system

Abstract

We provide the system. [Solution] A means for capturing a user's appearance information and generating a gender-neutral alternative image of the user, A means for acquiring the user's voice information and converting the voice into a neutral voice, A means for reflecting the acquired user's facial expressions and voice in the alternative video and converted audio in real time, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Gender bias is an important issue in modern society and may be particularly prominent in the employment selection process. In the conventional interview format, unconscious biases can occur, leading to unequal evaluations based on gender. Therefore, there is a need to provide a fair and neutral interview environment that can substantially evaluate the abilities and suitability of applicants.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that captures a user's appearance information, generates a gender-neutral alternative image, and further acquires its audio information and converts it into a gender-neutral voice. This allows for real-time reflection of the user's facial expressions and voice, creating an environment where fair evaluation is possible. Furthermore, by allowing the user to adjust the alternative image and providing the converted voice to a third party in real time, the system enables an interview process free from gender bias.

[0006] "User appearance information" refers to data about the user's appearance in the interview system, and is information obtained through photographs, videos, etc.

[0007] "Androgynous alternative images" are visual representations that are generated based on the user's appearance information and have a neutral appearance that does not convey gender characteristics.

[0008] "Voice information" refers to data related to the user's voice, including characteristics such as pitch, quality, and speed of sound acquired in the interview system.

[0009] "Gender-neutral voice" refers to a voice that has been transformed to remove gender-specific characteristics from the original voice, making it sound natural regardless of gender.

[0010] "Real-time reflection" means that user input information is processed immediately, and this instantly affects the output within the system.

[0011] A "third party" refers to an individual or organization that does not use the interview system but receives the information output by the system. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system for providing an online interview environment free from gender bias. The system is primarily achieved by generating a gender-neutral avatar and voice based on the user's appearance and voice information, and then reflecting this in the interview environment.

[0034] First, the user accesses the system using a device and uploads their photo and a pre-recorded voice sample. This collects basic data about the user's appearance and voice. This data is sent to a server, where it undergoes analysis to generate a gender-neutral avatar that abstracts the user's features. This gender-neutral avatar can be adjusted according to the user's choices, allowing it to have an appearance that aligns with the user's preferences.

[0035] The server further analyzes the voice data and applies a gender-neutral voice conversion model. This converts the user's voice to a gender-neutral voice during the interview, eliminating any gender-specific characteristics. This voice conversion process is performed in real time and transmitted to the client terminal.

[0036] During the interview, the device captures the user's facial expressions and voice in real time and sends them to the server. The server immediately processes this data and reflects it in the avatar's facial expressions and movements, enabling natural communication. In this way, interviewers can interact with users without bias, ensuring a fair evaluation.

[0037] As a concrete example, consider a scenario where a job seeker participates in a remote interview using this system. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and their movements and voice are displayed in real time on the interviewer's screen as a gender-neutral avatar. This process eliminates all gender-related identification, providing an environment where the job seeker is evaluated solely on their abilities and experience. This embodiment facilitates fair evaluation and reduces the impact of gender bias.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] Users access the system via their devices and upload photos and videos as information about their appearance. This prepares the basic data used for interviews.

[0041] Step 2:

[0042] The device records a sample of the user's voice via the microphone and sends it to the server. The voice data provides information necessary for subsequent processing.

[0043] Step 3:

[0044] The server generates a gender-neutral avatar based on the received appearance information. The algorithm used here aims for a gender-neutral appearance.

[0045] Step 4:

[0046] The server analyzes the audio data and prepares it for gender-neutralization. This includes pitch adjustment and sound quality modification.

[0047] Step 5:

[0048] Once the interview begins, the device captures the user's real-time video and audio and sends it to the server. This process continues throughout the interview.

[0049] Step 6:

[0050] The server processes incoming data in real time and reflects it in the avatar's movements and facial expressions. Additionally, the voice is gender-neutralized, and the conversion results are immediately communicated to the interviewer.

[0051] Step 7:

[0052] The terminal displays a gender-neutral avatar's image and converted audio for output to the interviewer. This allows the interviewer to evaluate the user without considering their gender characteristics.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] In today's remote interview environment, it is difficult to eliminate gender bias that interviewers may have towards candidates. Therefore, there is a need for a system that prevents gender-based evaluations and provides fair evaluation criteria.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes means for receiving image and audio information of a user and analyzing the user's characteristics, means for using a generation model that creates a neutral surrogate image based on the characteristics, and means for using an audio conversion model that analyzes the audio information and converts it into neutral audio. This enables the generation of unbiased, neutral images and audio, allowing users to be evaluated fairly during interviews.

[0058] "Image information" refers to visual data related to the user's appearance, including photographs and videos.

[0059] "Audio information" refers to auditory data related to the user's voice, including recorded audio samples.

[0060] "Features" refer to identifiable attributes and characteristics extracted from the user's image and audio information.

[0061] A "generative model" refers to an algorithm or technique trained to generate a neutral surrogate image from input data.

[0062] A "speech conversion model" refers to an algorithm or technology designed to convert input speech into a neutral speech.

[0063] "Proxy video" refers to an avatar with a gender-neutral appearance that is generated based on the user's characteristics.

[0064] "Androgynous voice" refers to converted audio data that has a sound quality and characteristics that are not biased towards a specific gender.

[0065] An "external recipient" refers to a third party who receives neutral video or audio generated using the system.

[0066] This invention is a system aimed at eliminating gender bias in online interview environments. The system generates gender-neutral surrogate video and audio that suppresses gender bias based on image and audio information provided by the user.

[0067] Users first access the system using a device and upload their photos and audio samples. The device then sends the data received from the user to the server in an appropriate format. This data is handled using encryption methods that take privacy into consideration.

[0068] The server utilizes image processing software (e.g., OpenCV or Dlib) to process the received image information. This extracts feature points from the user's face and obtains basic data for generating a neutral surrogate image. A generative AI model is then used to generate a neutral avatar based on these features.

[0069] In processing audio information, voice analysis tools (e.g., Pyaudio and Librosa) are used to extract the characteristics of the user's voice. The server analyzes these characteristics and applies a generative AI model (e.g., Tacotron 2 and WaveGlow) to generate a gender-neutral voice.

[0070] When a user conducts an interview, their device captures their facial expressions and voice in real time and sends them to the server. The server immediately processes this data and incorporates it into the generated surrogate video and neutral audio. As a result, the interviewer's device displays unbiased, neutral video and audio in real time.

[0071] As a concrete example, consider a case where a job seeker uses this system to participate in a remote interview. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and is displayed on the interviewer's screen as a generated gender-neutral avatar. In this process, gender information is removed, creating an environment where the job seeker is evaluated solely on their abilities and experience.

[0072] Examples of prompts to input into a generative AI model:

[0073] "Please generate a gender-neutral avatar and voice based on the user's image and voice data."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user uses a terminal to access the system and upload their photos and audio samples. The input data consists of JPEG images and WAV audio files. The terminal sends the received data to the server in the specified format. This inputs the user's image and audio information into the server.

[0077] Step 2:

[0078] The server receives image information and uses image processing software (e.g., OpenCV) to extract facial feature points. By analyzing the user's image and identifying facial landmarks, it obtains feature data based on the shape and arrangement of the face. This process generates intermediate data for input into the generative AI model.

[0079] Step 3:

[0080] The server uses a speech analysis tool (e.g., Librosa) to analyze the speech information. It extracts the fundamental frequency and energy of the speech data, and obtains information about the tempo and pitch of the speech. This prepares the speech feature data that should be input into the speech conversion model.

[0081] Step 4:

[0082] The server uses the generated facial feature data and a generative AI model to create a neutral surrogate image. In this process, the AI ​​model applies learned neutral parameters to output a substitute image that masks the user's features. This output is a neutral avatar image.

[0083] Step 5:

[0084] The server generates neutral speech using a speech conversion model based on speech feature data. The server then adjusts the speech features and outputs speech converted to a neutral voice quality. This output is neutral speech data.

[0085] Step 6:

[0086] During the interview, the terminal captures the user's facial expressions and voice in real time and sends them to the server. This data is reflected in the system-generated neutral voice and video. The server processes the data in real time and sends the generated neutral avatar and voice to the interviewer's terminal. This output enables a real-time communication environment.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In online communication, gender bias is a problem that influences users' evaluations and impressions. This invention aims to provide a means to eliminate such bias and realize fair interaction.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for the user to communicate with other users and service providers through the generated gender-neutral alternative image. This enables fair online communication that is not dependent on gender.

[0092] A "user" is an individual or group that uses the system and is the entity that provides their appearance information and voice information.

[0093] "Appearance information" refers to data related to the user's physical appearance, including photographs and video footage.

[0094] "Gender-neutral alternative images" are virtual images of users that are independent of gender attributes and are generated with the aim of eliminating gender bias.

[0095] "Voice information" refers to data related to the user's speech and voice, and includes recorded voice samples.

[0096] "Gender-neutral voice" refers to a voice that has been transformed into a gender-neutral form, and is used to eliminate the influence of gender bias.

[0097] "Facial expressions" refer to information about the user's facial movements and emotional expressions, and are data captured in real time.

[0098] "Communication" is the act of exchanging information and intentions with others and engaging in interaction.

[0099] A "service provider" is an entity that provides services to users on an online platform or in a virtual space.

[0100] The system for implementing this invention consists of a cloud-based server, a user terminal, and a communication infrastructure. Users access the system using a terminal such as a smartphone or a head-mounted display. First, the terminal acquires the user's appearance information as photos and videos and records audio information. This data is sent to the cloud server.

[0101] The cloud server analyzes received appearance information and generates a gender-neutral alternative image. Image processing algorithms and, if necessary, generation AI models are used for image generation. In addition, audio information is processed into a gender-neutral voice using a speech conversion algorithm. This provides a gender-neutral and fair communication environment.

[0102] Furthermore, when users communicate with other users or service providers, the cloud server captures the user's facial expressions and voice in real time and reflects them in a generated, gender-neutral avatar. This enables natural and smooth conversations in the virtual space. This process uses real-time image processing software and voice analysis tools. As a concrete example, consider a scenario where a user accesses an online virtual store to check product details. In this case, the user can check the product's features and usage instructions with staff through their gender-neutral avatar. A prompt such as, "Please explain how to use this product in detail from a gender-neutral perspective," allows the user to obtain a more objective and detailed explanation.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The user accesses the system using a terminal. First, the terminal captures the user's appearance as a photograph or video and records audio information. At this stage, the user's image data and audio data are obtained as input. As output, this data is ready to be sent to the server.

[0106] Step 2:

[0107] The server receives image data transmitted from the terminal. Upon receiving the data, the server uses image processing algorithms to generate a gender-neutral alternative image. This process includes feature extraction and face analysis, resulting in a gender-independent image based on the input image data. Generative AI models may also be used in this step.

[0108] Step 3:

[0109] The server then receives the audio data transmitted from the terminal. This audio data is analyzed using a speech conversion algorithm and converted into gender-neutral speech. The input is audio data, and the output is gender-neutral speech data. A speech analysis tool assists in this process.

[0110] Step 4:

[0111] Once a user begins communicating, the server continuously captures facial and audio data from the user in real time. This data is applied to the neutral alternative video generated in step 2 and is dynamically updated. Live data is used as input, and real-time video and audio are output.

[0112] Step 5:

[0113] Ultimately, users communicate with other users and service providers through a generated, gender-neutral avatar. They can use prompts to elicit specific information. At this stage, actual dialogue takes place, completing the interaction in the virtual space.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] This invention is a system for eliminating gender bias in online interviews and enabling fairer evaluations. In addition to a function for generating gender-neutral video and audio based on the user's appearance and voice information, this system incorporates an emotion engine to recognize and reflect the user's emotions.

[0116] First, users access the system via their device and upload their photos and voice samples. The server then generates a gender-neutral avatar based on this user information. This avatar has a gender-neutral appearance and can be adjusted according to the user's preferences. Additionally, voice data is converted to a gender-neutral voice, preparing it for real-time conversion during the interview.

[0117] During the interview process, the device captures the user's facial expressions and voice in real time and sends this data to a server. The server then generates a neutral video and audio based on this data, reflecting the user's actual facial expressions and emotions. An emotion engine analyzes the user's emotional state and applies the results to the neutral avatar's facial expressions, enabling richer communication.

[0118] As a concrete example, let's consider a scenario where a job seeker uses this system to participate in a remote interview with a company. In this case, the job seeker's device captures their facial expressions and voice and sends them to the server, where an emotion engine analyzes them. Based on the analysis results, the server adjusts the avatar's facial expressions to display appropriate emotions during the interview. The neutral voice generated during this process is converted in real time, including emotional information, and transmitted to the interviewer. This allows the interviewer to evaluate the job seeker's abilities and suitability without bias.

[0119] Furthermore, the acquired emotion recognition results are used as additional information to be provided to the interviewer. This enables decision-making based on a deeper understanding. Depending on the form in which the invention is implemented, it is possible to provide a fair and neutral evaluation procedure that takes user emotions into consideration, thereby improving the fairness and quality of the interview process.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The user uses a terminal to log in to the interview system. Next, they upload photos, videos, and audio samples representing their appearance to the system. This process prepares the basic data that the system will use.

[0123] Step 2:

[0124] The server generates a gender-neutral avatar based on the appearance information obtained from the user. In this step, an AI algorithm is used to create an avatar with a gender-independent appearance.

[0125] Step 3:

[0126] The server analyzes the user's voice information and converts it to a gender-neutral voice. A voice conversion module adjusts the pitch and tone to create a voice that does not convey gender characteristics.

[0127] Step 4:

[0128] The device captures the user's real-time video and audio through its camera and microphone at the start of the interview. This data is transmitted to the server in real time.

[0129] Step 5:

[0130] The server uses an emotion engine to analyze the user's emotions from the received audio and video. This analysis is then reflected in the facial expressions of a gender-neutral avatar to express those emotions.

[0131] Step 6:

[0132] The system transmits a converted, gender-neutral voice and a gender-neutral avatar reflecting emotions to the interviewer's device in real time. This allows the interviewer to engage in emotionally conscious conversations regardless of the user's gender.

[0133] Step 7:

[0134] The server saves the emotion recognition results as logs, providing information that can be further analyzed after the interview. This allows interviewers to gain a deeper understanding of the user's emotional state during the interview.

[0135] (Example 2)

[0136] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0137] In online interviews, a system is needed to eliminate gender bias based on the applicant's appearance and voice, enabling fair and neutral evaluation. Furthermore, technology is required to accurately reflect the applicant's emotions and facial expressions during the interview, providing the interviewer with a natural expression of those emotions.

[0138] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0139] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative visual representation of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; and means for analyzing the acquired user's emotional state and reflecting the analysis results in the alternative visual representation and voice in real time. This makes it possible to eliminate gender bias and conduct fair interview evaluations that take the user's emotions into consideration.

[0140] "Appearance information" refers to information that describes the user's basic appearance and facial features.

[0141] "Neutral alternative visual representations" refer to visual representations that are neutral in appearance and do not depend on a specific gender.

[0142] "Voice information" refers to data related to the user's voice, including voice characteristics.

[0143] A "neutral voice" refers to a voice that is not biased towards the characteristics of a particular gender, but is neutral.

[0144] "Emotional state" refers to the emotional state that can be interpreted from the user's facial expressions and voice.

[0145] "Adjusting alternative visual representations" is a feature that allows users to modify the generated visual representations according to their own preferences.

[0146] "Emotional analysis results" refer to data about the user's emotions obtained through emotional analysis methods.

[0147] "Real-time" refers to processing that occurs instantly without delay.

[0148] This invention provides a system for eliminating gender bias in online interviews and ensuring fair evaluations. Users first access the system via a terminal and upload their appearance information (photos) and audio information. The server then generates a neutral alternative visual representation and voice based on the user's appearance information. The technologies used include image processing and speech synthesis. Specifically, a generative AI model is used to generate a neutral appearance and voice.

[0149] The server uses an emotion analysis engine to analyze the user's emotional state from their facial expressions and voice, obtained in real time. The data is processed immediately and reflected in neutral alternative visual representations and audio in real time. Possible emotion engines include general emotion analysis APIs and software.

[0150] As a concrete example, when a user participates in a remote interview, the user's device uses its camera and microphone to capture facial expressions and voice, and sends this data to the server. Based on the transmitted data, the server adjusts the avatar's facial expressions in real time, visually reflecting the user's emotional state. An example of a prompt message the user might give to the system is, "Analyze the user's smile and reflect it on the avatar in real time."

[0151] This system enables interviewers to fairly evaluate applicants' abilities and aptitudes, ensuring a fair and neutral interview process. Furthermore, the sentiment analysis results are used as supplementary information provided to interviewers, supporting decision-making based on a deeper understanding.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] The user accesses the system from their device and uploads a photo and voice sample as their personal information. This input data becomes the basic information used for subsequent processing. The device sends this information to the server.

[0155] Step 2:

[0156] The server receives photos and audio samples sent by the user. A generative AI model is used to generate a gender-neutral alternative visual representation from the photos. This process utilizes image processing techniques to generate a neutral appearance that is not biased towards any particular gender. Audio samples are converted into gender-neutral voices using speech synthesis technology.

[0157] Step 3:

[0158] Once the user interview begins, the device uses its camera and microphone to capture the user's facial expressions and voice in real time. This data is continuously transmitted to the server as the interview progresses. The acquired data plays a role in instantly capturing the ambiguous emotions and facial expressions displayed by the user.

[0159] Step 4:

[0160] The server uses an emotion analysis engine to analyze the user's emotional state based on captured facial and audio data. The resulting emotional information is reflected in neutral alternative visual representations and audio in real time. This allows the avatar to express the user's true emotions.

[0161] Step 5:

[0162] The server provides the interviewer with generated, neutral alternative visual representations and converted audio in real time. At this stage, the interviewer receives emotional information from the user's neutral appearance and voice. This allows the interviewer to make an evaluation based on unbiased information.

[0163] Step 6:

[0164] Once the interview is complete, the server provides the interviewer with additional information based on the sentiment analysis results. This information helps in post-interview evaluation and decision-making. Based on this information, the interviewer can make decisions based on a deeper understanding that takes the user's emotions into account.

[0165] (Application Example 2)

[0166] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0167] The challenge in online interviews is not only to eliminate gender bias and ensure fair evaluation, but also to provide a method that considers the emotions and state of the passengers and offers a comfortable experience within the mode of transport. In particular, in autonomous vehicles, there is a need to select appropriate music and videos that respond to the emotions of the passengers, but there is a problem in that there is no technology to do this efficiently and individually.

[0168] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0169] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for analyzing the passenger's emotional state and selecting and providing ambient music or video content within the means of transport. This enables passengers to use the means of transport in a relaxed and comfortable manner.

[0170] "User appearance information" refers to digital data relating to the appearance and physical characteristics of individual users.

[0171] A "gender-neutral alternative image" is a visual avatar that eliminates gender-specific characteristics and is generated to be neutral and applicable to anyone.

[0172] "User voice information" refers to digital data related to a specific user's speech and manner of speaking.

[0173] A "gender-neutral voice" is a voice that has intermediate vocal characteristics without emphasizing a specific gender.

[0174] "Methods for real-time reflection" refer to technologies that process user input information immediately and reflect the results as output instantly.

[0175] "Methods for analyzing emotional states" refer to technologies that evaluate a user's psychological state and emotions at a given time based on their facial expressions and voice.

[0176] "Means of selecting and providing ambient music or video content" refers to technology that determines the optimal music or video according to the user's emotional state and settings, and then plays it back to the user.

[0177] This invention is based on a system installed in an autonomous vehicle and aims to generate neutral alternative images and sounds by capturing the user's appearance and voice information, and to provide appropriate music and images according to the user's emotional state. This system consists of multiple components, and in particular incorporates a process for processing the user's input data and providing optimized output.

[0178] The server acquires the user's facial expression and voice information transmitted from the terminal. This information is analyzed by an AI model and converted into gender-neutral avatar images and voices. A sentiment analysis engine using TENSORFLOW® is employed in this process. The generated gender-neutral alternative images and voices are updated in real time based on the user's facial expressions and voice characteristics.

[0179] Furthermore, the server analyzes the user's emotional state and, based on the results, selects the music played through the speakers in the autonomous vehicle and the images displayed on the screen. This information processing is performed in the cloud, and the results are immediately reflected on the terminal.

[0180] For example, if a user wants to relax in the car, and the emotion analysis engine determines that the user's stress level is low, the in-car environment will switch to relaxing music. An example of a prompt to input to the generative AI model could be, "Suggest the most suitable music based on the passenger's emotional state." In this way, a comfortable experience in the car can be promoted.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The user's device uses its built-in camera and microphone to capture facial and audio information in real time. This input data is sent to the server in video and audio formats. The server receives this data and prepares it for analysis by an AI model.

[0184] Step 2:

[0185] The server analyzes the received facial expression and audio information through an AI model. Here, the facial expression information is analyzed using an image processing algorithm to identify facial feature points, and the audio information is converted to gender-neutral vocal characteristics by a speech recognition algorithm. As a result, gender-neutral avatar video and audio data are generated.

[0186] Step 3:

[0187] The server sends the generated neutral avatar video and audio data back to the terminal, which then reflects it to the user in real time. This data is output through the user's display and speakers. Throughout this process, the AI ​​model's emotion analysis engine continuously assesses the user's current emotions and adjusts the video and audio as needed.

[0188] Step 4:

[0189] The server uses an emotion analysis engine to understand the user's emotional state. Based on this input data, it extracts emotional parameters such as the user's stress level and happiness level, and selects ambient music and video content accordingly. This information is selected using a generative AI model based on the prompt message, "Suggest the most suitable music based on the crew's emotional state."

[0190] Step 5:

[0191] The server transmits selected music and video content to the terminal, which then plays it through the car's speakers and display. This output provides the user with an optimal environment, resulting in a comfortable user experience.

[0192] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0193] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0198] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0199] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0200] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0202] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0203] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0206] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0207] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0208] This invention is a system for providing an online interview environment free from gender bias. The system is primarily achieved by generating a gender-neutral avatar and voice based on the user's appearance and voice information, and then reflecting this in the interview environment.

[0209] First, the user accesses the system using a device and uploads their photo and a pre-recorded voice sample. This collects basic data about the user's appearance and voice. This data is sent to a server, where it undergoes analysis to generate a gender-neutral avatar that abstracts the user's features. This gender-neutral avatar can be adjusted according to the user's choices, allowing it to have an appearance that aligns with the user's preferences.

[0210] The server further analyzes the voice data and applies a gender-neutral voice conversion model. This converts the user's voice to a gender-neutral voice during the interview, eliminating any gender-specific characteristics. This voice conversion process is performed in real time and transmitted to the client terminal.

[0211] During the interview, the device captures the user's facial expressions and voice in real time and sends them to the server. The server immediately processes this data and reflects it in the avatar's facial expressions and movements, enabling natural communication. In this way, interviewers can interact with users without bias, ensuring a fair evaluation.

[0212] As a concrete example, consider a scenario where a job seeker participates in a remote interview using this system. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and their movements and voice are displayed in real time on the interviewer's screen as a gender-neutral avatar. This process eliminates all gender-related identification, providing an environment where the job seeker is evaluated solely on their abilities and experience. This embodiment facilitates fair evaluation and reduces the impact of gender bias.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] Users access the system via their devices and upload photos and videos as information about their appearance. This prepares the basic data used for interviews.

[0216] Step 2:

[0217] The device records a sample of the user's voice via the microphone and sends it to the server. The voice data provides information necessary for subsequent processing.

[0218] Step 3:

[0219] The server generates a gender-neutral avatar based on the received appearance information. The algorithm used here aims for a gender-neutral appearance.

[0220] Step 4:

[0221] The server analyzes the audio data and prepares it for gender-neutralization. This includes pitch adjustment and sound quality modification.

[0222] Step 5:

[0223] Once the interview begins, the device captures the user's real-time video and audio and sends it to the server. This process continues throughout the interview.

[0224] Step 6:

[0225] The server processes incoming data in real time and reflects it in the avatar's movements and facial expressions. Additionally, the voice is gender-neutralized, and the conversion results are immediately communicated to the interviewer.

[0226] Step 7:

[0227] The terminal displays a gender-neutral avatar's image and converted audio for output to the interviewer. This allows the interviewer to evaluate the user without considering their gender characteristics.

[0228] (Example 1)

[0229] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0230] In today's remote interview environment, it is difficult to eliminate gender bias that interviewers may have towards candidates. Therefore, there is a need for a system that prevents gender-based evaluations and provides fair evaluation criteria.

[0231] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0232] In this invention, the server includes means for receiving image and audio information of a user and analyzing the user's characteristics, means for using a generation model that creates a neutral surrogate image based on the characteristics, and means for using an audio conversion model that analyzes the audio information and converts it into neutral audio. This enables the generation of unbiased, neutral images and audio, allowing users to be evaluated fairly during interviews.

[0233] "Image information" refers to visual data related to the user's appearance, including photographs and videos.

[0234] "Audio information" refers to auditory data related to the user's voice, including recorded audio samples.

[0235] "Features" refer to identifiable attributes and characteristics extracted from the user's image and audio information.

[0236] A "generative model" refers to an algorithm or technique trained to generate a neutral surrogate image from input data.

[0237] A "speech conversion model" refers to an algorithm or technology designed to convert input speech into a neutral speech.

[0238] "Proxy video" refers to an avatar with a gender-neutral appearance that is generated based on the user's characteristics.

[0239] "Androgynous voice" refers to converted audio data that has a sound quality and characteristics that are not biased towards a specific gender.

[0240] An "external recipient" refers to a third party who receives neutral video or audio generated using the system.

[0241] This invention is a system aimed at eliminating gender bias in online interview environments. The system generates gender-neutral surrogate video and audio that suppresses gender bias based on image and audio information provided by the user.

[0242] Users first access the system using a device and upload their photos and audio samples. The device then sends the data received from the user to the server in an appropriate format. This data is handled using encryption methods that take privacy into consideration.

[0243] The server utilizes image processing software (e.g., OpenCV or Dlib) to process the received image information. This extracts feature points from the user's face and obtains basic data for generating a neutral surrogate image. A generative AI model is then used to generate a neutral avatar based on these features.

[0244] In processing audio information, voice analysis tools (e.g., Pyaudio and Librosa) are used to extract the characteristics of the user's voice. The server analyzes these characteristics and applies a generative AI model (e.g., Tacotron 2 and WaveGlow) to generate a gender-neutral voice.

[0245] When a user conducts an interview, their device captures their facial expressions and voice in real time and sends them to the server. The server immediately processes this data and incorporates it into the generated surrogate video and neutral audio. As a result, the interviewer's device displays unbiased, neutral video and audio in real time.

[0246] As a concrete example, consider a case where a job seeker uses this system to participate in a remote interview. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and is displayed on the interviewer's screen as a generated gender-neutral avatar. In this process, gender information is removed, creating an environment where the job seeker is evaluated solely on their abilities and experience.

[0247] Examples of prompts to input into a generative AI model:

[0248] "Please generate a gender-neutral avatar and voice based on the user's image and voice data."

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The user uses a terminal to access the system and upload their photos and audio samples. The input data consists of JPEG images and WAV audio files. The terminal sends the received data to the server in the specified format. This inputs the user's image and audio information into the server.

[0252] Step 2:

[0253] The server receives image information and uses image processing software (e.g., OpenCV) to extract facial feature points. By analyzing the user's image and identifying facial landmarks, it obtains feature data based on the shape and arrangement of the face. This process generates intermediate data for input into the generative AI model.

[0254] Step 3:

[0255] The server uses a speech analysis tool (e.g., Librosa) to analyze the speech information. It extracts the fundamental frequency and energy of the speech data, and obtains information about the tempo and pitch of the speech. This prepares the speech feature data that should be input into the speech conversion model.

[0256] Step 4:

[0257] The server uses the generated facial feature data and a generative AI model to create a neutral surrogate image. In this process, the AI ​​model applies learned neutral parameters to output a substitute image that masks the user's features. This output is a neutral avatar image.

[0258] Step 5:

[0259] The server generates neutral speech using a speech conversion model based on speech feature data. The server then adjusts the speech features and outputs speech converted to a neutral voice quality. This output is neutral speech data.

[0260] Step 6:

[0261] During the interview, the terminal captures the user's facial expressions and voice in real time and sends them to the server. This data is reflected in the system-generated neutral voice and video. The server processes the data in real time and sends the generated neutral avatar and voice to the interviewer's terminal. This output enables a real-time communication environment.

[0262] (Application Example 1)

[0263] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In online communication, gender bias is a problem that influences users' evaluations and impressions. This invention aims to provide a means to eliminate such bias and realize fair interaction.

[0265] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0266] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for the user to communicate with other users and service providers through the generated gender-neutral alternative image. This enables fair online communication that is not dependent on gender.

[0267] A "user" is an individual or group that uses the system and is the entity that provides their appearance information and voice information.

[0268] "Appearance information" refers to data related to the user's physical appearance, including photographs and video footage.

[0269] "Gender-neutral alternative images" are virtual images of users that are independent of gender attributes and are generated with the aim of eliminating gender bias.

[0270] "Voice information" refers to data related to the user's speech and voice, and includes recorded voice samples.

[0271] "Gender-neutral voice" refers to a voice that has been transformed into a gender-neutral form, and is used to eliminate the influence of gender bias.

[0272] "Facial expressions" refer to information about the user's facial movements and emotional expressions, and are data captured in real time.

[0273] "Communication" is the act of exchanging information and intentions with others and engaging in interaction.

[0274] A "service provider" is an entity that provides services to users on an online platform or in a virtual space.

[0275] The system for implementing this invention consists of a cloud-based server, a user terminal, and a communication infrastructure. Users access the system using a terminal such as a smartphone or a head-mounted display. First, the terminal acquires the user's appearance information as photos and videos and records audio information. This data is sent to the cloud server.

[0276] The cloud server analyzes received appearance information and generates a gender-neutral alternative image. Image processing algorithms and, if necessary, generation AI models are used for image generation. In addition, audio information is processed into a gender-neutral voice using a speech conversion algorithm. This provides a gender-neutral and fair communication environment.

[0277] Furthermore, when users communicate with other users or service providers, the cloud server captures the user's facial expressions and voice in real time and reflects them in a generated, gender-neutral avatar. This enables natural and smooth conversations in the virtual space. This process uses real-time image processing software and voice analysis tools. As a concrete example, consider a scenario where a user accesses an online virtual store to check product details. In this case, the user can check the product's features and usage instructions with staff through their gender-neutral avatar. A prompt such as, "Please explain how to use this product in detail from a gender-neutral perspective," allows the user to obtain a more objective and detailed explanation.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] The user accesses the system using a terminal. First, the terminal captures the user's appearance information as a photo or video and records the voice information. At this stage, the user's image data and voice data are obtained as inputs. As an output, these data are prepared to be sent to the server.

[0281] Step 2:

[0282] The server receives the image data sent from the terminal. The server that has received the data generates a neutral alternative video using an image processing algorithm. This process includes feature extraction and face analysis, and a gender-independent video is output based on the input image data. A generation AI model may also be used in this step.

[0283] Step 3:

[0284] The server then receives the voice data sent from the terminal. This voice data is analyzed using a voice conversion algorithm and converted into gender-neutral voice. The input is voice data, and the output is neutral voice data. A voice analysis tool supports this process.

[0285] Step 4:

[0286] When the user starts communication, the server continues to capture the user's facial expression and voice data in real time. These data are applied to the neutral alternative video generated in Step 2 and updated dynamically. Live data is used as an input, and real-time video and voice are output.

[0287] Step 5:

[0288] Ultimately, users communicate with other users and service providers through a generated, gender-neutral avatar. They can use prompts to elicit specific information. At this stage, actual dialogue takes place, completing the interaction in the virtual space.

[0289] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0290] This invention is a system for eliminating gender bias in online interviews and enabling fairer evaluations. In addition to a function for generating gender-neutral video and audio based on the user's appearance and voice information, this system incorporates an emotion engine to recognize and reflect the user's emotions.

[0291] First, users access the system via their device and upload their photos and voice samples. The server then generates a gender-neutral avatar based on this user information. This avatar has a gender-neutral appearance and can be adjusted according to the user's preferences. Additionally, voice data is converted to a gender-neutral voice, preparing it for real-time conversion during the interview.

[0292] During the interview process, the device captures the user's facial expressions and voice in real time and sends this data to a server. The server then generates a neutral video and audio based on this data, reflecting the user's actual facial expressions and emotions. An emotion engine analyzes the user's emotional state and applies the results to the neutral avatar's facial expressions, enabling richer communication.

[0293] As a concrete example, let's consider a scenario where a job seeker uses this system to participate in a remote interview with a company. In this case, the job seeker's device captures their facial expressions and voice and sends them to the server, where an emotion engine analyzes them. Based on the analysis results, the server adjusts the avatar's facial expressions to display appropriate emotions during the interview. The neutral voice generated during this process is converted in real time, including emotional information, and transmitted to the interviewer. This allows the interviewer to evaluate the job seeker's abilities and suitability without bias.

[0294] Furthermore, the acquired emotion recognition results are used as additional information to be provided to the interviewer. This enables decision-making based on a deeper understanding. Depending on the form in which the invention is implemented, it is possible to provide a fair and neutral evaluation procedure that takes user emotions into consideration, thereby improving the fairness and quality of the interview process.

[0295] The following describes the processing flow.

[0296] Step 1:

[0297] The user uses a terminal to log in to the interview system. Next, they upload photos, videos, and audio samples representing their appearance to the system. This process prepares the basic data that the system will use.

[0298] Step 2:

[0299] The server generates a gender-neutral avatar based on the appearance information obtained from the user. In this step, an AI algorithm is used to create an avatar with a gender-independent appearance.

[0300] Step 3:

[0301] The server analyzes the user's voice information and converts it to a gender-neutral voice. A voice conversion module adjusts the pitch and tone to create a voice that does not convey gender characteristics.

[0302] Step 4:

[0303] At the start of the interview, the terminal captures the user's real-time video and audio through the camera and microphone. These data are sent to the server in real time.

[0304] Step 5:

[0305] The server analyzes the user's emotions from the received audio and video using an emotion engine. The analysis result is reflected in the expression of a neutral avatar to express the emotion.

[0306] Step 6:

[0307] The converted neutral voice and the neutral avatar reflecting the emotion are sent in real time to the interviewer's terminal. This enables the interviewer to conduct an emotion - considered conversation regardless of the user's gender.

[0308] Step 7:

[0309] The server saves the emotion recognition result as a log and provides information that can be further analyzed after the interview. This enables the interviewer to better understand the user's emotional state during the interview.

[0310] (Example 2)

[0311] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] In an online interview, a system is needed to eliminate gender bias in the user's appearance and voice and enable a fair and neutral evaluation. Also, a technology is required that can accurately reflect the user's emotions and expressions in the interview and provide the interviewer with the user's natural emotional expressions.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0314] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative visual representation of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; and means for analyzing the acquired user's emotional state and reflecting the analysis results in the alternative visual representation and voice in real time. This makes it possible to eliminate gender bias and conduct fair interview evaluations that take the user's emotions into consideration.

[0315] "Appearance information" refers to information that describes the user's basic appearance and facial features.

[0316] "Neutral alternative visual representations" refer to visual representations that are neutral in appearance and do not depend on a specific gender.

[0317] "Voice information" refers to data related to the user's voice, including voice characteristics.

[0318] A "neutral voice" refers to a voice that is not biased towards the characteristics of a particular gender, but is neutral.

[0319] "Emotional state" refers to the emotional state that can be interpreted from the user's facial expressions and voice.

[0320] "Adjusting alternative visual representations" is a feature that allows users to modify the generated visual representations according to their own preferences.

[0321] "Emotional analysis results" refer to data about the user's emotions obtained through emotional analysis methods.

[0322] "Real-time" refers to processing that occurs instantly without delay.

[0323] This invention provides a system for eliminating gender bias in online interviews and ensuring fair evaluations. Users first access the system via a terminal and upload their appearance information (photos) and audio information. The server then generates a neutral alternative visual representation and voice based on the user's appearance information. The technologies used include image processing and speech synthesis. Specifically, a generative AI model is used to generate a neutral appearance and voice.

[0324] The server uses an emotion analysis engine to analyze the user's emotional state from their facial expressions and voice, obtained in real time. The data is processed immediately and reflected in neutral alternative visual representations and audio in real time. Possible emotion engines include general emotion analysis APIs and software.

[0325] As a concrete example, when a user participates in a remote interview, the user's device uses its camera and microphone to capture facial expressions and voice, and sends this data to the server. Based on the transmitted data, the server adjusts the avatar's facial expressions in real time, visually reflecting the user's emotional state. An example of a prompt message the user might give to the system is, "Analyze the user's smile and reflect it on the avatar in real time."

[0326] This system enables interviewers to fairly evaluate applicants' abilities and aptitudes, ensuring a fair and neutral interview process. Furthermore, the sentiment analysis results are used as supplementary information provided to interviewers, supporting decision-making based on a deeper understanding.

[0327] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0328] Step 1:

[0329] The user accesses the system from their device and uploads a photo and voice sample as their personal information. This input data becomes the basic information used for subsequent processing. The device sends this information to the server.

[0330] Step 2:

[0331] The server receives photos and audio samples sent by the user. A generative AI model is used to generate a gender-neutral alternative visual representation from the photos. This process utilizes image processing techniques to generate a neutral appearance that is not biased towards any particular gender. Audio samples are converted into gender-neutral voices using speech synthesis technology.

[0332] Step 3:

[0333] Once the user interview begins, the device uses its camera and microphone to capture the user's facial expressions and voice in real time. This data is continuously transmitted to the server as the interview progresses. The acquired data plays a role in instantly capturing the ambiguous emotions and facial expressions displayed by the user.

[0334] Step 4:

[0335] The server uses an emotion analysis engine to analyze the user's emotional state based on captured facial and audio data. The resulting emotional information is reflected in neutral alternative visual representations and audio in real time. This allows the avatar to express the user's true emotions.

[0336] Step 5:

[0337] The server provides the interviewer with generated, neutral alternative visual representations and converted audio in real time. At this stage, the interviewer receives emotional information from the user's neutral appearance and voice. This allows the interviewer to make an evaluation based on unbiased information.

[0338] Step 6:

[0339] Once the interview is complete, the server provides the interviewer with additional information based on the sentiment analysis results. This information helps in post-interview evaluation and decision-making. Based on this information, the interviewer can make decisions based on a deeper understanding that takes the user's emotions into account.

[0340] (Application Example 2)

[0341] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0342] The challenge in online interviews is not only to eliminate gender bias and ensure fair evaluation, but also to provide a method that considers the emotions and state of the passengers and offers a comfortable experience within the mode of transport. In particular, in autonomous vehicles, there is a need to select appropriate music and videos that respond to the emotions of the passengers, but there is a problem in that there is no technology to do this efficiently and individually.

[0343] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0344] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for analyzing the passenger's emotional state and selecting and providing ambient music or video content within the means of transport. This enables passengers to use the means of transport in a relaxed and comfortable manner.

[0345] "User appearance information" refers to digital data relating to the appearance and physical characteristics of individual users.

[0346] A "gender-neutral alternative image" is a visual avatar that eliminates gender-specific characteristics and is generated to be neutral and applicable to anyone.

[0347] "User voice information" refers to digital data related to a specific user's speech and manner of speaking.

[0348] A "gender-neutral voice" is a voice that has intermediate vocal characteristics without emphasizing a specific gender.

[0349] "Methods for real-time reflection" refer to technologies that process user input information immediately and reflect the results as output instantly.

[0350] "Methods for analyzing emotional states" refer to technologies that evaluate a user's psychological state and emotions at a given time based on their facial expressions and voice.

[0351] "Means of selecting and providing ambient music or video content" refers to technology that determines the optimal music or video according to the user's emotional state and settings, and then plays it back to the user.

[0352] This invention is based on a system installed in an autonomous vehicle and aims to generate neutral alternative images and sounds by capturing the user's appearance and voice information, and to provide appropriate music and images according to the user's emotional state. This system consists of multiple components, and in particular incorporates a process for processing the user's input data and providing optimized output.

[0353] The server acquires the user's facial expression and voice information transmitted from the terminal. This information is analyzed by an AI model and converted into gender-neutral avatar images and voices. A sentiment analysis engine using TensorFlow is used for this process. The generated gender-neutral alternative images and voices are updated in real time based on the user's facial expressions and voice characteristics.

[0354] Furthermore, the server analyzes the user's emotional state and, based on the results, selects the music played through the speakers in the autonomous vehicle and the images displayed on the screen. This information processing is performed in the cloud, and the results are immediately reflected on the terminal.

[0355] For example, if a user wants to relax in the car, and the emotion analysis engine determines that the user's stress level is low, the in-car environment will switch to relaxing music. An example of a prompt to input to the generative AI model could be, "Suggest the most suitable music based on the passenger's emotional state." In this way, a comfortable experience in the car can be promoted.

[0356] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0357] Step 1:

[0358] The user's device uses its built-in camera and microphone to capture facial and audio information in real time. This input data is sent to the server in video and audio formats. The server receives this data and prepares it for analysis by an AI model.

[0359] Step 2:

[0360] The server analyzes the received facial expression and audio information through an AI model. Here, the facial expression information is analyzed using an image processing algorithm to identify facial feature points, and the audio information is converted to gender-neutral vocal characteristics by a speech recognition algorithm. As a result, gender-neutral avatar video and audio data are generated.

[0361] Step 3:

[0362] The server sends the generated neutral avatar video and audio data back to the terminal, which then reflects it to the user in real time. This data is output through the user's display and speakers. Throughout this process, the AI ​​model's emotion analysis engine continuously assesses the user's current emotions and adjusts the video and audio as needed.

[0363] Step 4:

[0364] The server uses an emotion analysis engine to understand the user's emotional state. Based on this input data, it extracts emotional parameters such as the user's stress level and happiness level, and selects ambient music and video content accordingly. This information is selected using a generative AI model based on the prompt message, "Suggest the most suitable music based on the crew's emotional state."

[0365] Step 5:

[0366] The server transmits selected music and video content to the terminal, which then plays it through the car's speakers and display. This output provides the user with an optimal environment, resulting in a comfortable user experience.

[0367] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0368] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0369] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0370] [Third Embodiment]

[0371] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0372] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0373] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0374] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0375] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0376] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0377] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0378] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0379] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0380] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0381] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0382] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0383] This invention is a system for providing an online interview environment free from gender bias. The system is primarily achieved by generating a gender-neutral avatar and voice based on the user's appearance and voice information, and then reflecting this in the interview environment.

[0384] First, the user accesses the system using a device and uploads their photo and a pre-recorded voice sample. This collects basic data about the user's appearance and voice. This data is sent to a server, where it undergoes analysis to generate a gender-neutral avatar that abstracts the user's features. This gender-neutral avatar can be adjusted according to the user's choices, allowing it to have an appearance that aligns with the user's preferences.

[0385] The server further analyzes the voice data and applies a gender-neutral voice conversion model. This converts the user's voice to a gender-neutral voice during the interview, eliminating any gender-specific characteristics. This voice conversion process is performed in real time and transmitted to the client terminal.

[0386] During the interview, the device captures the user's facial expressions and voice in real time and sends them to the server. The server immediately processes this data and reflects it in the avatar's facial expressions and movements, enabling natural communication. In this way, interviewers can interact with users without bias, ensuring a fair evaluation.

[0387] As a concrete example, consider a scenario where a job seeker participates in a remote interview using this system. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and their movements and voice are displayed in real time on the interviewer's screen as a gender-neutral avatar. This process eliminates all gender-related identification, providing an environment where the job seeker is evaluated solely on their abilities and experience. This embodiment facilitates fair evaluation and reduces the impact of gender bias.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] Users access the system via their devices and upload photos and videos as information about their appearance. This prepares the basic data used for interviews.

[0391] Step 2:

[0392] The device records a sample of the user's voice via the microphone and sends it to the server. The voice data provides information necessary for subsequent processing.

[0393] Step 3:

[0394] The server generates a gender-neutral avatar based on the received appearance information. The algorithm used here aims for a gender-neutral appearance.

[0395] Step 4:

[0396] The server analyzes the audio data and prepares it for gender-neutralization. This includes pitch adjustment and sound quality modification.

[0397] Step 5:

[0398] Once the interview begins, the device captures the user's real-time video and audio and sends it to the server. This process continues throughout the interview.

[0399] Step 6:

[0400] The server processes incoming data in real time and reflects it in the avatar's movements and facial expressions. Additionally, the voice is gender-neutralized, and the conversion results are immediately communicated to the interviewer.

[0401] Step 7:

[0402] The terminal displays a gender-neutral avatar's image and converted audio for output to the interviewer. This allows the interviewer to evaluate the user without considering their gender characteristics.

[0403] (Example 1)

[0404] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0405] In today's remote interview environment, it is difficult to eliminate gender bias that interviewers may have towards candidates. Therefore, there is a need for a system that prevents gender-based evaluations and provides fair evaluation criteria.

[0406] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0407] In this invention, the server includes means for receiving image and audio information of a user and analyzing the user's characteristics, means for using a generation model that creates a neutral surrogate image based on the characteristics, and means for using an audio conversion model that analyzes the audio information and converts it into neutral audio. This enables the generation of unbiased, neutral images and audio, allowing users to be evaluated fairly during interviews.

[0408] "Image information" refers to visual data related to the user's appearance, including photographs and videos.

[0409] "Audio information" refers to auditory data related to the user's voice, including recorded audio samples.

[0410] "Features" refer to identifiable attributes and characteristics extracted from the user's image and audio information.

[0411] A "generative model" refers to an algorithm or technique trained to generate a neutral surrogate image from input data.

[0412] A "speech conversion model" refers to an algorithm or technology designed to convert input speech into a neutral speech.

[0413] "Proxy video" refers to an avatar with a gender-neutral appearance that is generated based on the user's characteristics.

[0414] "Androgynous voice" refers to converted audio data that has a sound quality and characteristics that are not biased towards a specific gender.

[0415] An "external recipient" refers to a third party who receives neutral video or audio generated using the system.

[0416] This invention is a system aimed at eliminating gender bias in online interview environments. The system generates gender-neutral surrogate video and audio that suppresses gender bias based on image and audio information provided by the user.

[0417] Users first access the system using a device and upload their photos and audio samples. The device then sends the data received from the user to the server in an appropriate format. This data is handled using encryption methods that take privacy into consideration.

[0418] The server utilizes image processing software (e.g., OpenCV or Dlib) to process the received image information. This extracts feature points from the user's face and obtains basic data for generating a neutral surrogate image. A generative AI model is then used to generate a neutral avatar based on these features.

[0419] In processing audio information, voice analysis tools (e.g., Pyaudio and Librosa) are used to extract the characteristics of the user's voice. The server analyzes these characteristics and applies a generative AI model (e.g., Tacotron 2 and WaveGlow) to generate a gender-neutral voice.

[0420] When a user conducts an interview, their device captures their facial expressions and voice in real time and sends them to the server. The server immediately processes this data and incorporates it into the generated surrogate video and neutral audio. As a result, the interviewer's device displays unbiased, neutral video and audio in real time.

[0421] As a concrete example, consider a case where a job seeker uses this system to participate in a remote interview. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and is displayed on the interviewer's screen as a generated gender-neutral avatar. In this process, gender information is removed, creating an environment where the job seeker is evaluated solely on their abilities and experience.

[0422] Examples of prompts to input into a generative AI model:

[0423] "Please generate a gender-neutral avatar and voice based on the user's image and voice data."

[0424] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0425] Step 1:

[0426] The user uses a terminal to access the system and upload their photos and audio samples. The input data consists of JPEG images and WAV audio files. The terminal sends the received data to the server in the specified format. This inputs the user's image and audio information into the server.

[0427] Step 2:

[0428] The server receives image information and uses image processing software (e.g., OpenCV) to extract facial feature points. By analyzing the user's image and identifying facial landmarks, it obtains feature data based on the shape and arrangement of the face. This process generates intermediate data for input into the generative AI model.

[0429] Step 3:

[0430] The server uses a speech analysis tool (e.g., Librosa) to analyze the speech information. It extracts the fundamental frequency and energy of the speech data, and obtains information about the tempo and pitch of the speech. This prepares the speech feature data that should be input into the speech conversion model.

[0431] Step 4:

[0432] The server uses the generated facial feature data and a generative AI model to create a neutral surrogate image. In this process, the AI ​​model applies learned neutral parameters to output a substitute image that masks the user's features. This output is a neutral avatar image.

[0433] Step 5:

[0434] The server generates neutral speech using a speech conversion model based on speech feature data. The server then adjusts the speech features and outputs speech converted to a neutral voice quality. This output is neutral speech data.

[0435] Step 6:

[0436] During the interview, the terminal captures the user's facial expressions and voice in real time and sends them to the server. This data is reflected in the system-generated neutral voice and video. The server processes the data in real time and sends the generated neutral avatar and voice to the interviewer's terminal. This output enables a real-time communication environment.

[0437] (Application Example 1)

[0438] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0439] In online communication, gender bias is a problem that influences users' evaluations and impressions. This invention aims to provide a means to eliminate such bias and realize fair interaction.

[0440] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0441] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for the user to communicate with other users and service providers through the generated gender-neutral alternative image. This enables fair online communication that is not dependent on gender.

[0442] A "user" is an individual or group that uses the system and is the entity that provides their appearance information and voice information.

[0443] "Appearance information" refers to data related to the user's physical appearance, including photographs and video footage.

[0444] "Gender-neutral alternative images" are virtual images of users that are independent of gender attributes and are generated with the aim of eliminating gender bias.

[0445] "Voice information" refers to data related to the user's speech and voice, and includes recorded voice samples.

[0446] "Gender-neutral voice" refers to a voice that has been transformed into a gender-neutral form, and is used to eliminate the influence of gender bias.

[0447] "Facial expressions" refer to information about the user's facial movements and emotional expressions, and are data captured in real time.

[0448] "Communication" is the act of exchanging information and intentions with others and engaging in interaction.

[0449] A "service provider" is an entity that provides services to users on an online platform or in a virtual space.

[0450] The system for implementing this invention consists of a cloud-based server, a user terminal, and a communication infrastructure. Users access the system using a terminal such as a smartphone or a head-mounted display. First, the terminal acquires the user's appearance information as photos and videos and records audio information. This data is sent to the cloud server.

[0451] The cloud server analyzes received appearance information and generates a gender-neutral alternative image. Image processing algorithms and, if necessary, generation AI models are used for image generation. In addition, audio information is processed into a gender-neutral voice using a speech conversion algorithm. This provides a gender-neutral and fair communication environment.

[0452] Furthermore, when users communicate with other users or service providers, the cloud server captures the user's facial expressions and voice in real time and reflects them in a generated, gender-neutral avatar. This enables natural and smooth conversations in the virtual space. This process uses real-time image processing software and voice analysis tools. As a concrete example, consider a scenario where a user accesses an online virtual store to check product details. In this case, the user can check the product's features and usage instructions with staff through their gender-neutral avatar. A prompt such as, "Please explain how to use this product in detail from a gender-neutral perspective," allows the user to obtain a more objective and detailed explanation.

[0453] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0454] Step 1:

[0455] The user accesses the system using a terminal. First, the terminal captures the user's appearance as a photograph or video and records audio information. At this stage, the user's image data and audio data are obtained as input. As output, this data is ready to be sent to the server.

[0456] Step 2:

[0457] The server receives image data transmitted from the terminal. Upon receiving the data, the server uses image processing algorithms to generate a gender-neutral alternative image. This process includes feature extraction and face analysis, resulting in a gender-independent image based on the input image data. Generative AI models may also be used in this step.

[0458] Step 3:

[0459] The server then receives the audio data transmitted from the terminal. This audio data is analyzed using a speech conversion algorithm and converted into gender-neutral speech. The input is audio data, and the output is gender-neutral speech data. A speech analysis tool assists in this process.

[0460] Step 4:

[0461] Once a user begins communicating, the server continuously captures facial and audio data from the user in real time. This data is applied to the neutral alternative video generated in step 2 and is dynamically updated. Live data is used as input, and real-time video and audio are output.

[0462] Step 5:

[0463] Ultimately, users communicate with other users and service providers through a generated, gender-neutral avatar. They can use prompts to elicit specific information. At this stage, actual dialogue takes place, completing the interaction in the virtual space.

[0464] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0465] This invention is a system for eliminating gender bias in online interviews and enabling fairer evaluations. In addition to a function for generating gender-neutral video and audio based on the user's appearance and voice information, this system incorporates an emotion engine to recognize and reflect the user's emotions.

[0466] First, users access the system via their device and upload their photos and voice samples. The server then generates a gender-neutral avatar based on this user information. This avatar has a gender-neutral appearance and can be adjusted according to the user's preferences. Additionally, voice data is converted to a gender-neutral voice, preparing it for real-time conversion during the interview.

[0467] During the interview process, the device captures the user's facial expressions and voice in real time and sends this data to a server. The server then generates a neutral video and audio based on this data, reflecting the user's actual facial expressions and emotions. An emotion engine analyzes the user's emotional state and applies the results to the neutral avatar's facial expressions, enabling richer communication.

[0468] As a concrete example, let's consider a scenario where a job seeker uses this system to participate in a remote interview with a company. In this case, the job seeker's device captures their facial expressions and voice and sends them to the server, where an emotion engine analyzes them. Based on the analysis results, the server adjusts the avatar's facial expressions to display appropriate emotions during the interview. The neutral voice generated during this process is converted in real time, including emotional information, and transmitted to the interviewer. This allows the interviewer to evaluate the job seeker's abilities and suitability without bias.

[0469] Furthermore, the acquired emotion recognition results are used as additional information to be provided to the interviewer. This enables decision-making based on a deeper understanding. Depending on the form in which the invention is implemented, it is possible to provide a fair and neutral evaluation procedure that takes user emotions into consideration, thereby improving the fairness and quality of the interview process.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The user uses a terminal to log in to the interview system. Next, they upload photos, videos, and audio samples representing their appearance to the system. This process prepares the basic data that the system will use.

[0473] Step 2:

[0474] The server generates a gender-neutral avatar based on the appearance information obtained from the user. In this step, an AI algorithm is used to create an avatar with a gender-independent appearance.

[0475] Step 3:

[0476] The server analyzes the user's voice information and converts it to a gender-neutral voice. A voice conversion module adjusts the pitch and tone to create a voice that does not convey gender characteristics.

[0477] Step 4:

[0478] The device captures the user's real-time video and audio through its camera and microphone at the start of the interview. This data is transmitted to the server in real time.

[0479] Step 5:

[0480] The server uses an emotion engine to analyze the user's emotions from the received audio and video. This analysis is then reflected in the facial expressions of a gender-neutral avatar to express those emotions.

[0481] Step 6:

[0482] The system transmits a converted, gender-neutral voice and a gender-neutral avatar reflecting emotions to the interviewer's device in real time. This allows the interviewer to engage in emotionally conscious conversations regardless of the user's gender.

[0483] Step 7:

[0484] The server saves the emotion recognition results as logs, providing information that can be further analyzed after the interview. This allows interviewers to gain a deeper understanding of the user's emotional state during the interview.

[0485] (Example 2)

[0486] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0487] In online interviews, a system is needed to eliminate gender bias based on the applicant's appearance and voice, enabling fair and neutral evaluation. Furthermore, technology is required to accurately reflect the applicant's emotions and facial expressions during the interview, providing the interviewer with a natural expression of those emotions.

[0488] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0489] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative visual representation of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; and means for analyzing the acquired user's emotional state and reflecting the analysis results in the alternative visual representation and voice in real time. This makes it possible to eliminate gender bias and conduct fair interview evaluations that take the user's emotions into consideration.

[0490] "Appearance information" refers to information that describes the user's basic appearance and facial features.

[0491] "Neutral alternative visual representations" refer to visual representations that are neutral in appearance and do not depend on a specific gender.

[0492] "Voice information" refers to data related to the user's voice, including voice characteristics.

[0493] A "neutral voice" refers to a voice that is not biased towards the characteristics of a particular gender, but is neutral.

[0494] "Emotional state" refers to the emotional state that can be interpreted from the user's facial expressions and voice.

[0495] "Adjusting alternative visual representations" is a feature that allows users to modify the generated visual representations according to their own preferences.

[0496] "Emotional analysis results" refer to data about the user's emotions obtained through emotional analysis methods.

[0497] "Real-time" refers to processing that occurs instantly without delay.

[0498] This invention provides a system for eliminating gender bias in online interviews and ensuring fair evaluations. Users first access the system via a terminal and upload their appearance information (photos) and audio information. The server then generates a neutral alternative visual representation and voice based on the user's appearance information. The technologies used include image processing and speech synthesis. Specifically, a generative AI model is used to generate a neutral appearance and voice.

[0499] The server uses an emotion analysis engine to analyze the user's emotional state from their facial expressions and voice, obtained in real time. The data is processed immediately and reflected in neutral alternative visual representations and audio in real time. Possible emotion engines include general emotion analysis APIs and software.

[0500] As a concrete example, when a user participates in a remote interview, the user's device uses its camera and microphone to capture facial expressions and voice, and sends this data to the server. Based on the transmitted data, the server adjusts the avatar's facial expressions in real time, visually reflecting the user's emotional state. An example of a prompt message the user might give to the system is, "Analyze the user's smile and reflect it on the avatar in real time."

[0501] This system enables interviewers to fairly evaluate applicants' abilities and aptitudes, ensuring a fair and neutral interview process. Furthermore, the sentiment analysis results are used as supplementary information provided to interviewers, supporting decision-making based on a deeper understanding.

[0502] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0503] Step 1:

[0504] The user accesses the system from their device and uploads a photo and voice sample as their personal information. This input data becomes the basic information used for subsequent processing. The device sends this information to the server.

[0505] Step 2:

[0506] The server receives photos and audio samples sent by the user. A generative AI model is used to generate a gender-neutral alternative visual representation from the photos. This process utilizes image processing techniques to generate a neutral appearance that is not biased towards any particular gender. Audio samples are converted into gender-neutral voices using speech synthesis technology.

[0507] Step 3:

[0508] Once the user interview begins, the device uses its camera and microphone to capture the user's facial expressions and voice in real time. This data is continuously transmitted to the server as the interview progresses. The acquired data plays a role in instantly capturing the ambiguous emotions and facial expressions displayed by the user.

[0509] Step 4:

[0510] The server uses an emotion analysis engine to analyze the user's emotional state based on captured facial and audio data. The resulting emotional information is reflected in neutral alternative visual representations and audio in real time. This allows the avatar to express the user's true emotions.

[0511] Step 5:

[0512] The server provides the interviewer with generated, neutral alternative visual representations and converted audio in real time. At this stage, the interviewer receives emotional information from the user's neutral appearance and voice. This allows the interviewer to make an evaluation based on unbiased information.

[0513] Step 6:

[0514] Once the interview is complete, the server provides the interviewer with additional information based on the sentiment analysis results. This information helps in post-interview evaluation and decision-making. Based on this information, the interviewer can make decisions based on a deeper understanding that takes the user's emotions into account.

[0515] (Application Example 2)

[0516] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0517] The challenge in online interviews is not only to eliminate gender bias and ensure fair evaluation, but also to provide a method that considers the emotions and state of the passengers and offers a comfortable experience within the mode of transport. In particular, in autonomous vehicles, there is a need to select appropriate music and videos that respond to the emotions of the passengers, but there is a problem in that there is no technology to do this efficiently and individually.

[0518] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0519] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for analyzing the passenger's emotional state and selecting and providing ambient music or video content within the means of transport. This enables passengers to use the means of transport in a relaxed and comfortable manner.

[0520] "User appearance information" refers to digital data relating to the appearance and physical characteristics of individual users.

[0521] A "gender-neutral alternative image" is a visual avatar that eliminates gender-specific characteristics and is generated to be neutral and applicable to anyone.

[0522] "User voice information" refers to digital data related to a specific user's speech and manner of speaking.

[0523] A "gender-neutral voice" is a voice that has intermediate vocal characteristics without emphasizing a specific gender.

[0524] "Methods for real-time reflection" refer to technologies that process user input information immediately and reflect the results as output instantly.

[0525] "Methods for analyzing emotional states" refer to technologies that evaluate a user's psychological state and emotions at a given time based on their facial expressions and voice.

[0526] "Means of selecting and providing ambient music or video content" refers to technology that determines the optimal music or video according to the user's emotional state and settings, and then plays it back to the user.

[0527] This invention is based on a system installed in an autonomous vehicle and aims to generate neutral alternative images and sounds by capturing the user's appearance and voice information, and to provide appropriate music and images according to the user's emotional state. This system consists of multiple components, and in particular incorporates a process for processing the user's input data and providing optimized output.

[0528] The server acquires the user's facial expression and voice information transmitted from the terminal. This information is analyzed by an AI model and converted into gender-neutral avatar images and voices. A sentiment analysis engine using TensorFlow is used for this process. The generated gender-neutral alternative images and voices are updated in real time based on the user's facial expressions and voice characteristics.

[0529] Furthermore, the server analyzes the user's emotional state and, based on the results, selects the music played through the speakers in the autonomous vehicle and the images displayed on the screen. This information processing is performed in the cloud, and the results are immediately reflected on the terminal.

[0530] For example, if a user wants to relax in the car, and the emotion analysis engine determines that the user's stress level is low, the in-car environment will switch to relaxing music. An example of a prompt to input to the generative AI model could be, "Suggest the most suitable music based on the passenger's emotional state." In this way, a comfortable experience in the car can be promoted.

[0531] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0532] Step 1:

[0533] The user's device uses its built-in camera and microphone to capture facial and audio information in real time. This input data is sent to the server in video and audio formats. The server receives this data and prepares it for analysis by an AI model.

[0534] Step 2:

[0535] The server analyzes the received facial expression and audio information through an AI model. Here, the facial expression information is analyzed using an image processing algorithm to identify facial feature points, and the audio information is converted to gender-neutral vocal characteristics by a speech recognition algorithm. As a result, gender-neutral avatar video and audio data are generated.

[0536] Step 3:

[0537] The server sends the generated neutral avatar video and audio data back to the terminal, which then reflects it to the user in real time. This data is output through the user's display and speakers. Throughout this process, the AI ​​model's emotion analysis engine continuously assesses the user's current emotions and adjusts the video and audio as needed.

[0538] Step 4:

[0539] The server uses an emotion analysis engine to understand the user's emotional state. Based on this input data, it extracts emotional parameters such as the user's stress level and happiness level, and selects ambient music and video content accordingly. This information is selected using a generative AI model based on the prompt message, "Suggest the most suitable music based on the crew's emotional state."

[0540] Step 5:

[0541] The server transmits selected music and video content to the terminal, which then plays it through the car's speakers and display. This output provides the user with an optimal environment, resulting in a comfortable user experience.

[0542] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0543] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0544] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0545] [Fourth Embodiment]

[0546] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0547] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0548] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0550] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0552] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0553] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0554] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0555] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0556] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0557] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0558] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0559] This invention is a system for providing an online interview environment free from gender bias. The system is primarily achieved by generating a gender-neutral avatar and voice based on the user's appearance and voice information, and then reflecting this in the interview environment.

[0560] First, the user accesses the system using a device and uploads their photo and a pre-recorded voice sample. This collects basic data about the user's appearance and voice. This data is sent to a server, where it undergoes analysis to generate a gender-neutral avatar that abstracts the user's features. This gender-neutral avatar can be adjusted according to the user's choices, allowing it to have an appearance that aligns with the user's preferences.

[0561] The server further analyzes the voice data and applies a gender-neutral voice conversion model. This converts the user's voice to a gender-neutral voice during the interview, eliminating any gender-specific characteristics. This voice conversion process is performed in real time and transmitted to the client terminal.

[0562] During the interview, the device captures the user's facial expressions and voice in real time and sends them to the server. The server immediately processes this data and reflects it in the avatar's facial expressions and movements, enabling natural communication. In this way, interviewers can interact with users without bias, ensuring a fair evaluation.

[0563] As a concrete example, consider a scenario where a job seeker participates in a remote interview using this system. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and their movements and voice are displayed in real time on the interviewer's screen as a gender-neutral avatar. This process eliminates all gender-related identification, providing an environment where the job seeker is evaluated solely on their abilities and experience. This embodiment facilitates fair evaluation and reduces the impact of gender bias.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] Users access the system via their devices and upload photos and videos as information about their appearance. This prepares the basic data used for interviews.

[0567] Step 2:

[0568] The device records a sample of the user's voice via the microphone and sends it to the server. The voice data provides information necessary for subsequent processing.

[0569] Step 3:

[0570] The server generates a gender-neutral avatar based on the received appearance information. The algorithm used here aims for a gender-neutral appearance.

[0571] Step 4:

[0572] The server analyzes the audio data and prepares it for gender-neutralization. This includes pitch adjustment and sound quality modification.

[0573] Step 5:

[0574] Once the interview begins, the device captures the user's real-time video and audio and sends it to the server. This process continues throughout the interview.

[0575] Step 6:

[0576] The server processes incoming data in real time and reflects it in the avatar's movements and facial expressions. Additionally, the voice is gender-neutralized, and the conversion results are immediately communicated to the interviewer.

[0577] Step 7:

[0578] The terminal displays a gender-neutral avatar's image and converted audio for output to the interviewer. This allows the interviewer to evaluate the user without considering their gender characteristics.

[0579] (Example 1)

[0580] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0581] In today's remote interview environment, it is difficult to eliminate gender bias that interviewers may have towards candidates. Therefore, there is a need for a system that prevents gender-based evaluations and provides fair evaluation criteria.

[0582] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0583] In this invention, the server includes means for receiving image and audio information of a user and analyzing the user's characteristics, means for using a generation model that creates a neutral surrogate image based on the characteristics, and means for using an audio conversion model that analyzes the audio information and converts it into neutral audio. This enables the generation of unbiased, neutral images and audio, allowing users to be evaluated fairly during interviews.

[0584] "Image information" refers to visual data related to the user's appearance, including photographs and videos.

[0585] "Audio information" refers to auditory data related to the user's voice, including recorded audio samples.

[0586] "Features" refer to identifiable attributes and characteristics extracted from the user's image and audio information.

[0587] A "generative model" refers to an algorithm or technique trained to generate a neutral surrogate image from input data.

[0588] A "speech conversion model" refers to an algorithm or technology designed to convert input speech into a neutral speech.

[0589] "Proxy video" refers to an avatar with a gender-neutral appearance that is generated based on the user's characteristics.

[0590] "Androgynous voice" refers to converted audio data that has a sound quality and characteristics that are not biased towards a specific gender.

[0591] An "external recipient" refers to a third party who receives neutral video or audio generated using the system.

[0592] This invention is a system aimed at eliminating gender bias in online interview environments. The system generates gender-neutral surrogate video and audio that suppresses gender bias based on image and audio information provided by the user.

[0593] Users first access the system using a device and upload their photos and audio samples. The device then sends the data received from the user to the server in an appropriate format. This data is handled using encryption methods that take privacy into consideration.

[0594] The server utilizes image processing software (e.g., OpenCV or Dlib) to process the received image information. This extracts feature points from the user's face and obtains basic data for generating a neutral surrogate image. A generative AI model is then used to generate a neutral avatar based on these features.

[0595] In processing audio information, voice analysis tools (e.g., Pyaudio and Librosa) are used to extract the characteristics of the user's voice. The server analyzes these characteristics and applies a generative AI model (e.g., Tacotron 2 and WaveGlow) to generate a gender-neutral voice.

[0596] When a user conducts an interview, their device captures their facial expressions and voice in real time and sends them to the server. The server immediately processes this data and incorporates it into the generated surrogate video and neutral audio. As a result, the interviewer's device displays unbiased, neutral video and audio in real time.

[0597] As a concrete example, consider a case where a job seeker uses this system to participate in a remote interview. This job seeker uploads their photo and audio to the system in advance. During the interview, the job seeker's device sends the latest video and audio to the server, and is displayed on the interviewer's screen as a generated gender-neutral avatar. In this process, gender information is removed, creating an environment where the job seeker is evaluated solely on their abilities and experience.

[0598] Examples of prompts to input into a generative AI model:

[0599] "Please generate a gender-neutral avatar and voice based on the user's image and voice data."

[0600] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0601] Step 1:

[0602] The user uses a terminal to access the system and upload their photos and audio samples. The input data consists of JPEG images and WAV audio files. The terminal sends the received data to the server in the specified format. This inputs the user's image and audio information into the server.

[0603] Step 2:

[0604] The server receives image information and uses image processing software (e.g., OpenCV) to extract facial feature points. By analyzing the user's image and identifying facial landmarks, it obtains feature data based on the shape and arrangement of the face. This process generates intermediate data for input into the generative AI model.

[0605] Step 3:

[0606] The server uses a speech analysis tool (e.g., Librosa) to analyze the speech information. It extracts the fundamental frequency and energy of the speech data, and obtains information about the tempo and pitch of the speech. This prepares the speech feature data that should be input into the speech conversion model.

[0607] Step 4:

[0608] The server uses the generated facial feature data and a generative AI model to create a neutral surrogate image. In this process, the AI ​​model applies learned neutral parameters to output a substitute image that masks the user's features. This output is a neutral avatar image.

[0609] Step 5:

[0610] The server generates neutral speech using a speech conversion model based on speech feature data. The server then adjusts the speech features and outputs speech converted to a neutral voice quality. This output is neutral speech data.

[0611] Step 6:

[0612] During the interview, the terminal captures the user's facial expressions and voice in real time and sends them to the server. This data is reflected in the system-generated neutral voice and video. The server processes the data in real time and sends the generated neutral avatar and voice to the interviewer's terminal. This output enables a real-time communication environment.

[0613] (Application Example 1)

[0614] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0615] In online communication, gender bias is a problem that influences users' evaluations and impressions. This invention aims to provide a means to eliminate such bias and realize fair interaction.

[0616] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0617] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for the user to communicate with other users and service providers through the generated gender-neutral alternative image. This enables fair online communication that is not dependent on gender.

[0618] A "user" is an individual or group that uses the system and is the entity that provides their appearance information and voice information.

[0619] "Appearance information" refers to data related to the user's physical appearance, including photographs and video footage.

[0620] "Gender-neutral alternative images" are virtual images of users that are independent of gender attributes and are generated with the aim of eliminating gender bias.

[0621] "Voice information" refers to data related to the user's speech and voice, and includes recorded voice samples.

[0622] "Gender-neutral voice" refers to a voice that has been transformed into a gender-neutral form, and is used to eliminate the influence of gender bias.

[0623] "Facial expressions" refer to information about the user's facial movements and emotional expressions, and are data captured in real time.

[0624] "Communication" is the act of exchanging information and intentions with others and engaging in interaction.

[0625] A "service provider" is an entity that provides services to users on an online platform or in a virtual space.

[0626] The system for implementing this invention consists of a cloud-based server, a user terminal, and a communication infrastructure. Users access the system using a terminal such as a smartphone or a head-mounted display. First, the terminal acquires the user's appearance information as photos and videos and records audio information. This data is sent to the cloud server.

[0627] The cloud server analyzes received appearance information and generates a gender-neutral alternative image. Image processing algorithms and, if necessary, generation AI models are used for image generation. In addition, audio information is processed into a gender-neutral voice using a speech conversion algorithm. This provides a gender-neutral and fair communication environment.

[0628] Furthermore, when users communicate with other users or service providers, the cloud server captures the user's facial expressions and voice in real time and reflects them in a generated, gender-neutral avatar. This enables natural and smooth conversations in the virtual space. This process uses real-time image processing software and voice analysis tools. As a concrete example, consider a scenario where a user accesses an online virtual store to check product details. In this case, the user can check the product's features and usage instructions with staff through their gender-neutral avatar. A prompt such as, "Please explain how to use this product in detail from a gender-neutral perspective," allows the user to obtain a more objective and detailed explanation.

[0629] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0630] Step 1:

[0631] The user accesses the system using a terminal. First, the terminal captures the user's appearance as a photograph or video and records audio information. At this stage, the user's image data and audio data are obtained as input. As output, this data is ready to be sent to the server.

[0632] Step 2:

[0633] The server receives image data transmitted from the terminal. Upon receiving the data, the server uses image processing algorithms to generate a gender-neutral alternative image. This process includes feature extraction and face analysis, resulting in a gender-independent image based on the input image data. Generative AI models may also be used in this step.

[0634] Step 3:

[0635] The server then receives the audio data transmitted from the terminal. This audio data is analyzed using a speech conversion algorithm and converted into gender-neutral speech. The input is audio data, and the output is gender-neutral speech data. A speech analysis tool assists in this process.

[0636] Step 4:

[0637] Once a user begins communicating, the server continuously captures facial and audio data from the user in real time. This data is applied to the neutral alternative video generated in step 2 and is dynamically updated. Live data is used as input, and real-time video and audio are output.

[0638] Step 5:

[0639] Ultimately, users communicate with other users and service providers through a generated, gender-neutral avatar. They can use prompts to elicit specific information. At this stage, actual dialogue takes place, completing the interaction in the virtual space.

[0640] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0641] This invention is a system for eliminating gender bias in online interviews and enabling fairer evaluations. In addition to a function for generating gender-neutral video and audio based on the user's appearance and voice information, this system incorporates an emotion engine to recognize and reflect the user's emotions.

[0642] First, users access the system via their device and upload their photos and voice samples. The server then generates a gender-neutral avatar based on this user information. This avatar has a gender-neutral appearance and can be adjusted according to the user's preferences. Additionally, voice data is converted to a gender-neutral voice, preparing it for real-time conversion during the interview.

[0643] During the interview process, the device captures the user's facial expressions and voice in real time and sends this data to a server. The server then generates a neutral video and audio based on this data, reflecting the user's actual facial expressions and emotions. An emotion engine analyzes the user's emotional state and applies the results to the neutral avatar's facial expressions, enabling richer communication.

[0644] As a concrete example, let's consider a scenario where a job seeker uses this system to participate in a remote interview with a company. In this case, the job seeker's device captures their facial expressions and voice and sends them to the server, where an emotion engine analyzes them. Based on the analysis results, the server adjusts the avatar's facial expressions to display appropriate emotions during the interview. The neutral voice generated during this process is converted in real time, including emotional information, and transmitted to the interviewer. This allows the interviewer to evaluate the job seeker's abilities and suitability without bias.

[0645] Furthermore, the acquired emotion recognition results are used as additional information to be provided to the interviewer. This enables decision-making based on a deeper understanding. Depending on the form in which the invention is implemented, it is possible to provide a fair and neutral evaluation procedure that takes user emotions into consideration, thereby improving the fairness and quality of the interview process.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The user uses a terminal to log in to the interview system. Next, they upload photos, videos, and audio samples representing their appearance to the system. This process prepares the basic data that the system will use.

[0649] Step 2:

[0650] The server generates a gender-neutral avatar based on the appearance information obtained from the user. In this step, an AI algorithm is used to create an avatar with a gender-independent appearance.

[0651] Step 3:

[0652] The server analyzes the user's voice information and converts it to a gender-neutral voice. A voice conversion module adjusts the pitch and tone to create a voice that does not convey gender characteristics.

[0653] Step 4:

[0654] The device captures the user's real-time video and audio through its camera and microphone at the start of the interview. This data is transmitted to the server in real time.

[0655] Step 5:

[0656] The server uses an emotion engine to analyze the user's emotions from the received audio and video. This analysis is then reflected in the facial expressions of a gender-neutral avatar to express those emotions.

[0657] Step 6:

[0658] The system transmits a converted, gender-neutral voice and a gender-neutral avatar reflecting emotions to the interviewer's device in real time. This allows the interviewer to engage in emotionally conscious conversations regardless of the user's gender.

[0659] Step 7:

[0660] The server saves the emotion recognition results as logs, providing information that can be further analyzed after the interview. This allows interviewers to gain a deeper understanding of the user's emotional state during the interview.

[0661] (Example 2)

[0662] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In online interviews, a system is needed to eliminate gender bias based on the applicant's appearance and voice, enabling fair and neutral evaluation. Furthermore, technology is required to accurately reflect the applicant's emotions and facial expressions during the interview, providing the interviewer with a natural expression of those emotions.

[0664] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0665] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative visual representation of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; and means for analyzing the acquired user's emotional state and reflecting the analysis results in the alternative visual representation and voice in real time. This makes it possible to eliminate gender bias and conduct fair interview evaluations that take the user's emotions into consideration.

[0666] "Appearance information" refers to information that describes the user's basic appearance and facial features.

[0667] "Neutral alternative visual representations" refer to visual representations that are neutral in appearance and do not depend on a specific gender.

[0668] "Voice information" refers to data related to the user's voice, including voice characteristics.

[0669] A "neutral voice" refers to a voice that is not biased towards the characteristics of a particular gender, but is neutral.

[0670] "Emotional state" refers to the emotional state that can be interpreted from the user's facial expressions and voice.

[0671] "Adjusting alternative visual representations" is a feature that allows users to modify the generated visual representations according to their own preferences.

[0672] "Emotional analysis results" refer to data about the user's emotions obtained through emotional analysis methods.

[0673] "Real-time" refers to processing that occurs instantly without delay.

[0674] This invention provides a system for eliminating gender bias in online interviews and ensuring fair evaluations. Users first access the system via a terminal and upload their appearance information (photos) and audio information. The server then generates a neutral alternative visual representation and voice based on the user's appearance information. The technologies used include image processing and speech synthesis. Specifically, a generative AI model is used to generate a neutral appearance and voice.

[0675] The server uses an emotion analysis engine to analyze the user's emotional state from their facial expressions and voice, obtained in real time. The data is processed immediately and reflected in neutral alternative visual representations and audio in real time. Possible emotion engines include general emotion analysis APIs and software.

[0676] As a concrete example, when a user participates in a remote interview, the user's device uses its camera and microphone to capture facial expressions and voice, and sends this data to the server. Based on the transmitted data, the server adjusts the avatar's facial expressions in real time, visually reflecting the user's emotional state. An example of a prompt message the user might give to the system is, "Analyze the user's smile and reflect it on the avatar in real time."

[0677] This system enables interviewers to fairly evaluate applicants' abilities and aptitudes, ensuring a fair and neutral interview process. Furthermore, the sentiment analysis results are used as supplementary information provided to interviewers, supporting decision-making based on a deeper understanding.

[0678] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0679] Step 1:

[0680] The user accesses the system from their device and uploads a photo and voice sample as their personal information. This input data becomes the basic information used for subsequent processing. The device sends this information to the server.

[0681] Step 2:

[0682] The server receives photos and audio samples sent by the user. A generative AI model is used to generate a gender-neutral alternative visual representation from the photos. This process utilizes image processing techniques to generate a neutral appearance that is not biased towards any particular gender. Audio samples are converted into gender-neutral voices using speech synthesis technology.

[0683] Step 3:

[0684] Once the user interview begins, the device uses its camera and microphone to capture the user's facial expressions and voice in real time. This data is continuously transmitted to the server as the interview progresses. The acquired data plays a role in instantly capturing the ambiguous emotions and facial expressions displayed by the user.

[0685] Step 4:

[0686] The server uses an emotion analysis engine to analyze the user's emotional state based on captured facial and audio data. The resulting emotional information is reflected in neutral alternative visual representations and audio in real time. This allows the avatar to express the user's true emotions.

[0687] Step 5:

[0688] The server provides the interviewer with generated, neutral alternative visual representations and converted audio in real time. At this stage, the interviewer receives emotional information from the user's neutral appearance and voice. This allows the interviewer to make an evaluation based on unbiased information.

[0689] Step 6:

[0690] Once the interview is complete, the server provides the interviewer with additional information based on the sentiment analysis results. This information helps in post-interview evaluation and decision-making. Based on this information, the interviewer can make decisions based on a deeper understanding that takes the user's emotions into account.

[0691] (Application Example 2)

[0692] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] The challenge in online interviews is not only to eliminate gender bias and ensure fair evaluation, but also to provide a method that considers the emotions and state of the passengers and offers a comfortable experience within the mode of transport. In particular, in autonomous vehicles, there is a need to select appropriate music and videos that respond to the emotions of the passengers, but there is a problem in that there is no technology to do this efficiently and individually.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0695] In this invention, the server includes means for capturing the user's appearance information and generating a gender-neutral alternative image of the user; means for acquiring the user's voice information and converting the voice into a gender-neutral voice; means for reflecting the acquired user's facial expressions and voice in the alternative image and converted voice in real time; and means for analyzing the passenger's emotional state and selecting and providing ambient music or video content within the means of transport. This enables passengers to use the means of transport in a relaxed and comfortable manner.

[0696] "User appearance information" refers to digital data relating to the appearance and physical characteristics of individual users.

[0697] A "gender-neutral alternative image" is a visual avatar that eliminates gender-specific characteristics and is generated to be neutral and applicable to anyone.

[0698] "User voice information" refers to digital data related to a specific user's speech and manner of speaking.

[0699] A "gender-neutral voice" is a voice that has intermediate vocal characteristics without emphasizing a specific gender.

[0700] "Methods for real-time reflection" refer to technologies that process user input information immediately and reflect the results as output instantly.

[0701] "Methods for analyzing emotional states" refer to technologies that evaluate a user's psychological state and emotions at a given time based on their facial expressions and voice.

[0702] "Means of selecting and providing ambient music or video content" refers to technology that determines the optimal music or video according to the user's emotional state and settings, and then plays it back to the user.

[0703] This invention is based on a system installed in an autonomous vehicle and aims to generate neutral alternative images and sounds by capturing the user's appearance and voice information, and to provide appropriate music and images according to the user's emotional state. This system consists of multiple components, and in particular incorporates a process for processing the user's input data and providing optimized output.

[0704] The server acquires the user's facial expression and voice information transmitted from the terminal. This information is analyzed by an AI model and converted into gender-neutral avatar images and voices. A sentiment analysis engine using TensorFlow is used for this process. The generated gender-neutral alternative images and voices are updated in real time based on the user's facial expressions and voice characteristics.

[0705] Furthermore, the server analyzes the user's emotional state and, based on the results, selects the music played through the speakers in the autonomous vehicle and the images displayed on the screen. This information processing is performed in the cloud, and the results are immediately reflected on the terminal.

[0706] For example, if a user wants to relax in the car, and the emotion analysis engine determines that the user's stress level is low, the in-car environment will switch to relaxing music. An example of a prompt to input to the generative AI model could be, "Suggest the most suitable music based on the passenger's emotional state." In this way, a comfortable experience in the car can be promoted.

[0707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0708] Step 1:

[0709] The user's device uses its built-in camera and microphone to capture facial and audio information in real time. This input data is sent to the server in video and audio formats. The server receives this data and prepares it for analysis by an AI model.

[0710] Step 2:

[0711] The server analyzes the received facial expression and audio information through an AI model. Here, the facial expression information is analyzed using an image processing algorithm to identify facial feature points, and the audio information is converted to gender-neutral vocal characteristics by a speech recognition algorithm. As a result, gender-neutral avatar video and audio data are generated.

[0712] Step 3:

[0713] The server sends the generated neutral avatar video and audio data back to the terminal, which then reflects it to the user in real time. This data is output through the user's display and speakers. Throughout this process, the AI ​​model's emotion analysis engine continuously assesses the user's current emotions and adjusts the video and audio as needed.

[0714] Step 4:

[0715] The server uses an emotion analysis engine to understand the user's emotional state. Based on this input data, it extracts emotional parameters such as the user's stress level and happiness level, and selects ambient music and video content accordingly. This information is selected using a generative AI model based on the prompt message, "Suggest the most suitable music based on the crew's emotional state."

[0716] Step 5:

[0717] The server transmits selected music and video content to the terminal, which then plays it through the car's speakers and display. This output provides the user with an optimal environment, resulting in a comfortable user experience.

[0718] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0719] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0721] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0722] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0723] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0724] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0725] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0726] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0727] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0728] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0729] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0730] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0731] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0732] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0733] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0734] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0735] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0736] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0737] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0738] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0739] The following is further disclosed regarding the embodiments described above.

[0740] (Claim 1)

[0741] A means for capturing a user's appearance information and generating a gender-neutral alternative image of the user,

[0742] A means for acquiring the user's voice information and converting the voice into a neutral voice,

[0743] A means for reflecting the acquired user's facial expressions and voice in the alternative video and converted audio in real time,

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, further comprising means for allowing the user to adjust the alternative video.

[0747] (Claim 3)

[0748] The system according to claim 1, further comprising means for providing the converted audio to a third party in real time.

[0749] "Example 1"

[0750] (Claim 1)

[0751] A means for receiving image and audio information of a user and analyzing the characteristics of the user,

[0752] A means of using a generative model that creates a neutral surrogate image based on the said features,

[0753] A means of using a speech conversion model that analyzes the speech information and converts it into a neutral speech,

[0754] A means for reflecting the acquired user's facial expressions and voice in the proxy video and converted audio in real time,

[0755] A system that includes this.

[0756] (Claim 2)

[0757] The system according to claim 1, further comprising an interface that allows the user to adjust the proxy video.

[0758] (Claim 3)

[0759] The system according to claim 1, further comprising communication means for providing the converted audio to an external recipient in real time.

[0760] "Application Example 1"

[0761] (Claim 1)

[0762] A means for capturing a user's appearance information and generating a gender-neutral alternative image of the user,

[0763] A means for acquiring the user's voice information and converting the voice into a neutral voice,

[0764] A means for reflecting the acquired user's facial expressions and voice in the alternative video and converted audio in real time,

[0765] A means for users to communicate with other users and service providers through generated, neutral alternative videos,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, further comprising means for allowing the user to adjust the alternative video.

[0769] (Claim 3)

[0770] The system according to claim 1, further comprising means for providing the converted audio to a third party in real time.

[0771] "Example 2 of combining an emotion engine"

[0772] (Claim 1)

[0773] A means for capturing the user's appearance information and generating a neutral alternative visual representation for the user,

[0774] A means for acquiring the user's voice information and converting the voice into a neutral voice,

[0775] A means for analyzing the emotional state of the acquired user and reflecting the analysis results in real time in alternative visual representations and audio,

[0776] A means of providing acquired, converted audio and alternative visual representations to others in real time,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, further comprising means for allowing the user to adjust the alternative visual representation.

[0780] (Claim 3)

[0781] The system according to claim 1, further comprising means for providing the emotion analysis results to another person.

[0782] "Application example 2 when combining with an emotional engine"

[0783] (Claim 1)

[0784] A means for capturing a user's appearance information and generating a gender-neutral alternative image of the user,

[0785] A means for acquiring the user's voice information and converting the voice into a neutral voice,

[0786] A means for reflecting the acquired user's facial expressions and voice in the alternative video and converted audio in real time,

[0787] The means of analyzing the emotional state of the passengers and selecting and providing ambient music or video content within the mode of transport,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, further comprising means for allowing the user to adjust the alternative video.

[0791] (Claim 3)

[0792] The system according to claim 1, further comprising means for providing the converted audio to a third party in real time. [Explanation of symbols]

[0793] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for capturing a user's appearance information and generating a gender-neutral alternative image of the user, A means for acquiring the user's voice information and converting the voice into a neutral voice, A means for reflecting the acquired user's facial expressions and voice in the alternative video and converted audio in real time, A system that includes this.

2. The system according to claim 1, further comprising means for allowing the user to adjust the alternative video.

3. The system according to claim 1, further comprising means for providing the converted audio to a third party in real time.

Images