94results about How to "Improve human-computer interaction experience" patented technology

The invention discloses a data processing method for realizing multi-modal interaction and a multi-modal interaction system. The method comprises the following steps: receiving multi-modal input data and pre-processing the multi-modal input data; respectively analyzing the pre-processed multi-modal input data by utilizing an emotion engine, a thought engine and a self-learning engine; carrying out comprehensive decision on the basis of the analysis results so as to obtain decision data; outputting a multi-modal interaction result according to the decision data. According to the method, the intelligence of robot systems can be enhanced, the robot systems are enabled to have growth and humanization, and the man-machine interaction experience is greatly improved.

The invention relates to the technical field of mobile communication and provides a theme switching method. The method comprises the steps that matching information is obtained, wherein the matching information comprises image information of wallpaper or user feature information; a matching theme type is determined according to the matching information, and a terminal system theme or an application theme is switched into a theme corresponding to the matching theme type. The invention further provides a corresponding terminal. By means of the method, intelligence of theme switching can be achieved, the theme switching process is simplified, and the man-machine interaction experience of theme switching is improved.

The invention discloses a voice control information acquisition method under a standby state and an intelligent terminal. The method comprises the following steps: in accordance with sampling frequencies in different time periods specified by a voice collection scheme, collecting voice data; conducting characteristic matching on the voice data in accordance with preset voice command configuration data, and judging whether the voice data is a data command or not; in response to the voice command corresponding to the voice data, acquiring content information of a type corresponding to the voice command; and in accordance with the content information, associating with voice broadcast of the content information. Through processing of the voice control information acquisition method disclosed by the invention, a user can acquire information through personalized voice control when the intelligent terminal is under the standby state, so that energy consumption is reduced, and user-machine interactive experience in voice control and life and work efficiency of the user are improved.

The present invention provides a method for generating a robot interactive content, comprising: acquiring a multimode signal; determining a user's intention based on the multimode signal; combining the multidimensional signal and the user's intention, in combination with the current robot variable parameters generate robot interactive content. The invention adds the variable parameter of the robot to the interactive content generation of the robot so that the robot can generate the interactive content according to the previous variable parameter, so that the robot can be more anthropomorphic when interacting with the human being so that the robot can live shaft has a human way of life; the method can enhance the robot interactive content generated anthropomorphic, enhance the human-computer interaction experience and improve intelligence.

An embodiment of the invention provides a terminal and a method for manipulating the same. The method includes acquiring gesture graphics of users; judging whether the gesture graphics are matched with standard gesture graphics in stored graphics libraries or not; determining target control instructions from at least one stored control instruction corresponding to the standard gesture graphics if the gesture graphics are matched with the standard gesture graphics, and executing target operation instructions. The gesture graphics of the users are generated when operation is carried out on the upper side of a screen of the terminal by the users. The target control instructions correspond to the gesture graphics. The different control instructions correspond to the different standard gesture graphics. The terminal and the method have the advantages that the terminal can be manipulated in a non-contact manner, accordingly, man-machine interactive modes can be enhanced, and the experience can be improved for the users.

The invention concerns to an intelligent question-answer (Q&A) method and device, and belongs to the processing field of natural languages. The method comprises the following steps: establishing an initial business guiding model for each business scene; performing skip node complementarity optimization on the initial business guiding model to obtain a complete business guiding model; acquiring the specified user answer content matched with the machine output content stored at the current state node; performing text similarity matching on the specified user answer content and the user answer content stored at a specified skip node according to the compete business guiding model; determining the next state node of state migration according to an obtained matching result, and outputting the machine output content stored at the next state node. The business scene is modelled by intelligently analyzing the question suggested by a user, and relatively high matching accuracy rate is guaranteed according to strict text similarity matching, the free migration among various state nodes in the business scene is realized, and the intelligence is excellent.

The invention discloses a method and system for realizing human-computer interaction and belongs to the field of human-computer interaction. A main mouse body is mounted on the arm of a user through a mouse wearing device. The method comprises the following steps: when the user waves the arm, obtaining an acceleration signal through the main mouse body, and processing the acceleration signal to obtain a first processing result; according to the first processing result and the initial position of a mouse, calculating with a predefined algorithm to obtain the position information and the attitude information of the mouse; collecting an electromyographic signal of the limb surface of the user through the main mouse body, processing the electromyographic signal to obtain a second processing result, and carrying out analog-digital conversion for the second processing result to obtain a digital signal; detecting the button type according to the digital signal, wherein the key is a left key or a right key; transferring the position information and the attitude information of the mouse and the button type to a mouse interactive application device on terminal equipment to analyze the operation of the user through the main mouse body. The method can improve the human-computer interaction experience of the user and does not influence the health of the user.

The invention discloses a voice synthesis model training method and device, electronic equipment and a storage medium, and relates to the field of computer intelligent voice. According to the specificimplementation scheme, a syllable input sequence, a phoneme input sequence and a Chinese character input sequence of a current sample serve as input of an encoder of a model to-be trained, and encoding representation of all the sequences is obtained at the output end of the encoder; the method also has the following steps: fusing the three sequences represented by the codes to obtain a weighted combination of the three sequences; taking the weighted combination as the input of an attention module, and obtaining the weighted average of the weighted combination of the syllable input sequence, the phoneme input sequence and the Chinese character input sequence at each moment at the output end of the attention module; and taking the weighted average as the input of a decoder of the model to-be trained, and obtaining the voice Mel spectrum output of the current sample at the output end of the decoder. According to the embodiment of the invention, the pronunciation effect can be effectivelyimproved, and high-expressive-force and high-naturalness Chinese synthetic voice is provided for voice products.

The invention provides a refrigerator. The refrigerator comprises a refrigerator body, a door body installed on the refrigerator body, a power detection module used for detecting the power consumption loaded by the refrigerator, a display module used for displaying the power consumption information of the refrigerator, and a controller, wherein the controller is connected with the power detection module and the display module and is used for generating the power consumption information according to the power consumption and sending the power consumption information to the display module. Due to the embodiment provided by the invention, the power consumption loaded by the refrigerator can be detected in real time and the power consumption information is displayed to a user in a digital form, so that the user can see the power consumption condition clearly in real time, the brand impression of high technical content is established for consumers, and the market competition of the refrigerator is improved.

The invention relates to a display control method and system and a vehicle. The display control system is applied to the vehicle, and the vehicle comprises a vehicle-mounted display screen, wherein the vehicle-mounted display screen comprises a plurality of display areas. The display control system comprises a central processing module and an adjusting module connected with the central processing module, wherein the central processing module is used for detecting whether acquired external trigger information meets preset conditions and transmitting the external trigger information to the adjusting module when the external trigger information meets the preset conditions; the adjusting module is used for adjusting display parameters of at least one display area in the plurality of display areas of the vehicle-mounted display screen according to the external trigger information; and the display parameters at least comprise display contents. According to the technical scheme of the invention, multiple vehicle-mounted display screens do not need to be arranged in the vehicle, the cost is saved, and a driver can conveniently acquire the display content of each display area under the condition that the position is not changed, so that the condition that important information is missing due to position condition limitation is avoided, and man-machine interaction experience is improved.

The invention discloses an equipment fault defect diagnosis method based on an improved U-Net neural network. The method comprises the following steps: constructing an improved U-Net network model which contains five down-sampling network layers and five up-sampling network layers and has triple constraints; wherein the triple constraints include three-level loss constraints on a fifth upsamplingnetwork layer located at the bottommost layer, two-level loss constraints on a fourth upsampling network layer adjacent to the fifth upsampling network layer and one-level loss constraints on a firstupsampling network layer located at the topmost layer. According to the invention, defect crack position and shape prediction and generation are carried out on an original image by using an improved U-Net neural network model; 3D display interaction is carried out through a WebGL method, the precision and correctness of equipment appearance crack pixel-level prediction are further improved, meanwhile, the picture experience feeling of man-machine interaction is remarkably improved, effective recognition and precise positioning of the equipment appearance defect crack position are facilitated,and the maintenance cost is reduced.

The embodiment of the invention discloses vehicle-mounted terminal equipment, a vehicle-mounted interaction system and an interaction method. The vehicle-mounted terminal equipment comprises a speechinput unit, an image input unit, a voice output unit, a display unit, a processing unit and a communication unit. All the units conduct interactive cooperation to complete intelligent speech recognition and image recognition based on machine vision and multi-modal information interaction processing, thus accurate recognition, precise semantic understanding and personalized output of the input information are achieved, and thus the human-machine interaction experience of a user is improved.

The invention discloses a touch projection system and a touch action recognition method. The system comprises a projection unit used for projecting a picture to a preset projection touch area, adepthcamera which is used for acquiring a depth image of the hand of the user during touch control in a preset projection touch control area, an infrared camera which is used for acquiring an infrared image of the preset projection touch area, wherein the infrared image comprises the light spots, the infrared camera and the depth camera are both connected to a control unit; the control unit which is used for receiving the depth image and the infrared image and determining that an effective touch action occurs when it is judged that the first pixel position is matched with the second pixel positionaccording to the depth image and the infrared image, wherein the first pixel position is the pixel position corresponding to the light spot, and the second pixel position is the pixel position corresponding to the fingertip of the finger of the user. Therefore, the technical problem of higher false touch rate of a touch projection scheme in the prior art is solved, and the man-machine interactionexperience is improved.

The invention discloses a livestock positioning and forest grassland fire prevention monitoring system based on LoRa technology, and belongs to the technical field of information. The system is composed of a positioning node, a monitoring node, receivers, an access gateway, a cloud data system and a mobile terminal, wherein both the positioning node and the monitoring node send data to the receivers through the LoRa link; the access gateway periodically queries the status of each receiver, isolates the failed receivers and reports the status information thereof, simultaneously enables backup receivers and connects the same to the system, and uploads the record to the cloud data system; and the mobile terminal acquires corresponding data from the cloud data system according to the user request, and displays the data through the screen. The invention has the advantages of low construction, operation and maintenance cost, high robustness and good human-computer interaction experience.

The invention discloses a method and device for tracking a sound source.The method for tracking the sound source comprises the steps that S1, a sound source target is detected, and the detecting frequency of the sound source target at the moment tk and the last prediction time duration are acquired; S2, whether the sound source target is a real target or not is judged according to the detecting frequency and the last prediction time duration; S3, if the sound source target is the real target, the position information prediction value of the sound source target at the moment tk is output.According to the method and device for tracking the sound source in the embodiment, a position information detecting value and the position information prediction value at the same moment are subjected to data correlation, whether the sound source target is the real target or not can be accurately judged, therefore, interference and missing detection caused by noise, sound transmission complexity and other factors are effectively eliminated, the sound source target can be continuously and stably tracked, the accuracy and stability of a robot sound source locating system are improved, and then man-machine interaction experience is improved.

The invention discloses a capacitance detection system and method. The system comprises a capacitance sensor and a detection unit, the capacitance sensor is used for generating a first induction capacitance value and a second induction capacitance value when receiving the operation instruction. The detection unit is used for detecting a first induction capacitance value and a second induction capacitance value, calculating the first induction capacitance value and the first fixed capacitance value obtaining a first capacitance variation, calculating a second induction capacitance value and a second fixed capacitance value to obtain a second capacitance variation, determining an operation type corresponding to the operation instruction according to the first capacitance variation and the second capacitance variation, and outputting a control instruction corresponding to the operation type. By applying the system provided by the invention, the induction capacitance value of the capacitive sensor is detected, the induction capacitance value and the fixed capacitance value are calculated to obtain the calculated value, and the operation type of the operation instruction is determined according to the calculated value, so that the misjudgment on the touch screen is avoided, and the man-machine interaction experience of the touch screen is improved.

The embodiment of the invention discloses a map adjustment method and a related device, when a user needs to interact with a target application, terminal equipment acquires a target map in a display interface on a target application interface, and the target map is arranged in a first display area of the display interface. And if the user executes the triggering operation on the target map, the terminal equipment changes the target map from the first display area to a second display area, and the second display area is an area different from the first display area on the display interface. Ifit is determined that the target map is overlapped with the target object in the display interface at the moment according to the position information of the target map in the second display area, thetarget map is adjusted to a third display area, so that the adjusted target map is not overlapped with the target object, and user operation is prevented from being influenced. According to the method, the target map can automatically adapt to the position relation requirement between the objects on the display interface, repeated adjustment operation of a user is avoided, operation is rapid andconvenient, and the man-machine interaction experience of the user is improved.

The invention discloses a parking information interaction method and a user end. The parking information interaction method comprises the following steps: obtaining license plate number information input from the user end; judging whether a parking lot management system associated with the user end has parking information corresponding to the license plate number information; and when the parkinglot management system has the parking information corresponding to the license plate number information, displaying the parking information at the user end in an information dialogue mode. The parkinginformation interaction method can realize man-machine interaction between users and the parking lot management system through the user end in the dialogue mode, and meanwhile, simplifies tedious andredundant operation steps in the flow, thereby improving interactivity and enjoyment of communication between the system and the users, and improving man-machine interaction experience of the users.

The invention provides a control method of an air conditioner, a laser projection control system and an air conditioner. The control method comprises the steps that when an infrared module collects that a palm of a user is opened, a laser module is controlled to project a designated operation key to the palm of the user, and when a control instruction of the designated operation key is received, according to the control instruction, the air conditioner is controlled to run. User preset keys can be projected to the palm of the user, when the user does not need to get close to the specific area,equipment control can be achieved through operation on the palm of the user, the problem that in the prior art, due to projection to the specific area, operation is not convenient is solved, the usercontrol convenience and comfort can be improved, in addition, the designated operation key is a common key set by the user according to daily habits, compared with the manner that all keys are projected, the actual needs of the user can be met, the human-machine interaction experience can be improved, and more intelligence is achieved.

The invention provides a car headlight switch structure. The car headlight switch structure comprises a headlight switch panel, a proximity induction switch arranged in a headlight switch panel operation area and a backlight panel and further comprises a proximity induction module, a central processing module and a backlight module, wherein after the proximity induction switch is triggered for the first time, a first trigger signal is sent; the central processing module receives the first trigger signal and outputs a first backlight driving signal which lightening the backlight panel; and the backlight driving module receives the first backlight driving signal and lightening the backlight panel. The proximity induction switch is triggered, the proximity induction module in the proximity induction switch sends the first trigger signal, the central processing module sends the first backlight driving signal to drive the backlight panel to work after processing the first trigger signal, the headlight switch panel area is lightened after the backlight panel is lightened, accurate operation can be conducted on the headlight switch, human-computer interactive experience of a user is increased, and the convenience of headlight operation is improved. The invention is further provides a car with the above car headlight switch structure.