59 results about "Voice chat" patented technology

According to embodiments of the disclosure, a method, an apparatus, a device and a storage medium for live streaming interface interaction are provided. The method includes receiving a predetermined request for a live streaming interface, the live streaming interface providing, in real time, an audio-visual content associated with a target session established in a live streaming room; causing a target interface corresponding to the predetermined request to be presented; and superimposing, on the target interface, a window associated with the live streaming interface, the window at least displaying description information associated with at least one participant in the target session. In this way, with embodiments of the disclosure, it may present relevant information of a target session (e.g., voice chat or video chat) established in the live streaming room that the user is interested in, thereby improving efficiency of the user in obtaining information in the live streaming room.

A content moderation system analyzes speech, or characteristics thereof, and determines a toxicity score representing the likelihood that a given clip of speech is toxic. A user interface displays a timeline with various instances of toxicity by one or more users for a give session. The user interface is optimized for moderation interaction, and shows how the conversation containing toxicity evolves over the time domain of a conversation.

The invention discloses a virtual space social interaction engine system based on AI enhancement, and relates to the technical field of AI enhancement, the virtual space social interaction engine system constructs a multi-level and three-dimensional user portrait network structure, greatly improves the precision and dimension of user feature expression, and improves the user experience through multi-source fusion analysis of path data, physiological feature data and voice chat data. According to the method, the system can comprehensively capture dominant interests and recessive preferences of users, richer and more accurate user portraits are formed, subsequent user matching is facilitated, positive attraction factors and negative rejection factors can be considered at the same time, the matching accuracy and the satisfaction degree of user matching experience are greatly improved, and the user experience is improved. Meanwhile, by constructing a behavior feature layer, the system can dynamically adjust matching and interaction strategies according to different social scenes, and continuous optimization of system performance is achieved based on a self-adaptive optimization mechanism fed back by a user.

Disclosed is an intelligent dual-screen displayed calendar including a housing having a display provided therein, where the display is divided into a plurality of display areas; the plurality of display areas can respectively display schedule, reminders and digital photograph information, and display date and time, weather, positioning information and GPT voice chat; and a rear end face of the housing is provided with two detachable brackets which may be provided at either a first end or a second end of the housing, so that the housing may be placed on a carrier in either the transverse or longitudinal direction. A physical screen is divided into plurality of display areas, and a multi-screen function is achieved by virtual segmentation technology, which avoids adding additional hardware cost. The plurality of display areas can display the core information such as schedule and reminders.

Methods and systems are provided for generating chat communication in a video game. One method includes accessing a gameplay database that includes dialog scripts from player interactions occurring during interactive scenarios of a cooperative video game. The method includes processing the dialog scripts to extract chat words between real players during the cooperative video game and labeling the chat words to correlate the chat words to one or more interactive scenarios and correlate the chat words to a game context, wherein over time an artificial intelligence (AI) model is trained using the chat words that are labeled to learn contextually relevant chat words for the cooperative video game. The method includes identifying a non-player character (NPC), during an instance of gameplay of the cooperative video game, the NPC is present in the cooperative video game while an avatar of a real player is present in a scene of the cooperative video game. The method includes generating one or more NPC chat words for the NPC using the AI model, the NPC chat words being audible to the real player.

1. Name of the designed product: AI voice chat robot (sp-esp32-s3-1.54-muma). 2. Use of the designed product: voice inquiry and human-computer interaction. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

Disclosed herein is a Voice-Enabled AI Chat Agent, optimized for use within web browsers. This advanced AI system facilitates natural, voice-driven interactions, allowing users to engage in conversations through speech instead of traditional text input. It features a sophisticated voice recognition module, a dynamic natural language processing engine, and a versatile role adaptation mechanism, enabling it to assume various user-defined roles such as a tutor, doctor, or counsellor. Designed with an emphasis on accessibility and user-friendliness, this AI chat agent represents a significant advancement in human-computer interaction, making digital communication more intuitive and accessible for a wide range of users.

A chat execution unit configured to cause terminals used by a plurality of respective accounts that participate in one room to perform a voice chat, a setting unit configured to set, based on an operation by a user of a first account, one or more accounts in friend relation with the first account as first-state accounts for the first account, a determination unit configured to determine whether or not a predetermined condition is satisfied when an invitation operation to invite the first account to a room is performed by a user of a second account, the predetermined condition including a condition that at least one of the first-state accounts for the first account is not participating in the room, and a notification unit configured to cause a terminal used by the first account to notify that the first account is invited to the room when the predetermined condition is satisfied.

A content moderation system analyzes speech, or characteristics thereof, and determines a toxicity score representing the likelihood that a given clip of speech is toxic. A user interface displays a timeline with various instances of toxicity by one or more users for a give session. The user interface is optimized for moderation interaction, and shows how the conversation containing toxicity evolves over the time domain of a conversation.

The utility model relates to the technical field of ai voice chat assistants, in particular to an ai voice chat assistant with a flashlight function. An ai voice chat assistant with a flashlight function comprises a chat assistant body and the like. The chat assistant body is provided with an adjusting assembly, the adjusting assembly is used for clamping and fixing the chat assistant body to the collar of a user and adjusting the front and back sides of the chat assistant body, and the front and back sides of the chat assistant body are provided with lighting assemblies for providing a lighting function. The clothes can be flexibly clamped on a collar through the elastic back clamp, communication is facilitated, and the angle of the illuminating lamp a can be adjusted at night to illuminate the road surface; in a dark environment, the chat assistant body can be rotated to enable the illuminating lamp b to reach the front side, the illuminating lamp b is fixed under the action of the reset spring, and the two lamps are turned on to provide brighter illumination, so that the functionality of the chat assistant is increased through the design, and the chat assistant plays a greater role in the aspect of illumination assistance on the basis of voice interaction.

The invention provides techniques for intelligently positioning speech in a virtual environment. Factors such as user preferences, the location of virtual environment audio and / or visual events, avatar location, and others can be taken into account when selecting a suitable location for the speech. The virtual environment can be a game environment, a meeting environment, an augmented reality environment, a virtual reality environment, and the like. The invention can be implemented by an audio processing unit which may be part of a game console.

1. Name of the product in this design: AI Voice Chatbot (ESP32-S3-LCD-1.28-BOX-THIN). 2. Purpose of this design: To conduct voice inquiries and human-computer interaction. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

Implementations described herein relate to methods, systems, and computer-readable media to provide automatic translation of voice chat in virtual experiences. The automatic translation may retain context data and / or emotion data extracted from input speech received from a first user. The context data and / or emotion data may be used in translating the input speech into a second language for output to a second user at a user device.

The invention relates to an AI live broadcast method and system based on a large language model. The method comprises the following steps: generating an AI anchor in a network platform live broadcast room; creating a voice chat link with the user according to a connection request initiated by the user; converting the voice data of the user in the voice chat link into a voice question text; inputting the voice question text into a large language model, and linking the large language model to a product database; outputting a reply text by combining a large language model with a product database; and converting the reply text into audio, and replying to the user through the AI anchor. The voice question of the user is converted into the text in real time, and the personalized voice reply is generated by using the large language model, so that richer and more vivid communication experience is provided. And compared with the existing AI live broadcast based on characters, the tedious process that the user needs to typewrite to ask questions is solved, and the real-time interaction effect is improved.

Some embodiments relate to systems, methods, and computer readable media for replacing violation content in a voice chat communication in real time. In some implementations, a computer-implemented method obtains a real-time audio stream for a voice chat communication and divides the real-time audio stream into a plurality of chunks. For each block, the computer-implemented method: provides the audio of the block to a machine learning-based detection model; obtaining an indication of whether violation content exists in the audio of the block as an output of the detection model; in response to an indication that violation content exists in the audio of the block, the audio of the block is modified to mute at least a portion of the audio of the block and / or replace at least a portion of the audio of the block with a different audio. The computer-implemented method then provides the audio stream to the client device for playback at the client device, where the audio stream is provided in a delayed manner.

The present application discloses a voice chat display method and apparatus, an electronic device and a computer-readable medium. The method comprises: when a first voice chat page is displayed on a broadcaster terminal used by a broadcaster and the first voice chat page comprises multiple candidate user interfaces, displaying a gift panel after the broadcaster terminal receives a trigger operation by the broadcaster with respect to a first target interface in the candidate user interfaces; and then, after the broadcaster terminal receives a trigger operation with respect to a first adjustment control in the gift panel, adjusting, on the first voice chat page, the interface display state of at least one user interface to be adjusted in the multiple candidate user interfaces, wherein the at least one user interface to be adjusted comprises the first target interface.

1. The name of the design product: multi-person chat room graphical user interface of electronic device. 2. The use of the design product: used for displaying graphical user interface of electronic device, and the electronic device can be used for mobile phone, tablet computer, computer, smart TV or car screen. 3. The design points of the design product: the interface content of the graphical user interface. 4. The picture or photo that best shows the design points: front view. 5. The design contains colors. 6. The use of the graphical user interface: the graphical user interface is used for display on the display screen panel, and the display screen panel is an existing design, which can be selected from mobile phone, tablet computer, computer, smart TV or car screen. The front view is the room interface of voice chat room; the interface content includes the room information bar at the top, the user display in the middle and the function button at the bottom, the user display in the middle includes the invitation link for inviting other users to join the voice chat room; the interface change state figure 1 is the interface displayed after clicking the line cube icon button in the lower right corner of the front view; the interface change state figure 2 is the interface displayed after clicking the "creative workshop" button in the interface change state figure 1, and the interface content includes template type; the interface change state figure 3 is the interface displayed after clicking the "custom" template in the interface change state figure 2, and the interface content includes background, and user microphone position, expression, pattern, component, sticker, dynamic resource, etc. that can be increased, decreased and moved; the interface change state figure 4 is the interface displayed after clicking any microphone button in the interface change state figure 3.

A healthcare communications system may include a user interface device associated with a given patient in a healthcare facility and configured to listen for a voice activation command from the given patient. The healthcare communications system may also include a healthcare communications server configured to obtain medical history data associated with the given patient and determine a medical condition of the given patient based upon the medical history data. The healthcare communications server may also be configured to load an initial chatbot conversation script associated with the determined medical condition, and audibly operate a chatbot conversation with the given patient via the user interface device using the initial chatbot conversation script and based upon the voice activation command. The healthcare communications server may further be configured to generate and communicate a medical supply stocking list for the healthcare facility based upon the chatbot conversation and the determined medical condition.

A messaging system, which hosts a backend service for an associated messaging client, includes a voice chat system that provides voice chat functionality that enables users to dictate their messages, while delivering the resulting message to the intended recipient as both the associated audio and text content. When a user at a sender client device begins dictating a voice message, the voice chat system starts converting the received audio stream into text and, also, starts communicating the audio content together with the generated text to the recipient client device. The recipient user can listen to the voice message and read the text generated from the audio in real time. It is also possible for the recipient user to consume the voice message in a textual form only, if the sound at the client device is undesirable.

1. Name of the design product: Desktop robot (Zhineng Sprite). 2. Use of the design product: For voice chat interaction, daily companionship and desktop decoration. 3. Design points of the design product: In shape. 4. Picture or photo best indicating the design points: Perspective view.

The objective is to provide a new method for controlling microphone audio when multiple voice chat systems coexist. [Solution] The information processing device comprises an audio system, a microphone sound acquisition unit that acquires microphone sound, and a second voice chat system that provides a voice chat function. The audio system comprises a first audio provision unit that provides first audio data corresponding to microphone sound or second audio data corresponding to silence, and a second audio provision unit that provides third audio data corresponding to microphone sound. When the second voice chat system is running, the audio system causes the first audio provision unit to provide second audio data and the second audio provision unit to provide third audio data.

The invention provides a voice room microphone position state updating method and device, electronic equipment and a storage medium, and relates to the technical field of Internet. The method comprises the following steps: receiving and aggregating microphone position operation instruction streams pushed by a server in a preset time window; executing operation counteracting and / or operation compression processing on at least part of microphone bit operation instruction streams to generate an effective operation instruction set; the effective operation instruction sets are submitted to the microphone bit state data model in batches, and all changed microphone bit fields are updated in an atomized mode; detecting a microphone bit field through a differential binding mechanism, and sending an update notification to a view component subscribing to the microphone bit field; and updating the view components in batches to realize updating of the microphone position state. By reducing invalid instruction processing and precisely and locally refreshing, the wake-up frequency and the working time of a client CPU / GPU are reduced, and the endurance time of a terminal is prolonged; by updating the view components in batches, UI drawing is prevented from being frequently triggered, frame loss is reduced, the microphone position state switching animation is more coherent, and the visual experience of a user is improved.

The invention provides a high-efficiency intelligent pancake making robot, and relates to the field of robots, the high-efficiency intelligent pancake making robot comprises a robot main body, an auxiliary structure, an operation assembly and an operation table, the auxiliary structure is arranged in the robot main body, the operation assembly is installed in the center of the robot main body, and the operation table is installed at the front end of the robot main body. Through cooperation of the master control chip and the intelligent voice chat system, the robot can automatically complete the whole pancake making process, the operation efficiency is greatly improved, the requirement for manual intervention is reduced, pancake making every time is faster and more stable, and the production efficiency is improved. The operation assembly ensures that the height and the position of the pancake making plate can be accurately controlled in the operation process, pancakes are evenly spread, and therefore the quality of the pancakes is improved, too thin or too thick areas are avoided, the palm and fingers of the machine are designed in a human body imitating mode, the flexibility and the accuracy of the robot are enhanced, high-precision operation can be executed, and the working efficiency is improved. And unnecessary errors in the pancake making process are avoided.

The application discloses a driver fatigue awakening device and method, and relates to the technical field of voice interaction. The device comprises a vehicle terminal and a Web voice chat room module. In the vehicle terminal, an intelligent voice dialogue module is used to output dialogue text by using a large language model after receiving a voice interaction instruction of a receiving instruction issuing module. The large language model records the historical dialogue of the driver and selects a question or topic more targeted to the cognitive level of the driver as the dialogue text according to the historical dialogue. A voice synthesis module is used to convert the dialogue text into output voice. An automatic speech recognition module is used to recognize the answering voice of the driver to obtain answering text when the driver answers the output voice, and feed back the answering text to the intelligent voice dialogue module. In the case that the intelligent voice dialogue module fails to affect the driver, the Web voice chat room module is automatically switched to everyone interaction to awaken the driver. The application can relieve the fatigue state of the driver and improve the driving safety.

To allow a user to selectively perform a text chat or voice chat with an operator when a chat involving automated responses ends.SOLUTION: A dialogue control device has a function of a scenario-based chatbot and interacts with a user who uses a user terminal through an avatar. A chat screen including an avatar image is displayed on a display device of the user terminal. The dialogue control device automatically chats with the user, and when it sends the final response at the time of automated responses to the user terminal, that is, when the chat involving automated responses ends, a selection screen (200) for the user to choose a text chat or voice chat with an operator is displayed on the display device of the user terminal. The user then selects either a text chat or voice chat with the operator on the selection screen and performs the text chat or voice chat with the operator.SELECTED DRAWING: Figure 7

The invention relates to a voice packet sending method and device, a voice chat system, electronic equipment and a computer readable storage medium. The method comprises the following steps: when a user enters a chat room, performing scenario analysis on real-time chat data of the chat room to obtain scenario awareness information; generating a voice packet recommendation queue according to the context awareness information and a voice packet resource library of the user; wherein the voice packet resource library stores a voice packet exclusive to the user; obtaining a first voice packet selected by the user from the voice packet recommendation queue, and sending the first voice packet to the chat room; according to the technical scheme, the voice packet utilization rate of the user can be increased, and the user is helped to participate in interaction more naturally.

Embodiments of the application disclose a voice dialogue method and device, terminal equipment and a storage medium. The method comprises: obtaining user state information, wherein the user state information comprises first state information corresponding to a first user of the first terminal equipment and / or second state information corresponding to a second user, the second user being in a close relationship with the first user; generating dialogue content according to the first state information and / or the second state information through a dialogue model; obtaining a voiceprint feature of a target user, and generating dialogue voice according to the voiceprint feature and the dialogue content, and playing the dialogue voice. The embodiment can enhance the accompanying effect of AI voice chat provided for the user, and improve the human-computer interaction of the terminal equipment.

Disclosed is a method for operating and participating in a voice chat room subordinate to a message chat room is disclosed. The method for operating a voice chat room subordinate to a message chat room includes: managing, by a server, messages transmitted and received through the message chat room in which a first user and a second user participate; receiving, by the server, a request for creation of the voice chat room subordinate to the message chat room from the first user; creating, by the server, the voice chat room in response to the received request for creation of the voice chat room; providing, by the server, information that the voice chat room is being operated to the second user through the message chat room; providing, by the server, information that the voice chat room is being operated to the second user through a message chat room list.

A metaverse application receives encoded audio that includes a first audio stream associated with a first avatar in a virtual environment and a first voice-activity detection (VAD) signal for the first audio stream, and a second audio stream associated with a second avatar in the 3D virtual environment and a second VAD signal for the second audio stream. The metaverse application determines that the first avatar is blocked by a user associated with the user avatar. The metaverse application determines that the first VAD signal indicates that the first audio stream includes speech. The metaverse application generates additional audio. The metaverse application mixes the additional audio with the encoded audio. The metaverse application provides the mixed audio to a speaker for output.