples in daily life. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data acquired in daily life to the generation AI and have the generation AI execute analysis of the voice data.

[0069] The analysis unit can learn the person's speaking style and voice characteristics based on the collected voice data. The analysis unit learns the person's speaking style and voice characteristics based on, for example, the collected voice data. For example, the analysis unit analyzes the pronunciation of specific words, speaking speed, intonation, etc., and models the person's speaking style. This makes it possible to reproduce a more accurate speaking style and voice characteristics by learning based on the voice data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the collected voice data to the generation AI and cause the generation AI to learn the speaking style and voice characteristics.

[0070] The lip sync unit can adjust the mouth movement to match the lines when the voice collecting device speaks. For example, the lip sync unit adjusts the mouth movement to match the lines when the voice collecting device speaks. For example, the lip sync unit uses a face tracking function to match the mouth movement and the lines. This makes it possible to provide a more natural conversation experience by matching the mouth movement and the lines. Some or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI or may be performed without using AI. For example, the lip sync unit can input data acquired by the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the lines.

[0071] The collection unit can estimate the user's emotion and adjust the collection timing of the voice sample based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the collection timing of the voice sample based on the estimated user's emotion. For example, when the user is relaxed, the collection unit collects voice samples in a natural conversation. Also, when the user is feeling stressed, the collection unit can avoid the collection timing and try collection again in a relaxed state. Also, when the user is in an emotional moment, the collection unit can preferentially collect voice samples that reflect the emotion. In this way, by adjusting the collection timing according to the user's emotion, more natural voice samples can be collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the collection timing.

[0072] The collection unit can filter specific environmental sounds and background sounds to collect clearer voice samples. The collection unit, for example, filters specific environmental sounds and background sounds to collect clearer voice samples. For example, when there is a lot of background sound, the collection unit uses noise canceling technology to collect clear voice samples. In addition, when the environmental sound has a certain pattern, the collection unit can learn the pattern and filter it. In addition, the collection unit can remove sounds in a specific frequency band to make the voice sample clear. In this way, a clear voice sample can be collected by filtering the environmental sound and background sound. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data of the environmental sound and background sound to the generation AI and cause the generation AI to perform filtering.

[0073] When collecting a voice sample, the collection unit can detect the activity status of the collection subject and select the optimal collection method. When collecting a voice sample, the collection unit can detect the activity status of the collection subject (e.g., during a conversation, during a break, etc.) and select the optimal collection method. For example, when the collection subject is talking, the collection unit collects a natural voice sample from the conversation. When the collection subject is resting, the collection unit can also collect a voice sample in a quiet environment. When the collection subject is exercising, the collection unit can also adjust the collection method taking into account the influence of exercise. This allows the voice sample to be efficiently collected by selecting the optimal collection method according to the activity status of the collection subject. A part or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can input the activity status data of the collection subject to the generation AI and cause the generation AI to select the optimal collection method.

[0074] The collection unit can estimate the user's emotion and determine the priority of the voice samples to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority of the voice samples to be collected based on the estimated user's emotion. For example, when the user is in an emotional moment, the collection unit preferentially collects voice samples that reflect the emotion. In addition, when the user is relaxed, the collection unit can also collect voice samples in natural conversation. In addition, when the user is feeling stressed, the collection unit can avoid the collection timing and try to collect again in a relaxed state. In this way, by determining the priority of the voice samples according to the user's emotion, important samples can be preferentially collected. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input user emotion data to the generation AI and have the generation AI determine the priority of voice samples.

[0075] The collection unit can preferentially collect voice samples at a specific location based on the geographical location information of the collection target. The collection unit, for example, preferentially collects voice samples at a specific location based on the geographical location information of the collection target. For example, when the collection target is in a specific location, the collection unit preferentially collects voice samples at that location. In addition, when the collection target is moving, the collection unit can also collect voice samples at the moving destination. In addition, when the collection target is participating in a specific event, the collection unit can also collect voice samples during the event. In this way, by taking the geographical location information into consideration, voice samples at a specific location can be efficiently collected. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information data of the collection target to the generation AI and cause the generation AI to perform preferential collection of voice samples.

[0076] The collection unit can analyze the social media activity of the collection target person and collect related voice samples. The collection unit, for example, analyzes the social media activity of the collection target person and collects related voice samples. For example, the collection unit collects voices transmitted by the collection target person during social media activities. The collection unit can also collect voices transmitted by the collection target person during live streaming on social media. The collection unit can also collect voice messages on social media by the collection target person. This makes it possible to efficiently collect related voice samples by analyzing social media activities. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the social media activity data of the collection target person to the generation AI and cause the generation AI to collect related voice samples.

[0077] The analysis unit can estimate the user's emotion and adjust the accuracy of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the accuracy of the analysis based on the estimated user's emotion. For example, when the user is relaxed, the analysis unit performs a detailed analysis to improve the accuracy. In addition, when the user is in a hurry, the analysis unit can also perform a quick analysis to provide the result quickly. In addition, when the user is in an emotional moment, the analysis unit can perform an analysis that reflects the emotion. In this way, by adjusting the accuracy of the analysis according to the user's emotion, a more accurate analysis result can be obtained. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the accuracy of the analysis.

[0078] The analysis unit can evaluate the sound quality and noise level of the voice sample and select the optimal analysis algorithm. The analysis unit, for example, evaluates the sound quality and noise level of the voice sample and selects the optimal analysis algorithm. For example, when the sound quality is high, the analysis unit applies a detailed analysis algorithm. Furthermore, when the noise level is high, the analysis unit can also perform analysis by applying noise reduction technology. Furthermore, the analysis unit can select the optimal analysis algorithm according to the sound quality and noise level. As a result, the accuracy of the analysis is improved by selecting the optimal analysis algorithm according to the sound quality and noise level. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input sound quality and noise level data of the voice sample to the generation AI and cause the generation AI to select the optimal analysis algorithm.

[0079] The analysis unit can automatically identify the language or dialect of the voice sample and apply an analysis method according to the language or dialect. The analysis unit can automatically identify the language or dialect of the voice sample and apply an analysis method according to the language or dialect. For example, the analysis unit can automatically identify the language of the voice sample and apply an analysis method suitable for the language. The analysis unit can also automatically identify the dialect of the voice sample and apply an analysis method suitable for the dialect. In addition, when multiple languages ​​or dialects are included, the analysis unit can also apply an analysis method suitable for each of them. As a result, the accuracy of the analysis is improved by applying an analysis method according to the language or dialect. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input language or dialect data of the voice sample to the generation AI and cause the generation AI to apply an appropriate analysis method.

[0080] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis result based on the estimated user's emotion. For example, the analysis unit displays detailed analysis results when the user is relaxed. The analysis unit can also display concise analysis results when the user is in a hurry. The analysis unit can also display analysis results reflecting the emotion when the user is in an emotional moment. This makes it possible to provide results that are easy for the user to understand by adjusting the display method of the analysis result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the analysis result.

[0081] The analysis unit can determine the priority of the analysis based on the submission time of the collected voice sample. The analysis unit determines the priority of the analysis based on, for example, the submission time of the collected voice sample. For example, if the collected voice sample is new, the analysis unit performs the analysis preferentially. Also, if the collected voice sample is old, the analysis unit can perform the analysis later. Also, the analysis unit can dynamically adjust the priority of the analysis based on the submission time. As a result, the analysis can be performed efficiently by determining the priority of the analysis based on the submission time. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission time data of the collected voice sample to the generation AI and cause the generation AI to execute the determination of the analysis priority.

[0082] The analysis unit can improve the accuracy of the analysis by referring to related literature of the collected voice samples. The analysis unit can improve the accuracy of the analysis by referring to related literature of the collected voice samples, for example. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the collected voice samples. The analysis unit can also improve the analysis algorithm based on knowledge obtained from the related literature. The analysis unit can also compare the collected voice samples with the related literature and verify the analysis results. As a result, the accuracy of the analysis is improved by referring to the related literature. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input related literature data of the collected voice samples to the generation AI and cause the generation AI to perform improvement of the accuracy of the analysis.

[0083] The lip sync unit can estimate the user's emotion and adjust the accuracy of lip sync based on the estimated user's emotion. The lip sync unit, for example, estimates the user's emotion and adjusts the accuracy of lip sync based on the estimated user's emotion. For example, when the user is relaxed, the lip sync unit performs detailed lip sync to increase accuracy. Also, when the user is in a hurry, the lip sync unit can perform quick lip sync to provide the result quickly. Also, when the user is in an emotional moment, the lip sync unit can perform lip sync reflecting the emotion. In this way, more natural lip sync can be realized by adjusting the accuracy of lip sync according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the lip sync unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the lip sync unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the accuracy of lip sync.

[0084] The lip sync unit can analyze the facial features of the collection target in detail and reproduce more natural mouth movements. The lip sync unit can, for example, analyze the facial features of the collection target in detail and perform lip sync based on the features. For example, the lip sync unit can analyze the facial movements of the collection target in real time and reproduce natural mouth movements. The lip sync unit can also learn the facial features of the collection target and improve the accuracy of lip sync. As a result, more natural mouth movements can be reproduced by analyzing the facial features of the collection target in detail. A part or all of the above-mentioned processing in the lip sync unit can be performed using, for example, AI or without AI. For example, the lip sync unit can input facial feature data of the collection target to the generation AI and cause the generation AI to reproduce natural mouth movements.

[0085] The lip sync unit can detect facial expression changes of the collection subject in real time and adjust the mouth movement accordingly. The lip sync unit can, for example, detect facial expression changes of the collection subject in real time and adjust the mouth movement according to the changes. For example, the lip sync unit learns facial expression changes of the collection subject and improves the accuracy of lip sync. The lip sync unit can also analyze facial expression changes of the collection subject and reproduce natural mouth movement. As a result, more natural lip sync can be realized by detecting facial expression changes in real time. A part or all of the above-mentioned processing in the lip sync unit may be performed using, for example, AI, or may be performed without using AI. For example, the lip sync unit can input facial expression change data of the collection subject to the generation AI and cause the generation AI to adjust the mouth movement.

[0086] The lip sync unit can estimate the user's emotion and adjust the display method of the lip sync based on the estimated user's emotion. The lip sync unit, for example, estimates the user's emotion and adjusts the display method of the lip sync based on the estimated user's emotion. For example, the lip sync unit displays detailed lip sync when the user is relaxed. The lip sync unit can also display concise lip sync when the user is in a hurry. The lip sync unit can also display lip sync reflecting the emotion when the user is in an emotional moment. This allows for more appropriate display by adjusting the display method of the lip sync according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the lip sync unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the lip sync unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the lip sync.

[0087] The lip sync unit can improve the accuracy of lip sync at a specific location by taking into account the geographical location information of the collection target. The lip sync unit can improve the accuracy of lip sync at a specific location by taking into account, for example, the geographical location information of the collection target. For example, when the collection target is in a specific location, the lip sync unit can improve the accuracy of lip sync at that location. In addition, when the collection target is moving, the lip sync unit can also improve the accuracy of lip sync at the destination. In addition, when the collection target is participating in a specific event, the lip sync unit can also improve the accuracy of lip sync during the event. In this way, by taking into account the geographical location information, the accuracy of lip sync at a specific location can be improved. Part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI, or may be performed without using AI. For example, the lip sync unit can input the geographical location information data of the collection target to the generation AI and cause the generation AI to improve the accuracy of lip sync.

[0088] The lip sync unit can analyze the social media activity of the collection subject and reproduce the related facial expressions and mouth movements. The lip sync unit, for example, analyzes the social media activity of the collection subject and reproduces the related facial expressions and mouth movements. For example, the lip sync unit reproduces the facial expressions and mouth movements transmitted by the collection subject during social media activities. The lip sync unit can also reproduce the facial expressions and mouth movements transmitted by the collection subject during live streaming on social media. The lip sync unit can also reproduce the voice messages on social media by the collection subject. In this way, by analyzing social media activities, the related facial expressions and mouth movements can be reproduced. A part or all of the above-mentioned processing in the lip sync unit may be performed, for example, using AI, or may be performed without using AI. For example, the lip sync unit can input the social media activity data of the collection subject to the generation AI and cause the generation AI to reproduce the facial expressions and mouth movements.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The analysis unit can estimate the user's emotion based on the collected voice samples and adjust the tone of the conversation based on the estimated emotion. For example, if the user is sad, the analysis unit can generate a response in a gentle tone. If the user is excited, the analysis unit can generate a response in an energetic tone. Furthermore, if the user is relaxed, the analysis unit can generate a response in a calm tone. This makes it possible to provide an appropriate conversation experience according to the user's emotion.

[0091] When collecting a voice sample of a collection subject, the collection unit can monitor the health condition of the collection subject and adjust the collection method according to the health condition. For example, if the collection subject has a cold, the collection unit can reduce the frequency of collection and try collection again after the health condition has recovered. Also, if the collection subject is tired, the collection unit can adjust the collection timing and collect after resting. Furthermore, if the collection subject is feeling stressed, the collection unit can prioritize collection when the collection subject is in a relaxed state. This makes it possible to collect samples while taking into consideration the health condition of the collection subject.

[0092] The analysis unit can estimate the user's emotions based on the collected voice samples and adjust the content of the conversation based on the estimated emotions. For example, if the user is sad, the analysis unit can generate a response including words of comfort. If the user is happy, the analysis unit can also generate a response including words of congratulations. Furthermore, if the user is angry, the analysis unit can also generate a response that encourages a calm response. This makes it possible to provide appropriate conversation content according to the user's emotions.

[0093] The lip sync unit can reproduce not only the mouth movements of the collection subject but also the entire facial expression based on the voice sample of the collection subject. For example, if the collection subject is smiling, the lip sync unit reproduces the smile along with the mouth movements. If the collection subject is surprised, the lip sync unit can also reproduce a surprised facial expression. Furthermore, if the collection subject is sad, the lip sync unit can also reproduce a sad facial expression. This allows for more natural and emotional lip sync.

[0094] When collecting a voice sample of a collection subject, the collection unit can adjust the collection timing taking into account the activity history of the collection subject. For example, if the collection subject is tired after exercise, the collection unit can collect after the collection subject has rested. Also, if the collection subject is at work, the collection unit can collect after the collection subject has finished work. Furthermore, if the collection subject is traveling, the collection unit can attempt to collect at the travel destination. This makes it possible to provide an appropriate collection timing according to the activity history of the collection subject.

[0095] The analysis unit can estimate the user's emotions based on the collected voice samples, and adjust the conversation speed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can advance the conversation at a slower speed. Also, if the user is in a hurry, the analysis unit can advance the conversation at a faster speed. Furthermore, if the user is in an emotional moment, the analysis unit can advance the conversation at a speed that is in tune with the user's emotions. This makes it possible to provide an appropriate conversation progress according to the user's emotions.

[0096] The lip sync unit can reproduce not only the mouth movements of the collection subject, but also gestures and body movements based on a sample of the collection subject's voice. For example, if the collection subject moves his / her hands when speaking, the lip sync unit reproduces the gestures. Also, if the collection subject moves his / her body, the lip sync unit can reproduce the movement. Furthermore, if the collection subject makes a specific movement when making a particular expression, the lip sync unit can reproduce the movement. This makes it possible to provide a more natural and realistic conversation experience.

[0097] When collecting a voice sample of the collection subject, the collection unit can analyze the environmental sounds around the collection subject and adjust the collection method according to the environmental sounds. For example, if the collection subject is in a noisy place, the collection unit can collect a clear voice sample using noise canceling technology. Also, if the collection subject is in a quiet place, the collection unit can collect a detailed voice sample using a highly sensitive microphone. Furthermore, if the collection subject is outdoors, the collection unit can also perform collection using technology to remove wind noise. This makes it possible to provide an appropriate collection method according to the surrounding environmental sounds.

[0098] The analysis unit can estimate the user's emotions based on the collected voice samples and personalize the content of the conversation based on the estimated emotions. For example, if the user is sad, the analysis unit can generate a response including words of comfort or messages of encouragement. If the user is happy, the analysis unit can also generate a response including words of congratulations or messages of sympathy. Furthermore, if the user is angry, the analysis unit can also generate a response encouraging a calm response. This makes it possible to provide personalized conversation content according to the user's emotions.

[0099] The lip sync unit can reproduce not only the mouth movements of the collection subject, but also the eye and eyebrow movements based on a sample of the collection subject's voice. For example, if the collection subject opens his or her eyes when speaking, the lip sync unit reproduces the eye movements. Also, if the collection subject raises his or her eyebrows when expressing surprise, the lip sync unit can also reproduce the eyebrow movements. Furthermore, if the collection subject lowers the corners of their eyes when laughing, the lip sync unit can also reproduce the eye movements. This makes it possible to achieve more natural and expressive lip sync.

[0100] The process flow of the second embodiment will be briefly described below.

[0101] Step 1: The collection unit collects voice samples. The collection unit collects voice samples using, for example, a voice collection device. The voice collection device includes, for example, a microphone or a smartphone. The collection unit collects voice samples of family members and people who are far away in daily life. For example, when family members are talking, the voices are recorded and saved as data. Step 2: The analysis unit analyzes the voice samples collected by the collection unit. The analysis unit analyzes the voice characteristics using, for example, voice analysis technology. Voice analysis technology includes, for example, spectrum analysis and acoustic models. The analysis unit learns the person's speaking style and voice characteristics based on the collected voice data. For example, the analysis unit analyzes the pronunciation of specific words, speaking speed, intonation, etc., and models the person's speaking style. Step 3: The lip sync unit aligns the mouth movement and the dialogue based on the data analyzed by the analysis unit. The lip sync unit aligns the mouth movement and the dialogue using, for example, a face tracking function. The face tracking function includes, for example, camera-based tracking and tracking using a sensor. The lip sync unit adjusts the mouth movement to match the dialogue when the voice collection device speaks. This allows the AI ​​chatbot system to provide a natural conversation experience to the user. Some or all of the above-mentioned processing in the lip sync unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the lip sync unit can input data acquired using the face tracking function to the generation AI and cause the generation AI to synchronize the mouth movement and the dialogue.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0104] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0105] Each of the multiple elements including the collection unit, analysis unit, and lip sync unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects voice samples using the microphone and camera 42 of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected voice data to model the person's speaking style. The lip sync unit is realized, for example, by the control unit 46A of the smart device 14, and uses a face tracking function to match the mouth movement and the lines. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

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

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

[0114] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

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

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0121] Each of the multiple elements including the above-mentioned collection unit, analysis unit, and lip sync unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects voice samples using the microphone 238 and the camera 42 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected voice data to model the person's speaking style. The lip sync unit is realized, for example, by the control unit 46A of the smart glasses 214, and uses a face tracking function to match the mouth movement and the lines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements including the above-mentioned collection unit, analysis unit, and lip sync unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects voice samples using the microphone 238 and the camera 42 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected voice data to model the person's speaking style. The lip sync unit is realized, for example, by the control unit 46A of the headset type terminal 314, and uses a face tracking function to match the mouth movement and the lines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0149] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] Each of the multiple elements including the above-mentioned collection unit, analysis unit, and lip sync unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects voice samples using the microphone 238 and the camera 42 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected voice data to model the person's speaking style. The lip sync unit is realized, for example, by the control unit 46A of the robot 414, and uses a face tracking function to match the mouth movement and the lines. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0156] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0160] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0167] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration in which a processor is used that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0171] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0173] (Appendix 1) a collection unit for collecting voice samples; an analysis unit that analyzes the voice samples collected by the collection unit; A lip sync unit that synchronizes mouth movements and lines based on the data analyzed by the analysis unit. A system characterized by: (Appendix 2) The collecting unit includes: Collect voice samples using audio collection devices 2. The system of claim 1, (Appendix 3) The analysis unit is Analyze voice characteristics using voice analysis technology 2. The system of claim 1, (Appendix 4) The lip sync unit includes: Use face tracking to match mouth movements with dialogue 2. The system of claim 1, (Appendix 5) The collecting unit includes: Collect voice samples from family members or distant people in your daily life 2. The system of claim 1, (Appendix 6) The analysis unit is Learns a person's speaking style and vocal characteristics based on collected voice data 2. The system of claim 1, (Appendix 7) The lip sync unit includes: When the voice capture device speaks, it adjusts the mouth movements to match the dialogue. 2. The system of claim 1, (Appendix 8) The collecting unit includes: A user's emotion is estimated, and a timing of collecting voice samples is adjusted based on the estimated user's emotion. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Filter out certain environmental and background sounds to capture clearer vocal samples 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting voice samples, the system detects the target's activity status and selects the optimal collection method. 2. The system of claim 1, (Appendix 11) The collecting unit includes: A user's emotion is estimated, and a priority is determined for voice samples to be collected based on the estimated user's emotion. 2. The system of claim 1, (Appendix 12) The collecting unit includes: Prioritize collection of voice samples from specific locations based on the subjects' geographic location 2. The system of claim 1, (Appendix 13) The collecting unit includes: Analyze the recipients' social media activity and collect relevant testimonial samples 2. The system of claim 1, (Appendix 14) The analysis unit is Estimate user emotions and adjust analysis accuracy based on the estimated user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is Evaluate the quality and noise level of the voice sample and select the optimal analysis algorithm 2. The system of claim 1, (Appendix 16) The analysis unit is Automatically identify the language and dialect of a voice sample and apply analysis techniques accordingly 2. The system of claim 1, (Appendix 17) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 18) The analysis unit is Prioritize analysis based on when voice samples were collected 2. The system of claim 1, (Appendix 19) The analysis unit is Improve the accuracy of the analysis by referring to related literature on collected voice samples 2. The system of claim 1, (Appendix 20) The lip sync unit includes: To estimate a user's emotion and adjust lip-sync accuracy based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The lip sync unit includes: Analyze the facial features of the subjects in detail and reproduce more natural mouth movements. 2. The system of claim 1, (Appendix 22) The lip sync unit includes: Detects changes in facial expressions of subjects in real time and adjusts mouth movements accordingly 2. The system of claim 1, (Appendix 23) The lip sync unit includes: To estimate a user's emotion and adjust a method of displaying lip sync based on the estimated user's emotion 2. The system of claim 1, (Appendix 24) The lip sync unit includes: Taking into account the geographic location information of collected subjects, improve the accuracy of lip-sync in a specific location 2. The system of claim 1, (Appendix 25) The lip sync unit includes: Analyze the social media activity of subjects and recreate relevant facial expressions and mouth movements 2. The system of claim 1, [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit for collecting voice samples; an analysis unit that analyzes the voice samples collected by the collection unit; A lip sync unit that synchronizes mouth movements and lines based on the data analyzed by the analysis unit. A system characterized by:

2. The collecting unit includes: Collect voice samples using audio collection devices 2. The system of claim 1 .

3. The analysis unit is Analyze voice characteristics using voice analysis technology 2. The system of claim 1 .

4. The lip sync unit includes: Use face tracking to match mouth movements with dialogue 2. The system of claim 1 .

5. The collecting unit includes: Collect voice samples from family members or distant people in your daily life 2. The system of claim 1 .

6. The analysis unit is Learns a person's speaking style and vocal characteristics based on collected voice data 2. The system of claim 1 .

7. The lip sync unit includes: When the voice capture device speaks, it adjusts the mouth movements to match the dialogue.

2. The system of claim 1 .

8. The collecting unit includes: A user's emotion is estimated, and a timing of collecting voice samples is adjusted based on the estimated user's emotion.

2. The system of claim 1 .

Images