177results about How to "Interactive friendly" patented technology

The invention relates to an embedded type speech emotion recognition method and an embedded type speech emotion recognition device. The method comprises a feature extraction method, an emotion model training method, a Gaussian mixture model and an emotion recognition method. The method is as follows: parameters of a speech emotion recognition model can be adjusted in a self-adoption manner according to the recognition result of a speaker module, and an unspecific speaker speech emotion recognition question is transformed into a specific speaker speech emotion recognition problem. The device comprises a central processor, a power supply, a clock generator, a Nand Flash storage, a Nor Flash storage, an audio coding-decoding chip, a microphone, a loudspeaker, a keyboard, an LCD (Liquid Crystal Display) display and an USB (Universal Serial Bus) interface storage. According to the embedded type speech emotion recognition method and device, a speaker recognition model is added to the speech emotion recognition, and therefore, the problem that the speech emotion recognition is suddenly declined under an unspecific speaker condition is solved, and the identity recognition function is brought to the device.

The invention provides a method and system for parameter optimization of a machine learning algorithm. The method comprises the steps: (A), determining the machine learning algorithm for training a machine learning model; (B), providing a graphical interface for a user to set a parameter adjustment configuration item of the machine learning algorithm, wherein the parameter adjustment configurationitem is used for limiting how to generate multiple groups of candidate algorithm parameter values; (C), receiving an input operation of a user for setting the parameter adjustment configuration itemon the graphical interface, and obtaining the parameter adjustment configuration item set by the user according to the input operation; (D), generating multiple groups of candidate algorithm parametervalues based on the obtained parameter adjustment configuration item; (E), training a machine learning model corresponding to each group of candidate algorithm parameter values under each group of candidate algorithm parameter values according to the machine learning algorithm; (F), estimating the effect of the trained machine learning model corresponding to each group of candidate algorithm parameter values.

The invention discloses a 422 bus solid-liquid power aircraft flying control testing system. The 422 bus solid-liquid power aircraft flying control testing system comprises a main control testing platform, a portable measurement and control box, a flying control computer, an emulation computer and an interface machine; the main control testing platform provides a human-computer interaction interface and sends a testing command to a flying control computer; the portable measurement and control box outputs the testing command to the flying control computer after performing isolation transferring on the testing command signal to achieve flying control computer power supply, analog acquisition output and switching value signal input and output channel functions; the flying control computer performs sub-system testing and control to perform flying control algorithm resolving and generate into rudder deflection control quantity; the emulation computer simulates the aircraft to perform model real-time resolving; the interface machine perform data fusion and sending. The 422 bus solid-liquid power aircraft flying control testing system can achieve full-system semi-real-object testing, comprehensive monitoring of bus information, real-time storage and display of data, obtains possible conditions during flying to examine in advance and lays foundation for smooth execution of flight tests.

The invention discloses an ARM temperature and humidity self-correction based electromagnetic radiation measuring device and a measuring method. The ARM temperature and humidity self-correction based electromagnetic radiation measuring device comprises an electromagnetic radiation sampling module, a signal processing module, a temperature and humidity digital sensor, an embedded type micro-processor module, a memorizer and a display module; the embedded type micro-processor module is respectively connected with the signal processing module, the temperature and humidity digital sensor, the memorizer and the display module; the signal processing module is connected with the electromagnetic radiation sampling module. According to the ARM temperature and humidity self-correction based electromagnetic radiation measuring device, environment temperature and humidity influences to a measuring result are considered meanwhile the environmental electromagnetic radiation intensity is measured, the measuring result is corrected in real time through an artificial neural network model, the measuring result authenticity and accuracy is guaranteed, environmental limit to utilization conditions of instruments is effectively widened, measurement can be performed under the severe environment, and the device automatically stops working to avoid instrument damage when the environment temperature and humidity exceeds a threshold value.

A “Pre-Touch” pointer method and apparatus for facilitating data entry and control of touch-screen devices. As a user hovers finger(s) above a touch-screen device (before making contact), plurality of sensors detect the finger and based on the physical location of the finger, create a pointer that is offset from the location of finger (to prevent obstruction). Said pointer helps a user target the precisely desired target location by reducing its size as finger(s) approaches the screen. When contact is made by finger(s), the location of said offset pointer remains the same, but it could become invisible—to help prevent obstruction. Its properties can also change to help better visualize or interact with touch-screen devices.12

The invention discloses a ship-lock multi-channel water level measuring system and a filter method thereof. The ship-lock multi-channel water level measuring system comprises a multi-water level sensor, a data acquisition module, a remote motoring PC (Personal Computer) machine, a GSM (Global System of Mobile communication) module, a communication network, and the like. The ship-lock multi-channel water level measuring system is characterized by monitoring the water levels of multiple measurement points, namely ship-lock upstream and downstream, a lock chamber, and the like, in real time by taking a singlechip as a lower microcontroller and using a high-accuracy A / D (Analog to Digital) convertor, packing and reforming multipath data and then remotely transmitting to an upper monitoring PC machine by utilizing a 485 bus to display the water level values of the measurement points in real time, transmitting water level information to a certain mobile phone subscriber through a GSM short message module and a wireless network thereof and supporting the mobile phone subscriber to actively take the water level values of the measurement points at any time by utilizing the GSM network. The ship-lock multi-channel water level measuring system disclosed by the invention is easy to realize the advantage of absolute stability by adopting an FIR (Finite Impulse Response) filter based on the median filter of the singlechip and has the advantages of low cost, high accuracy and anti-interference capacity and friendly human-computer interaction.

A steady-state evoked potential brain-computer interface method based on motion turning vision sensing comprises the steps of arranging an electrode on the head of a user, measuring brain electric signals and sending the measured brain electric signals to a computer, then simultaneously showing newton ring motion stimulating units to the user by a computer screen, in the stimulation showing process, contracting and expanding the newton ring motion stimulating units according to a sine modulation mode so as to form periodical reciprocating motion in two directions, after the newton ring motion stimulating units are formed, enabling the user to stare any one of the newton ring motion stimulating units, synchronously acquiring a stimulating start position and a stimulating end position by the computer, acquiring the brain electric signals by a test electrode, calculating a stimulating target with the maximum related coefficient, judging and indicating the target through the screen, and then executing the next target recognizing task. The steady-state evoked potential brain-computer interface method has the characteristics of low flickering rate and low adaptability, can not result in visual fatigue of the user and the reduction of brain response signals, and is suitable for occasions needing brain-computer interaction for a long time.

The invention discloses a Spark-based data processing method and system. The method comprises the following steps of: 1) selecting operators by a user according to a requirement of a to-be-processed document, configuring parameters of the selected operators, establishing a connection relationship of the selected operators and generating an XML file of a scene, wherein the XML file of the scene comprises XML content of each selected operator and the connection relationship of the operators; 2) generating a corresponding directed acyclic graph DAG according to the XML file of the scene; and 3) segmenting the directed acyclic graph DAG into a plurality of subtasks subJob which can be executed under distributed calculation environment, and executing the segmented subtasks subJob under a Spark calculation framework so as to process the to-be-processed document. The method and system are capable of realizing butt joint of various pieces of data, so that the data processing flexibility is improved.

The embodiment of the invention discloses a movie visualization processing method and system based on content. The method includes the steps that audio-video information of a movie is extracted and subjected to structural processing, and corresponding audio-video structural content information is obtained; movie semantic boundaries are detected according to the audio-video structural content information of the movie, the movie is divided into content-independent plots, a semantic subject is summarized, and movie plot information is concluded; a visualization frame is built according to the movie semantic boundaries, the concluded movie plot information and the corresponding audio-video information, and a visualization interface is generated. According to the movie visualization processing method and system in the embodiment, the content and the integral structure of the movie is intensively presented in a multi-angle mode through video semantic division and plot summarizing, the user interaction is friendly, a user is effectively assisted in rapidly catching the important plots of the movie and understanding the style and the subject of the movie, and the movie screening efficiency and the use experience feeling of the user are improved.

Provided is a steady motion visual evoked potential brain computer interface method based on stochastic resonance enhancement. First, an electrode is arranged on the head of a user, a detected electroencephalogram signal is sent to a computer, then movement stimulating units are presented in front of the user through a computer screen at the same time, the movement stimulating units are shielded by two-dimensional noise points obeying Gaussian distribution, the noise point update frequency is synchronized with the screen refresh rate, and the noise strength is represented by Gaussian distribution standard deviation. After the movement stimulating units are formed, the user watches any one of the movement stimulating units, a computer acquires a stimulation starting flag bit and a stimulation finishing flag bit, a computer signal is acquired through a test electrode, the significance probabilities of different stimulation targets are calculated, the targets are judged and indicated through the screen, and then the next target identification is conducted. The steady motion visual evoked potential brain computer interface method based on stochastic resonance enhancement can remarkably enhance brain response strength of the user, improve precision and efficiency of an existing brain computer interface, and innovatively improve practical level of the brain computer interface technology.

Various embodiments of the present invention provide systems and method for behavior determination. As an example, a system for behavior determination is disclosed that includes: a first monitoring device, a second monitoring device, and a monitoring system. The monitoring system is operable to: receive information from the first monitoring device; receive information from the second monitoring device; identify at least a first zone around the first monitoring device; identify at least a second zone around the second monitoring device; and characterize an intersection of the first zone and the second zone.

The invention discloses a carbon dioxide concentration-corrected exhaled gas multi-component detection instrument and detection method. The detection instrument comprises a filter flask, a carrier gas pump, a drying pipe, a sampling gas pump, a sample ring, a first two-phase three-way solenoid valve, a second two-phase three-way solenoid valve, a third two-phase three-way solenoid valve, a chromatographic column and a detection gas chamber, and after communication, a sampling passage, a washing passage and a detection passage are respectively formed. The detection gas chamber is of a cuboid structure and is provided with a PCB tank, a MOS tank, a carbon dioxide sensor tank, a temperature measuring hole, a gas reaction chamber and the like. A sensor can quickly give a response and restore a baseline; after the outputted response is subjected to signal processing and calculation, hydrogen and methane concentrations are obtained and can be corrected according to carbon dioxide concentration, so that sample acquisition constraints are reduced, and the error caused by breath collection and other human factors is reduced. The carbon dioxide concentration-corrected exhaled gas multi-component detection instrument is perfect in functions, small in size, simple and convenient to operate, higher in accuracy, stability and repeatability and friendly in user interaction, and facilitates popularization of large-scale clinical application.

The invention discloses an underground garage for reasonably controlling parking space allocation and parking space occupied spaces. The underground garage comprises a main building basement and an external underground garage area located on the outer side of the main building basement, the external underground garage area is provided with a first traffic lane area, a second traffic lane area, a miniature vehicle parking area, a medium-sized vehicle parking area and a large vehicle parking area, and the medium-sized vehicle parking area and the large vehicle parking area are arranged between the first traffic lane area and the second traffic lane area; the main building basement is provided with an upper layer space and a lower layer space, the upper layer space is provided with a storeroom, the lower layer space is provided with a main parking area or an equipment area, the joint position of the main building basement and the external underground garage area is provided with a self-walking parking area, and parking space dynamically allocating and computing systems are arranged on the external underground garage area and the lower layer space. According to the underground garage, the underground garage is reasonably partitioned, the area occupied by vehicles is reduced, the size of garage column grids is effectively controlled, and the problem that an existing three-dimensional garage cannot achieve dynamic distribution of unoccupied parking spaces is solved.

The invention provides a full-digital high-power plasma arc precise cutting system which comprises a power circuit, a control circuit, a high-frequency arc starter module, a coupling reactance module, a plasma arc cutting gun, a cooling system, an air compressing system and a cutting traveling mechanism. The high-frequency arc starter module, the coupling reactance module and the plasma arc cutting gun are sequentially connected. The control circuit is connected with a three-phase alternating current input power supply, the power circuit and the high-frequency arc starter module. The input ends of the cooling system, the air compressing system and the cutting traveling mechanism are connected with the control circuit, and the output ends are connected with the plasma arc cutting gun. One end of the power circuit is connected with the three-phase alternating current input power supply, and the other end is connected with the coupling reactance module. By means of the system, power enhancing and electric energy efficient conversion and reliable transferring are achieved, a full-digital control technology and a visual man-machine interaction technology based on a structure of advanced reduced instruction set computer machines (ARM)+RA8875+touch screen are introduced in the system, control precision and operability of the system are improved.

The invention relates to an adjustable low-frequency pulse electromagnetic instrument for treating dysphagia, comprising a power module, a stimulation signal generation module and a man-computer interaction module. The power module is connected with the stimulation signal generation module, one end of the man-computer interaction module is connected with the stimulation signal generation module, the other end of the man-computer interaction module is connected with the power module, and the stimulation signal generation module outputs specific adjustable low-frequency pulse electromagnetic signals for treating the dysphagia. When in use, stimulation signals are output to act on parts of a human body needing to be treated through two sets of six stimulation electrodes, the stimulation signal generation module is controlled, parameters such as stimulation signal groups, types, stimulation times and stimulation strengths are regulated, and the requirements of different patients to the stimulation signals are realized. Clinical tests show that in the environment with specific strength and frequency generated by the low-frequency pulse electromagnetic signals, the invention has better effect for treating the dysphagia by stimulating for 30-60min per time and treating 10-14 times on the average.

A method and system for generating a combined feature of a machine learning sample are provided. The method includes the steps of (A) acquiring unit features that can be combined; (B) providing a userwith a graphical interface for setting a feature combination configuration option that is used for defining how to perform feature combination among the unit features; (C) receiving an input operation performed by the user on the graphical interface in order to set the feature combination configuration option, and acquiring the feature combination configuration option set by the user according tothe input operation; and (D) combining the features to be combined in the unit features based on the acquired feature combination configuration option to generate a combined feature of a machine learning sample. According to the invention, the user only needs to set the related configuration option for defining how to perform feature combination through the interactive interface, then the automatic feature combination can be realized, the user experience is improved, and the effect of the machine learning model is also enhanced.

The invention discloses a method and a system for opening an animation with an entity, is suitable for iOS and OS X platforms and relates to the technical field of networks. The method comprising the steps of: creating pictures of an entity and a plurality of layers for loading the pictures, each of the pictures showing at least one side surface of the outer surface or inner surface of the entity; setting the loading order and the animation effect of the picture loaded in each layer and the pictures in the specified layers; stacking all the layers, setting the animation execution order of the specified layers, displaying the three-dimensional graph of the entity in the closed state when all the layers begin to load the pictures, and displaying the three-dimensional graph of the entity in the opened state after all the pictures in the specified layers are loaded. The method and the system are easy to implement, the workload of the designer is greatly reduced, and the method and the system are suitable for various scenes of opening the entity and meet the customized demands of the user.

The embodiment of the invention discloses a set-top box browser control focus skip method, which comprises the following steps of: receiving key message; converting the key message into a standard key event of a browser; shunting the message; searching the last focus by calculating the priorities of all alternative focuses ahead of the current focus to find the focus with highest priority as the last focus; setting the acquired focus with highest priority as the current focus to complete focus skip processing; setting the focus by directly adopting a standard default mode of the browser to complete focus skip processing; searching the next focus by calculating the priorities of all alternative focuses behind the current focus to find the focus with highest priority as the next focus; and setting the acquired focus with highest priority as the current focus to complete focus skip processing. Through the embodiment, accurate skip of upper and lower keys is realized, the browser provides friendly user interaction, and the satisfaction of a user is effectively improved.

The invention discloses a method and equipment for displaying large-scale three-dimensional reconstruction scenes in real time. The method comprises the following steps of: taking a point cloud model or triangular mesh model of a large-scale three-dimensional reconstruction scene as input data; constructing multilayer detail model data of the three-dimensional scene through forked tree processing; and reading corresponding model data by a processor of the equipment to be processed according to the method, and outputting the processing result to a display interface in real time to be displayed. According to the method, data is processed through a forked tree, the processing speed is at an index level, so that the limits of computer memories can be overcome, the point cloud or triangular mesh-based large-scale three-dimensional reconstruction scenes can be displayed in real time, and a favorable interaction function is provided. The method and the equipment are not limited to three-dimensionally reconstructed scene models, are also suitable for the other three-dimensional point cloud or triangular mesh models with large data volumes, and have strong theoretical significance and broad application prospect.

The invention relates to a novel menu of a foot action of an interaction control method based on a foot posture and an action, called FootMenu. The novel menu of the foot action is composed of a flexible sensor 1, a control module 2, a communication module 3, a power module 4 and matched terminal software 5, wherein the flexible sensor 1 takes charge of sensing and capturing pressure information of feet of a user and digitalizing the pressure signal; the control module 2 takes charge of collecting, analyzing and managing the signal, and transmitting and executing corresponding computer instruction through internal program; the communication module 3 takes charge of data exchange of the instruction signal and the terminal device; the power module 4 provides action power of the flexible sensor 1 and each module, and the three modules are highly integrated. The novel menu coordinates with a knock action of the foot to the ground to select the menu by utilizing rotary information of a heel, and carries out two functions of quick instruction operation by inducing pressure of different positions of a sole on the ground.

The invention discloses an optical-fiber-waveguide automatic alignment coupling instrument based on image processing, and belongs to the technical fields of optical fiber communication and optical fiber sensing. The optical-fiber-waveguide automatic alignment coupling instrument based on image processing includes an image acquisition module, an image processing and control module, a motion execution module and a man-machine interaction module, wherein the motion execution module includes a pigtail filler block, a Y waveguide element, a six-dimensional electric displacement table, a motor control panel, two sets of hand-operated displacement tables and the like, wherein the image processing and control module includes a processor, a storage module, a communication interface and a display module; and the image acquisition module acquires side surface images and end surface images with clear definition, and then the motion execution module extracts the edge feature straight lines from theside surface images with clear definition and calculates the relative deviation after the side surface images and end surface images are processed by the image processing and control module, then eliminates the deviation to realize initial light, determines the output point position and controls the maximum gray value of the output light point to achieve automatic alignment coupling of the fiber-Y waveguide. The optical-fiber-waveguide automatic alignment coupling instrument based on image processing has the advantages of small volume, low cost, friendly man-machine interaction and high operation speed, and can avoid long time operation of artificial alignment.

The invention relates to partial discharge detection of three-phase power cable insulation in a metal sheath crossing interconnection mode, and provides a power cable partial discharge detection system based on ultrahigh-frequency and high-frequency current combination for diagnosing and recognizing the insulation partial discharge defect of the power cable. Therefore, the technical scheme adoptedby the invention is that the power cable partial discharge detection system based on the combination of UHF and HFCT comprises an ultra-high frequency signal acquisition unit, and a data acquisitionand transmission unit, which are sequentially in series connection; a high-frequency signal acquisition unit, a data acquisition and transmission unit, which are sequentially in series connection; a host computer and a wireless synchronization module. The method is mainly applied to partial discharge detection of phase power cable insulation.

The invention discloses an intelligent wheelchair control and route optimization method based a on visual evoked brain-computer interface. The method comprises the following steps: presenting a Newton's ring to a user who sits on a wheelchair as a motion stimulating unit; acquiring and processing electroencephalogram signals of the user; recognizing out a stimulating target which is currently gazed at by virtue of a computer; indicating out the target which is gazed at by virtue of a computer screen, and transmitting a target result, which is recognized out, to an intelligent wheelchair motorcontroller so as to control the motion of a motor, so that the wheelchair is advanced; when the wheelchair, which adopts a mode of firstly rotating in situ and advancing straightly, moves straightly or is free from continuous turning in a same direction, not adjusting the rotating angle of the wheelchair, when the wheelchair, which is controlled by a user, is subjected to a continuous turning operation in a same direction, pre-judging whether the wheelchair is further to be turned in a same direction by the user, and compensating the rotating angle of the wheelchair by virtue of a curve-fitting method and shortening an advancing distance. According to the method provided by the invention, the number of target stimulation is reduced, and an advancing process of the wheelchair in continuousturning in the same direction is optimized.

The invention discloses a rope-driven upper limb rehabilitation training robot system based on virtual reality and a use method thereof. The rope-driven upper limb rehabilitation training robot systemcomprises a 7-DOF upper limb rehabilitation train robot body and a virtual reality rehabilitation training system, can realize shoulder joint abduction / adduction, external / internal rotation and flexion / extension, elbow flexion / extension, forearm internal / external rotation and wrist joint abduction / adduction and flexion / extension rehabilitation training of patients with upper limb motor dysfunction, can ensure the safety of rehabilitation training and improve the control accuracy of rehabilitation training robot through a method of shoulder joint movement center positioning; and the virtual reality rehabilitation training system recognizes the posture of human upper limbs through the posture sensor and Kinect binocular vision sensor installed on the rehabilitation training robot, and, as the input of virtual reality scene, improves the interest and efficiency of rehabilitation through games related to upper limb movement training.

The invention discloses an ARM-based integrated polarization maintaining fiber axis positioning instrument. The instrument comprises an image acquisition unit, an image processing and control unit, movement of the actuator and interactive unit; image acquisition unit includes a light source, a microscope objective lens barrel, a complementary metal oxide semiconductor (CMOS) industrial cameras and micro-camera; movement of the actuator comprises a fiber rotator, manual displacement units, the displacement of the electric station, fiber pad, a first motion control board and a second motion control board; interactive unit including a touch screen; an image processing and control unit comprises a microprocessor, memory module, a communication interface, a display module, debug and power modules; ARM as the processor uses the touch screen as the user interface, small size, low cost, interactive and friendly, the advantages of fast speed.

A method and system to process data records are provided. The method comprises: (A) acquiring a user-assigned data table, wherein one row of the data table corresponds to one data record, and one column of the data table corresponds to one field; (B) providing a user with a graphics interface to set a field processing item, wherein the field processing item is used for defining how to process fields in the data table; (C) receiving an input operation which the user executes on the graphics interface in order to set the field processing item, and acquiring a user-set field processing item according to the input operation; and (D) processing fields in the data table according to the acquired field processing item, and acquiring characteristics of a machine learning sample corresponding to the data records in the data table based on the processed fields.

The invention discloses a state switching method and device. The method is suitable for electronic equipment comprising a storage unit, wherein the storage unit stores at least one object and one configuration file, the object has a hidden state and an unhidden state, and the configuration file comprises at least one object identification corresponding to the at least one object. The state switching method comprises the following steps of: receiving a first receiving command, and switching the electronic equipment from a first state to a second state, wherein the first state is the unhidden state of a preset object, and the second state is the hidden state of the preset object. By applying the embodiment of the invention, objects in the electronic equipment can be rapidly hidden; and the state switching method and device are simple in realization way.

The invention provides a method and a system for realizing data table splicing and automatically training a machine learning model. The method for realizing data table splicing comprises the followingsteps of: establishing a main foreign key association relationship between any two data tables according to an input operation executed by a user in a screen; generating at least one splicing schemefor at least two data tables which are associated with each other through a main foreign key association relationship; and according to each generated splicing scheme, splicing a corresponding associated data table between the at least two associated data tables.

The invention provides a method and a system for realizing data table splicing and automatically training a machine learning model. The method for realizing data table splicing comprises the followingsteps of: establishing an association relationship based on association fields between any two data tables according to an input operation which is executed by a user in a screen and is used for establishing the association relationship between the data tables based on the association fields; according to an input operation which is executed by a user in the screen and is used for specifying theassociation relationship between the fields in the data table and the primary keys and / or the types of the fields, setting the association relationship between the fields in the data table and the primary keys and / or the types of the fields; and splicing a corresponding associated data table between at least two data tables which are associated with each other through the association relationshipbased on the association fields based on the association relationship between the fields in the data tables and the primary keys and / or the types of the fields.