68 results about "Smart toys" patented technology

The invention relates to the technical field of large model semantic analysis, in particular to an AI intelligent toy multi-round automatic dialogue method based on a large model, and the method comprises the steps: obtaining a question word vector corresponding to a current round of dialogue of an AI intelligent toy, and a question word vector and an answer word vector of each round of historical dialogue, so as to calculate the related theme coherence of each round of historical dialogue, identifying candidate historical dialogues of the current round of dialogues, analyzing semantic similarity between the current round of dialogues and question vocabulary sets of all the candidate historical dialogues to obtain theme expression ambiguity of all the candidate historical dialogues, and then obtaining context criticality of all the candidate historical dialogues to extract key historical dialogues of the current round of dialogues; the method is used for constructing a message queue of a current round of conversation so as to realize multiple rounds of conversations between the AI intelligent toy and the user by using a large model. According to the invention, the accuracy of multi-round dialogues of the AI intelligent toy can be improved.

1. Name of the product under this design: Toy (Intelligent Toy Machine). 2. Purpose of this design product: toy. 3. The key design points of this design product lie in the shapes of each design. 4. The picture or photo that best illustrates the key points of the design: Design 1 three-dimensional diagram. 5. Designate Design 1 as the base design.

The invention discloses a body surface appendage form control method of an artificial intelligence toy, electronic equipment, a readable storage medium and a computer program product, and belongs to the technical field of intelligent terminals. The method comprises the following steps: acquiring target situation data, wherein the target situation data comprises at least one of the following data: interaction state data of a user, environment state data of the user, interaction state data of an artificial intelligence toy and environment state data of the artificial intelligence toy; corresponding control reference data are determined according to the target situation data, and the control reference data are used for indicating the body surface appendage form corresponding to the target situation data; and controlling the shape of the body surface appendage of the artificial intelligence toy based on the control reference data.

This invention discloses a tactical competitive data interaction method and system based on an offline physical battlefield, relating to the field of offline real-world entertainment and multi-platform client linkage technology. The method includes: players registering and binding their accounts via any mainstream mini-program or H5 client such as WeChat, Alipay, Douyin, Meituan, and Xiaohongshu; setting up minefields (including proprietary toy mines), wearable smart equipment (including smart helmets, smart vests, and smart toy guns), escape room puzzle areas, and withdrawal points on the offline physical battlefield; anti-theft tags embedded in items on the battlefield and in the minefield; and an alarm sounding when a player dies without leaving with all items; collecting player offline behavior data and synchronizing it to the server; unified settlement at the cashier, with data synchronized to various mini-programs and H5 clients; enabling data reuse, online virtual auctions for offline redemption, and lottery activities; and the system including an offline physical terminal, multi-platform clients, and a server, with the server handling data processing, algorithm calculations, and anti-theft management. This invention solves the problems of existing offline tactical competitive experiences being monotonous, inefficient in operation, prone to item loss, and insufficient online-offline linkage, enhancing player immersion and stickiness, forming a unique technological barrier, and facilitating lightweight promotion.

The invention relates to a self-adaptive voice dialogue generation system of an intelligent toy and a use method thereof, and belongs to the technical field of voice dialogues of intelligent toys, the self-adaptive voice dialogue generation system comprises a voice acquisition module, a voice recognition module, a user portrait module, a dialogue management module, a natural language generation module, a safety filtering module and a voice synthesis module, the voice acquisition module acquires user voice signals, the voice recognition module is connected with the voice acquisition module and converts the voice signals into text information, and the user portrait module establishes and dynamically updates personalized user portraits corresponding to users. The user portrait at least comprises a cognitive level quantized value, an interest preference vector and an emotion mode label which are calculated on the basis of interaction historical data. According to the method, a high-fault-tolerance voice processing chain is formed from directional pickup of a beam forming algorithm at a hardware end to a CNN-LSTM acoustic model optimized for children at a software end, so that the smoothness and the stability of an interaction process in a real children use scene are fundamentally guaranteed.

The invention discloses an intelligent toy dynamic action control method and device based on natural language understanding. According to the device, an ESP32 is used as a core controller, a microphone, a Wi-Fi module and an audio output unit are integrated, voice semantics of a user are analyzed through a cloud large model, a structured instruction containing'action types' and'parameter values' is generated, and an external execution mechanism is driven to complete physical actions. The system supports multi-expression unified response, composite instruction automatic disassembly and plug-and-play functions, and is suitable for various interactive electronic devices with motor or electromagnetic driving capability. According to the method, dynamic action response under natural language control is realized, and the method has the advantages of high interaction authenticity, high universal adaptability, no need of firmware burning and the like.

1. Name of the product in this design: Intelligent Toy (AI Dialogue Type). 2. Purpose of this design: For use in toys, enabling AI intelligent dialogue functionality. 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.

1. Name of the product in this design: Intelligent Toy Mechanism. 2. Intended use of this design: for recreational toys. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

1. The name of this design product: Smart Toy (three views). 2. Purpose of this design product: to cultivate spatial thinking and logical reasoning abilities. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the key points of the design: Refer to Figure 1 for the usage status.

The utility model discloses a light control system and an intelligent toy. The light control system comprises a brightness acquisition module, a voice acquisition module, a control chip and a light module. The brightness acquisition module acquires the brightness of the surrounding environment and feeds back a brightness signal to the control chip, and the control chip judges whether the surrounding environment becomes dark or not; when a brightness signal value transmitted by the brightness acquisition module is lower than a brightness threshold value, the control chip judges that the surrounding environment is darkened, the voice acquisition module acquires sound in the surrounding environment and feeds back a sound signal to the control chip, and the control chip judges whether the sound in the surrounding environment is uniform breath sound or not; and when the control chip judges that the sound in the surrounding environment is uniform breathing sound, the control chip controls the light module to reduce the light brightness. According to the intelligent toy, through the cooperative work of the brightness acquisition module and the voice acquisition module, the intelligent toy can automatically adjust the light brightness when detecting that the surrounding environment becomes dark and recognizing uniform breath sounds, and sleep is facilitated.

1. The name of the design product: the movement for AI intelligent toy. 2. The use of the design product: for placing inside the plush toy, providing sound and light effects, also for soothing baby children, helping sleep. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The invention is applicable to the technical field of artificial intelligence, and provides an intelligent toy control method based on semantic risk detection, which comprises the following steps: acquiring voice data of a target user, and performing voice-to-text processing on the voice data to obtain corresponding target text data; performing semantic risk analysis on the target text data through a preset semantic risk detection model, and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level tag; and based on the semantic risk analysis result and the corresponding risk level label, determining a target safety response strategy in a preset safety response strategy library, and controlling the intelligent toy to execute the target safety response strategy. The problems that an existing method depends on a universal semantic recognition and content filtering algorithm, under the condition that language expression is not standard, semantic misjudgment or missed judgment is prone to occurring, a real-time detection and intervention mechanism for voice behaviors is lacked, and potential risk behaviors cannot be actively recognized in the interaction process are solved.

The present invention relates to an intelligent system and method for analyzing, evaluating, predicting and managing the behavior and development of a child on the basis of a multi-sensor and physical AI. The intelligent method according to the present invention comprises steps in which a management device: collects health and development information about a child in a care facility, and multimodal information about the child from a multi-sensor including a plurality of intelligent CCTVs, smart toys, and wearable devices in the care facility; analyzes, evaluates and predicts, on the basis of the collected information, the behavior and development state of the child in real time by using a physical AI algorithm; and predicts customized information required for the growth and development of each child according to the results of the analysis, evaluation and prediction, thereby providing the results and the predicted customized information to a guardian terminal or an expert terminal.

The invention relates to an AI anthropomorphic robot system with multi-user independent memory ability and a method, and relates to the technical field of AI toy interaction. According to the method, through cooperation of three-layer architecture of a hardware layer, a software layer and a model service layer, the intelligent toy only equipped with one set of audio input and output equipment can provide multiple users with consecutive, personalized and personified dialogue accompanying like own exclusive equipment, and finally physical single-channel, multi-channel and multi-user interaction is achieved. According to the technical scheme, innovative experience of logic multi-session channels is achieved, the toy achieves the function of simulating sounds of other people, law compliance requirements are deeply integrated into core logic of a toy system while interactive experience is guaranteed, and real-time safety monitoring and automatic risk intervention of the interactive process are achieved.

The invention is suitable for the technical field of artificial intelligence, and provides an intelligent toy control method based on dynamic intimacy, and the method comprises the steps: responding to a feeding operation of a target user, and determining a target feeding article in the feeding operation and a corresponding feeding article type; performing multi-dimensional attribute semantic recognition on the target feeding article through a preset semantic extension model, and outputting a multi-dimensional semantic feature corresponding to the target feeding article; calculating a current intimacy value through a preset intimacy evolution strategy based on the multi-dimensional semantic features; and based on the current intimacy value, determining a target feedback strategy from a behavior strategy library of the intelligent toy, and controlling the intelligent toy to execute a corresponding action behavior according to the target feedback strategy. According to the method and the device, the problem of poor user experience caused by lack of individuation and emotional coherence of generated feeding feedback content due to lack of understanding of dimensions such as semantics, scenes and emotions when matching is performed based on general names in an existing method is solved.

1. Name of the product in this design: Doll (Big-Eyed Yellow). 2. Purpose of this design: For use in intelligent AI toy dolls. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The invention relates to the technical field of intelligent interaction of pets, and discloses an AI intelligent interaction system for pets, which comprises a pet body, a main control chip, a voice acquisition module, a display module, a sensing module, a feedback execution module, an NFC friend-making module, an offline wake-up word recognition module and an intimacy management module. The induction module is used for identifying shaking actions or touch induction received by the pets, the feedback execution module is used for outputting feedback signals, the NFC friend making module is used for triggering interaction between different pets, and the offline wake-up word identification module is used for waking up the pets without a network. The intimacy management module is used for recording the interaction behavior between the user and the pet body and calculating the intimacy. A social scene is covered through the NFC friend-making module, interaction between toys is achieved, the guidance and use threshold of green hands is lowered, and the whole scene from single-person accompanying to multi-person interaction is covered; due to the integrated design, the AI pet intelligent toy can be developed step by step, the user experience is better, and the activity of the user can be improved.

The present application relates to the technical field of children's intelligent toys, and particularly relates to a children's professional experience modular toy using NFC identification and AIGC content generation. The toy comprises a modular professional experience house, which is provided with a plurality of NFC identification points provided with RFID sensor antenna coils; an NFC interaction module, which is detachably placed on the NFC identification points and internally encapsulates an RFID electronic tag storing professional type and / or prop attribute data; and an RFID sensor, a single-chip microcomputer, a Wi-Fi module and a loudspeaker integrated in the house. The RFID sensor reads the RFID electronic tag data through the antenna coil and uploads the data to the single-chip microcomputer, the single-chip microcomputer calls a cloud AIGC model to generate a professional plot text through the Wi-Fi module, and drives the loudspeaker to perform voice broadcast. The present application solves the problems of lack of intelligent interaction, fixed content and inability to dynamically generate plots of existing children's professional experience toys, and has the advantages of modular assembly, NFC intelligent identification, AIGC dynamically generated content, support for online updates and outstanding educational value.

The invention provides a control method for an intelligent toy, and the method comprises the steps: determining whether current dialogue data is a personal information query intention or not when the current dialogue data of a user is received; if the current dialogue data is the personal information query intention, performing voiceprint extraction processing on the current dialogue data to obtain voiceprint features corresponding to the current dialogue data; determining a target short-term personal information base of the user based on the voiceprint features; and based on a target short-term personal information base, performing question and answer processing on the current dialogue data to obtain answer data, and controlling the intelligent toy to output the answer data. The problem that an existing intelligent toy cannot accurately answer personal information questions and answers is solved, and the question and answer accuracy is improved.

1. Name of the product in this design: Intelligent Toy (AI Magic Mirror). 2. Intended use of this design: for toys. 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 rendering 1.

The invention relates to the technical field of voice recognition, in particular to an AI-based multi-line intelligence development interaction method and toy, and the method comprises the steps: building a voice interaction recognition session, and carrying out the initialization after receiving a start instruction; continuously receiving audio clips and writing the audio clips into a voice feature buffer area; frame-level features are extracted from the segments to be buffered, when the accumulated length exceeds the length of a first numerical value, the sequence with the length is extracted as a batch, and a subsequent second numerical value is obtained to serve as a right-side context; segmenting the batch into sub-blocks according to a third numerical value, splicing left and right contexts for each block to form a CSC sequence, combining into a CSC feature matrix, and sending the CSC feature matrix into an acoustic model to calculate acoustic scores in parallel; detecting transient pause, triggering backtracking, stage output and state reset by using a voice activity detection model based on the score; and searching by combining viterbi with a language model to obtain a final recognition text. According to the invention, the problems of long response time delay in voice interaction of the intelligent toy, easy serial connection caused by multi-person concurrence and incoherent interaction caused by pause misjudgment can be solved.

The invention discloses a toy interaction system and method based on multi-agent coordination in the technical field of intelligent toys. The method comprises the steps that S1, an intelligent toy end and a cloud coordination server are arranged; s2, obtaining a user interaction text of a to-be-interacted user; s3, setting toy role configuration of the intelligent toy terminal; s4, analyzing according to the user interaction text to obtain a cue word mode and an output cue word template of the first interaction toy corresponding to the user to be interacted, and obtaining a cue word mode and an output cue word template of the questioning intelligent toy according to the cue word mode and the cue word template; s5, a broadcast toy terminal is obtained according to the first interaction toy and the questioning intelligent toy; and S6, performing audio broadcasting on toy interaction contents corresponding to the broadcasting toy terminal in the intelligent toy terminal based on the toy interaction sequence. Natural and smooth multi-agent dialogue experience is provided, and meanwhile richness of the toy interaction process is enhanced.

1. The name of the design product: robot (dead machine). 2. The use of the design product: for product image, such as brand IP image, advertising image, peripheral cultural and creative product image, intelligent toy or doll, intelligent robot, etc. 3. The design points of the design product: the combination of shape and pattern. 4. The picture or photo that best indicates the design points: perspective view 1. 5. The top view has been embodied in the perspective view, and the top view is omitted; the bottom view is not common, and the bottom view is omitted.

The invention is suitable for the technical field of artificial intelligence, and provides an intelligent toy control method based on dialogue analysis, and the method comprises the steps: receiving the input data of a target child user; performing acoustic preprocessing on the input data through a preset acoustics-text joint model to obtain acoustic emotion features; performing fuzzy matching and feature mapping processing on the acoustic emotion features, and outputting character feature vectors; dynamically updating the character portrait of the target child user according to the character feature vector in combination with a context memory library to obtain an updated character portrait; and according to the updated character portrait, determining a target guiding strategy in a preset guiding strategy library, and controlling the intelligent toy to execute the target guiding strategy. According to the method, the problem that the long-term character tendency of children cannot be effectively described due to the fact that in an existing method, instant emotion judgment is carried out through single matching or a single keyword, and subtle evolution of characters cannot be dynamically captured through continuous and natural dialogues is solved.

The invention provides a control method for an intelligent toy, and the method comprises the steps: determining whether the current dialogue data contains corresponding features in an emotional social knowledge base or not when the current dialogue data of a user is received; if the current dialogue data contains corresponding features in an emotional social knowledge base, a target emotional dialogue strategy of the user and a target personal information base of the user are determined, and the personal information base comprises long-term memory knowledge and short-term memory knowledge; and based on the target emotional dialogue strategy, the long-term memory knowledge and the short-term memory knowledge, performing question and answer processing on the current dialogue data to obtain answer data, and controlling the intelligent toy to output the answer data. The problems that an existing intelligent toy is single in interaction mode, and when the user emotion and the social relation are involved, guiding type answering cannot be conducted, so that answering data are inaccurate are solved.

The invention provides a control method for an intelligent toy, and the method comprises the steps: determining whether the current dialogue data is an aggressive language or not when the current dialogue data of a user is received; if the current dialogue data is an aggressive language, controlling the intelligent toy to enter an emotional dialogue mode, and marking the user as an attack state; and when the user is in the attack state, determining a first target emotional dialogue strategy based on the current dialogue data and the emotional dialogue mode, and controlling the intelligent toy to output answer data corresponding to the current dialogue data according to the first target emotional dialogue strategy. The problems that an existing intelligent toy is single in interaction mode, and when a user is in a poor emotion state, time needed by the emotion of the user is not considered for digestion, so that accompanying somatosensory is poor are solved.

The invention discloses a game agency method for virtuality and reality combined intelligent toys, which is used for effectively connecting and interacting AI intelligent toys with element universe and network games and solving the problem of interaction separation between physical toys and virtual games. The core innovation is as follows: on the aspect of the entity layer, a multi-form toy (plush bear / worker toy) is integrated with a heat-sensitive material and a magnetic sensor to acquire entity actions such as embracing and shaking; in the mapping layer aspect, entity actions are mapped into virtual game atomic operations through a declarative proxy protocol, and an entropy filter (less than or equal to 3 times per second) is implanted to avoid plug-in judgment; in a virtual layer aspect, a proxy source (such as "worker toy proxy construction") is declarated in a game interface, and a virtual state is synchronously fed back through vibration / LEDs. Virtuality and reality are combined, the efficiency of user operation Minecraft is obviously improved, the game participation degree of autism children is effectively improved, and five types of virtual platforms such as Roblox and the like are compatible.

A rotary display toy based on persistence of vision relates to the field of intelligent toys and comprises a base, a controller, a rotator, a transparent disc and a lamp strip. The controller and the lamp strip are embedded into the transparent disc and fixedly matched with the transparent disc, and the controller is electrically connected with the lamp strip and used for controlling the content displayed by the lamp strip; the rotator is fixed to the base, the transparent disc is installed on the rotator, and the rotator is used for driving the transparent disc, the lamp strip and the controller to rotate relative to the base. According to the structural design of the display toy, the safety can be improved, the service life of the light bar is prolonged, and the compactness of the whole structure is improved.