58results about How to "Interactive intelligence" patented technology

The invention discloses a man-machine interactive system and a real-time gesture tracking processing method for the same. The method comprises the following steps of: obtaining image information of user side, executing gesture detection by a gesture detection unit to finish separation of a gesture and a background, and automatically determining a smaller rectangular frame which surrounds the hand as a region of interest in the image information through a vision algorithm; calculating the hand profile state of each frame in a video sequence by a gesture tracking unit; executing validity check on hand actions according to the calculated hand profile state, and determining the gesture action finished by the user; and generating a corresponding gesture action control instruction according to the determined gesture action, and making corresponding feedbacks by a three-dimensional user interface according to the gesture action control instruction. In the system and the method, all or part of gesture actions of the user are sensed so as to finish accurate tracking on the gesture, thus, a real-time robust solution is provided for an effective gesture man-machine interface port based on a common vision sensor.

The invention discloses a man-machine interactive system which provides an operating platform for man-machine interactive equipment to extend and even execute a human thinking expression on a machine. The man-machine interactive system comprises an input unit, a storage unit, a processing unit and an output unit, wherein the input unit is used for a user to carry out initial input of original information and confirming input of relevant information; the storage unit is used for storing a database which establishes a mapping relationship between first information characterizing user input information and second information characterizing a mapping function item; the processing unit is used for adopting the original information as a key word of the first information, retrieving the second information relevant to the first information in the database and adopting the second information as the relevant information of the original information; and the output unit is used for outputting the relevant information so as to be convenient to execute the conforming input with the user in an interactive manner. In order to execute the extended expression, a corresponding executing unit or a corresponding executing module is further needed. In addition, the invention also discloses a relevant system, a device and a method. The invention realizes the man-machine interactive mode (namely, what you think is what you get) and changes man-machine interactive habits.

The invention discloses a virtual friend conversational system and a method of the virtual friend conversational system. The virtual friend conversational system comprises a virtual friend control management service system, a core network, an access network and a terminal device. The terminal device is connected with the virtual friend control management service system through the access network and the core network. The virtual friend control management service system comprises a core management module, a monitoring and alarming module, a voice recognition synthesis module, an artificial intelligence module, a data acquisition module, a virtual friend picture synthesis module and a virtual friend expert knowledge base. The method for implementing a virtual friend conversation comprises the steps of talking connection, video communication in the talking process, talking ending and the like. The virtual friend conversational system and the method of the virtual friend conversational system partly realize a virtual reality technology, and various lifelike 3D virtual friend models are created through 3D simulation software and can communicate with real humans intelligently to assuage worries and boredom and enrich entertainment life for people.

A game engine device based on HTML5 comprises an operation environment part and a development tool part, the operation environment part comprises a scene manager suitable for processing nodes of a scene contained in to-be-processed data and converting setting of the nodes into rendering instructions, wherein the rendering instructions comprise material information; and an image rendering module which is suitable for combining rendering instructions with the same material information, and rendering by using the combined rendering instructions. Through the scheme provided by the invention, the basic characteristics of HTML5 can be supported, the platform difference is shielded, a game developer can develop a game conveniently, and the game performance and the user experience are improved.

The invention discloses a voice interaction method and device, a storage medium and a computer device. The method comprises steps of: in a learning mode, learning an interaction habit of voice interaction between different users according to a preset learning training model; and in a voice interaction mode, when the user's voice information is collected, according to the interaction habit, simulating one user who performs voice interaction with another user to respond to the voice information. The method initiates a targeted intelligent response to the voice initiating user by the learned interaction habit between the voice initiating user and the voice responding user in the learning mode, so that the interaction between the human and the machine is more intelligent and the user experience is better.

The invention discloses an automatic sketch map classification method and device. The method comprises the following steps that: independently matching contents input by the voice of a user with the sentence libraries of positive intentions, negative intentions and specific answer intentions to independently obtain a first positive intention score, a first negative intention score and a first specific answer intention score; and judging whether the first positive intention score, the first negative intention score or the first specific answer intention score achieves a first corresponding appointed score or not, and outputting a corresponding result. By use of the method, contents input by the user are classified, a system automatically replies, interaction is more accurate, manual cost isgreatly saved, and an effect of ''a continuous dialogue around the same theme'' can be achieved.

The invention discloses an intelligent lifting equipment cabinet which is composed of a human body recognition module, a movable cabinet module, a lifting cabinet carrier module and a lifting platformmodule. The human body recognition module can automatically recognize the height of a user. The lifting platform module is adjusted to the corresponding height, storing and taking information is input through a display screen on the lifting platform module. The lifting platform module can move to the height of the corresponding movable cabinet module. The movable cabinet module is carried to moveup and down, and the height of the lifting cabinet carrier module can be automatically adjusted according to the size of equipment. The problems that due to the facts that the height of a traditionalequipment cabinet is not easy to adjust and the distance between layers in the cabinet cannot be automatically adjusted according to the size of equipment, users cannot conveniently take and place the equipment, and the high-rise space is wasted are solved.

The invention discloses a message interaction method, which comprises the following steps: when a message is monitored to be received, if a current interface is an interface for receiving the message,displaying a floating interaction window on the current interface; generating an interaction prompt according to the message, and generating a corresponding number of button controls according to theinteraction prompt, the floating interaction window being used for displaying the button controls, and the interaction prompt being displayed on the button controls; and responding to an interactionoperation instruction performed on the button control, and displaying a function window corresponding to the interaction prompt on a current interface. According to the invention, the types and the number of interactive services which can be provided in the messages received by the user can be effectively improved, so that the richness and the intelligence of user interaction are further improved.The invention further provides a message interaction device and a storage medium.

The invention relates to an intelligent interaction control system and method for a vehicle, the vehicle and a storage medium. The intelligent interaction control system comprises an explicit controldevice configured to receive an explicit control instruction corresponding to a scene where a vehicle is located and control lamp effect projection display of a projection lamp installed outside the vehicle and display of an explicit screen based on explicit setting in the explicit control instruction. According to the intelligent interaction control system and method, the vehicle and the storagemedium, the interaction between the vehicle and other traffic participants can be increased and more intelligent, so that the science and technology feeling and the ceremony feeling of the vehicle aregreatly enhanced, and the user experience is effectively improved.

The invention relates to the technical field of electronic products and provides a user intelligent companion terminal apparatus and a using method thereof. The terminal apparatus comprises a rotary pedestal and a tablet personal computer; each of the top and the bottom of the rotary pedestal is provided with a rotary part; the rotary part at the top is provided with a first connecting contact, a first magnet, a protrusion and two rotary motors; the rotary part at the bottom is provided with a rotary motor therein; the bottom of the tablet personal computer is provided with a second connecting contact, a second magnet and a first groove; the magnets are connected by attracting each other, the two connecting contacts are connected, and the protrusion is installed in the first groove; the tablet personal component transmits movement instructions to the rotary motors on the rotary pedestal via the connecting contacts. With multiple sensors and according to the threshold values of light intensity and distance, the brightness of the tablet personal computer and the distance between the computer and eyes can be automatically adjusted and the vision of users can be effectively protected; the using flexibility of the tablet personal computer is combined with the intelligence and interestingness of a robot, so that the user experience of using intelligent apparatuses is improved.

The invention relates to a touch screen interaction method of an intelligent interaction handle terminal. The method comprises the following steps of: obtaining startup touch screen information; popping up a play content selection picture according to the startup touch screen information; obtaining play content selection touch screen information; and playing corresponding video content according to the play content selection touch screen information. The intelligent interaction handle terminal comprises a shell; a handle position or a handle mounting position is arranged on the shell; a touch liquid crystal screen is arranged on the shell; an intelligent chip with a multimedia play function is arranged in the shell; and the intelligent chip is connected with the touch liquid crystal screen. According to method provided by the invention, the interaction between the handle terminal and the users is more intelligent through a touch screen interaction manner, so that the troubles caused by operation key interaction are avoided, the product quality is enhanced and the service life is prolonged.

The invention relates to the technical field of power systems, and especially relates to a power grid planning-oriented visual application system. The system comprises a power grid GIS platform, a service port and a visual engine, the visual engine establishes communication connection with the power grid GIS platform through the service port; and the visual engine comprises a development graph-model corresponding unit, a visual interaction unit, a one-graph three-state unit, a deepening power grid analysis unit and a deepening space analysis unit. On the basis of the power grid GIS platform, the intelligent planning system visual engine based on the Internet of Things is built; automatic analysis on a statistical stage diagram, efficient design on a planning stage diagram, intelligent decision on the planning stage diagram and dynamic tracking on a construction stage diagram are realized, and the visual work engine suitable for developing different majors is constructed; and power distribution network planning full-service processes such as support data acquisition and treatment simplification, current situation analysis and diagnosis, load prediction and checking, intelligent siteselection and line selection, planning scheme comparison and selection argumentation, planning result display and the like are realized, and power grid analysis and space analysis are deepened.

The invention discloses a robot control method and device, electronic equipment and a storage medium and relates to the field of man-machine interaction. The robot control method and device, the electronic equipment and the storage medium are applied to a robot. The method includes the steps that identity information of a target object is collected, the identity information includes voice information and image information, the target object is a person of a first type or an animal of a second type, the state information of the target object is determined according to the voice information andthe image information of the target object, the state information of the target object includes at least one of emotion data and health data of the target object, and the action matched with the stateinformation is executed. By means of the robot control method and device, the electronic equipment and the storage medium, interaction with the target object can be more intelligently conducted by executing the action matched with the state information, and the use experience of a user is improved.

The invention belongs to the field of service robots and artificial intelligence, and particularly relates to a robot knowledge graph node updating method based on voiceprint recognition. The method mainly comprises the following steps: starting voiceprint recognition, collecting voiceprint information of a target person, querying a local or cloud database, judging whether the voiceprint information is in a knowledge graph database or not, if not, adding a new figure entity, taking the voiceprint information as an identification tag, actively asking a target person to obtain basic informationof the target person so as to add a new triple instance, reasoning the relationship between the target person entity and other entities, distinguishing different character entities, and carrying out personalized man-machine interaction selection in a targeted mode. According to the method, character entities are distinguished through voiceprint recognition, so that a robot determines different entities in conversation with the robot, entity information is actively added into a personalized knowledge graph of the robot, new triples are continuously inferred in interaction, the relationship between the entities is updated, and the knowledge graph is perfected.

The invention relates to a design method of an efficient shopping guide robot based on an SVM and an A-Star algorithm. The shopping guide robot uses a camera module to detect a client to remind the client to input a shopping intention; the shopping guide robot sends a destination to the shopping mall server through the WIFI module, the shopping mall camera collects images on a path, the SVM algorithm is used for detecting the crowd density of each area of the path, the pedestrian speed of each area is calculated according to the crowd density and the pedestrian speed model, and the pedestrianspeed is sent to the shopping guide robot. The shopping guide robot updates the A-Star evaluation function according to the pedestrian speed and searches for the shortest path, so that path planning is conducted in the shortest time mode, meanwhile, a crowded area can be avoided, and a wide area is selected to quickly arrive at a terminal point. And high accuracy of the intelligent shopping guiderobot is realized.

A vehicle-based IoT control method and device, a storage medium, and a terminal are provided. The method includes: when a user drives a vehicle, acquiring first data associated with the user or seconddata associated with the vehicle; recognizing acquired voice data to obtain a recognition result; at least according to the first data, the second data, or the recognition result, instructing the vehicle to perform data interaction with at least one terminal in the IoT. The method can enable the vehicle to interact with a terminal lcated in the same IoT of the vehicle.

The invention discloses a linkage control method and system between intelligent devices and a computer storage medium. The method comprises the steps of sensing control intention information through a first intelligent device, transmitting the control intention information to a second intelligent device through the first intelligent device, and enabling the second intelligent device to be in communication connection with the first intelligent device, analyzing the received control intention information by utilizing the second intelligent device, and generating a real-time working mode instruction corresponding to the control intention information based on an analysis result, and controlling the second intelligent device to work according to the real-time working mode instruction. The linkage control system comprises an information sensing device, an information sending device, an information receiving device, an information analyzing device, an instruction generating device and an equipment control device. Through the linkage between the intelligent massage devices, the massage products are connected in a deeper level, so that the interaction between users and the devices and between the devices is more intelligent, and the user experience is very good.

The invention provides a virtual character driving method, device and equipment based on expression recognition, and relates to the fields of artificial intelligence, deep learning, machine learning, virtual reality and the like in the computer technology. According to the method, the face image of the user is obtained in real time in the conversation between the virtual character and the user, and the target classification of the current expression of the user is accurately recognized according to the face image of the user through the base model and the multi-modal alignment model for face expression recognition; and when it is determined that the target classification belongs to a preset expression classification and currently meets a response triggering condition of the target classification, determining corresponding driving data according to a response strategy corresponding to the expression classification of the user expression, and driving the virtual character to execute a corresponding response behavior according to the driving data and a three-dimensional image rendering model of the virtual character. Therefore, the virtual character can make a timely response to the expression of the user, the personification degree of the virtual character is improved, and the interaction between the virtual character and people is smoother and more intelligent.

The embodiment of the invention provides a data processing method, electronic equipment and a computer program product. The data processing method comprises the steps that interaction data of current interaction is acquired, and the interaction data comprises at least one of voice feature data, emotion data and interaction environment feature data of an interaction object; determining a language style corresponding to the feedback voice of the current interaction according to the interaction data; determining a feedback statement text according to the language style; and converting the feedback statement text into feedback voice of a tone corresponding to the language style, so as to interact with the interaction object by using the feedback voice. The method can improve the interaction intelligence.

The embodiment of the invention discloses an information interaction method between vehicle-mounted terminals and the vehicle-mounted terminal. In the embodiment of the present invention, the first vehicle-mounted terminal triggers at least one second vehicle-mounted terminal around to establish a first relationship with the first vehicle-mounted terminal by sending a broadcast message, and establishes a second relationship with at least one third vehicle-mounted terminal. The terminal performs corresponding relationship type information interaction with at least one second or third vehicle-mounted terminal, so that the information interaction range of the vehicle-mounted terminal can be expanded, and more vehicles can intelligently exchange vehicle-mounted information, and different vehicle-mounted terminals Carry out different information interactions and properly protect private information.

An instrument calibration apparatus and a calibration method using same. The apparatus comprises a physical quantity input / output unit, a physical quantity measurement unit, a physical quantity configuration unit, a display unit, a man-machine interaction unit, a storage unit, and a control unit. The apparatus can be widely applied to automatic calibration of multivariable instruments.

The present application relates to a processing method and device for a query request, a computer device, and a storage medium. After receiving a device query request sent by a third-party device, a RCD first detects whether there is a shadow device, and if so, selects directly to send the device information of the shadow device to the third-party device or do not respond, and the shadow device responds to the third-party device; after the RCD detects that the shadow device has established synchronization with its resources, when the request of the third-party device is processed, no matter which processing method is used, the RCD can only give the third-party device the device information of the shadow device; therefore, when the third party device performs subsequent control process, only the device information of the shadow device is obtained from either the RCD or the shadow device, so the third-party device can only control the shadow device, thus avoiding the trouble of the third-party device choosing the RCD, making the human-computer interaction more intelligent, and greatly improving the quality of services.

The embodiment of the invention provides a child intention and sentiment analysis method and system. The child intention and sentiment analysis method comprises the steps that front-end equipment collects the audio information of a child, and transmits the audio information to a rear-end server; the back-end server captures audio data in the audio information at preset time intervals; the rear-endserver selects a child language habit model according to the audio data to complete voice analysis of the child; and the back-end server obtains a child intention and sentiment analysis result according to the voice analysis result. By adopting the technical scheme of the invention, the interaction effect between the child user and the intelligent equipment can be improved, and the accuracy of child intention and sentiment analysis is improved.

The invention discloses an input device based on pressure sensing, terminal equipment and an input method and belongs to the field of pressure sensing and control equipment. The input device comprisesa collection module, an acquisition module, a synthesis module and an output module, wherein the collection module is used for acquiring information of strength exerted on external input equipment; the acquisition module is used for acquiring first instruction information of the external input equipment; the synthesis module is used for converting the strength information and the first instruction information into second instruction information recognizable to the terminal equipment; and the output module is used for outputting the second instruction information to the terminal equipment. Through the input device based on pressure sensing, the strength information generated in the process that a user touches the external input equipment can be acquired, then the strength information and an operation instruction of the external input equipment are synthesized, therefore, the terminal equipment can show a response action / behavior distinct from an existing single pressure control mode ora conventional operation mode of the external input equipment according to the instruction information obtained after synthesis, and the operation mode of the terminal equipment by the user is enriched.

The invention relates to a medical order making method and device. The method comprises steps that according to different medical order types, medical indicator elements related to medical order typesare added to medical lists to form multiple types of medical lists; the type information of a to-be-made medical order is detected, one or more types of the multiple types of medical lists are calledin an interface of the to-be-made medical order and are integrated for display for use in the business edit process. The method is advantaged in that dialogues between clinic doctors and the information system are realized, and intelligent, comprehensive professional and concentrated interaction between the clinic doctors and the information system is facilitated.

The invention relates to the technical field of power systems, in particular to a visualization application system for power grid planning, comprising a power grid GIS platform, a business port and a visualization engine; the visualization engine establishes a communication connection with the power grid GIS platform through the business port; the visualization engine includes a development graph model Corresponding unit, visual interaction unit, one-picture three-state unit, deepening power grid analysis unit and deepening space analysis unit. On the basis of the power grid GIS platform, build a visualization engine of the intelligent planning system based on the Internet of Things; realize automatic analysis on the statistical stage map, efficient design on the planning stage map, intelligent decision-making on the planning stage map, and dynamic tracking on the construction stage map. Develop visual work engines of different professions; realize the whole business process of distribution network planning, such as simplifying data collection and management, status analysis and diagnosis, load forecasting and checking, intelligent site selection and route selection, planning scheme comparison and demonstration, planning results display, etc., and deepen power grid analysis and spatial analysis.

The present invention relates to a voice and image composite interaction execution method and system for a robot. The method comprises: the step 1: a robot detects the surrounding sound, and the sound source is located; the step 2, the robot detects the human faces around, the human faces are located, the location of the human faces and the location of the sound source are compared and matched, the interference sound source is filtered, the voice sound source is initially determined, and a voice command is initially determined; the step 3, the robot detects the human objects around, the human objects are tracked, the limb command is identified and is compared and matched with the initially determined voice command, the interference sound command is filtered, and the effective user command is determined; and the step 4, the robot executes the corresponding operation according to the user command. The robot is able to accurately understand the user's command in a complex background and accurately identify the user command sent to the robot, and is higher in robustness, more intelligent, and more efficient for interaction with people.

The invention provides a unified interactive robot multi-task learning method based on an attention mechanism. A model can recognize facial expressions, age distribution and gender information in an image. A unified interactive robot multi-task learning method based on an attention mechanism comprises the following steps: S1, carrying out multi-task learning by a unified deep convolutional neural network model based on the attention mechanism, and identifying facial expressions and evaluating age and gender at the same time; and S2, training and optimizing the model in the step S1: 1) setting a loss function for the model realized in the step 1), 2) inputting a data set and training the model, 3) stopping training when the model convergence or the accuracy reaches the application requirement, and S3, deploying the trained model in the step S2 to the robot.

The present application discloses an adapter, an electronic device and a wireless communication system, wherein the adapter comprises a first information acquiring unit for acquiring adapter information of the adapter and / or electronic device information from an electronic device, and a first wireless communication unit electrically connected to the first information acquiring unit and configured to perform at least one of the following operations in a wireless way: transmitting the adapter information to the electronic device, and receiving the electronic device information from the electronic device. Various information can be communicated between the adapter and the electronic device in the present application.

An interaction method for a vehicle terminal, a vehicle terminal and a server. The interaction method includes: acquiring the user's driving behavior state information; comparing the driving behavior state information with the user's driving behavior habit data; determining the driving behavior habit data corresponding to the driving behavior state information based on the comparison result; Based on the driving behavior habit data, interactive information is output to the user. The interaction method of the embodiment of the present disclosure can interact with the user according to the user's habits and driving status, making the interaction more intelligent and improving the user experience.