91results about How to "Realize intelligent judgment" patented technology

The invention provides a network teaching method and a system. The system comprises multiple user terminals and a server. The user terminals communicate with the server via the network. The method comprises a data acquisition step, a synchronous display step, a real-time recording step and a broadcasting and replaying step. In the data acquisition step, image data, application data and/or audio data in the network teaching processes are acquired and are used for synchronous display and real-time recording. In the synchronous display step, the acquired data are automatically synchronously displayed or transmitted on student user terminals. In the real-time recording step, the acquired data are separately stored into a database, so users can download the data. In the broadcasting and replaying step, according to the users' requests, the recorded and stored data are transmitted to the users and are combined and redisplay the teaching processes on the user terminals.

The invention provides a network teaching method and system. Double identity verification of face recognition and voice recognition is realized, the voice signal collection accuracy in a teaching process, an oral training process, a test process and an examination process are scored and assessed by a plurality of models, so that the assessment accuracy is improved, the network teaching is more autonomous and effective, and particularly in reading and listening and recitation teaching, the authenticity and effectiveness of learning can be improved by these functions of the system. By adopting the method provided by the invention, the face recognition is combined with the voice recognition, the user identity is checked before an oral test or system login of the user, and the user can be better encouraged to carry out a human voice test in a use process.

The invention provides a synchronous display method and device of images. Compression treatment is carried out through periodically capturing screen contents; the transmission capability can be realized at any time; the transmission effect is improved; and the transmission time can be shortened. The captured image contents can be quickly compared according to the feature values analyzed in the image compression process; the images are judged intelligently synchronously; the images are transmitted automatically synchronously without manual operation; the screen contents are prevented from being transmitted repeatedly; the storage pressure of a student user terminal is relieved; comprehensiveness of the contents is ensured; the screen image contents are marked and judged, the review efficiency of a student is improved, when the student reviews, the student can directly view the last few pages of blackboard-writings.

The invention provides a network teaching method and system with a voice assessment function. According to the voice assessment method provided by the invention, a phoneme state of a voice is used for replacing a multi-Gaussian mixture model trained by a conventional Mel-frequency cepstral coefficient (MFCC), and a posterior probability and a zero-order Baum-Welch statistical magnitude are calculated according to the feature. A voice feature based on phonemes is extracted through a multi-language phoneme identifier. A feature based on multi-language extraction is complementary during catching of non-native pronunciation information, and a feature based on phoneme duration is effective in automatic native accent assessment. Finally, a fusion system is provided in the method, so that Spearman relevant coefficients of 0.5706 and 0.6089 are reached on a development set and a test set. As indicated by the relevant coefficients, the method provided by the invention is very accurate and effective in oral speech assessment.

The invention discloses an intelligent method and a system for controlling alternate irrigation of local root zone of crops. The system comprises a signal collecting module and a control module, wherein the signal collecting module is used for collecting the soil water-content information of different root zones of the crops in real time and the control module is used for controlling the motor of the irrigation system by utilizing the water difference alternate threshold, upper limit and lower limit of the soil water content and practically measured soil water-content real-time information of all side root zones. The system is applicable to the automatic control on the alternate irrigation of local root zones of field furrow irrigation crops such as corns, cottons, potatoes and the like, fruit trees and greenhouse vegetable crops, has the advantages of land saving, water saving and energy saving, has low cost and simple operation and is convenient for being generalized and applied in large area.

The invention discloses a worker safety behavior monitoring system based on video capture. The monitoring system comprises a video acquisition device, a data transmission device, a video processor and a display device. A monitoring method based on the system comprises the following steps that: the video acquisition device acquires daily working behaviors of workers on a construction site, and converts a video signal into a digital signal; the data transmission device transmits the digital signal to the video processor through the video acquisition device; the video processor is linked with a worker safety behavior rule, wherein the rule is established on the basis of relevant national specifications for construction behaviors; the video processor receives the acquired video after acquiring the video signal, runs a program to form a video in which a construction personnel behavior video and the worker safety behavior rule are overlapped, and inputs the video into display equipment; a dangerous area is set; and whether construction personnel behaviors meet specification requirements or not is judged intelligently according to an overlapped video provided by the display equipment, and an alarm is made.

The invention discloses an intelligent roller shutter system based on the image processing technique. The intelligent roller shutter system comprises a master control module, a meteorological station, a camera, a GPRS module, an oscillating bar and a roller shutter motor. According to the intelligent roller shutter system, an intelligent weather recognition system based on weather images is established with the master control module serving as a data processing and controlling platform, rain, snow and other severe weather conditions can be effectively judged by collecting the temperature, the humidity, the illumination, the wind speed and direction and other weather information in the meteorological station outside a greenhouse and combining the weather images so that the rolling-up and the pavement of a heat preservation quilt can be controlled in time. By means of the positioning technology of the heat preservation quilt, an operator can accurately control the heat preservation quilt to be located at any position between the initial position and the ending position of the heat preservation quilt when carrying out long-distance operation or operating in a control chamber. Meanwhile, the fault can be intelligently diagnosed, the working state of a roller shutter motor can be monitored in real time, and when the roller shutter motor breaks down, the master control module automatically cuts off a power source of a roller shutter, and therefore the whole system can be safe and reliable.

The invention provides a defrosting control method for an air source heat pump unit. The air source heat pump unit is provided with an outdoor ambient temperature sensor, an outdoor ambient humidity transmitter and a surface air cooler fin temperature sensor. A control unit of the air source heat pump unit is connected with the outdoor ambient temperature sensor, the outdoor ambient humidity transmitter and the surface air cooler fin temperature sensor. The defrosting control method comprises the following steps that 1, the dew point temperature is calculated through the outdoor temperature and the outdoor humidity; 2, the air source heat pump unit enters into first defrosting; 3, the air source heat pump unit enters into automatic defrosting; and 4, the air source heat pump unit exits defrosting. The defrosting control method for the air source heat pump unit has the beneficial effects that in a region with the large humidity, the air source heat pump unit is accurately controlled toenter into and exit defrosting, so that accumulating of frost on a surface air cooler is avoided, and defrosting is clean and thorough; and when the temperature is low, whether the air source heat pump unit needs to enter into defrosting or not is judged accurately, so that the situation that the unit frequently enters into defrosting is avoided, intelligent judgment and automatic adjustment of the defrosting time and interval are achieved, the heating effect of the air source heat pump unit is improved, and energy consumption is low.

The invention relates to an address assignment method and an address assignment system for intelligent access type decision, and an AAA system. The method comprises the following steps: a Radius server receives an authentication request message sent by BRAS equipment, wherein the message carries the account name of a user and the IP address of the BRAS equipment connected with the user; the Radius server queries an AAA database according to the account name of the user and the IP address of the BRAS equipment, respectively determines the user IP address assignment type corresponding to the account name of the user as well as the equipment function service scope and the equipment IP address assignment type corresponding to the IP address of the BRAS equipment, determines the IP address assignment type according to the equipment function service scope, the user IP address assignment type and the equipment IP address assignment type, and returns an authentication response message to the BRAS equipment after authentication, wherein the message carries a domain identifier corresponding to the IP address assignment type; and the BRAS equipment calls a corresponding domain template configuration policy according to the domain identifier in the message to assign an IP address for customer premise equipment. Intelligent user IP address access type judgment and address assignment can be realized.

The invention discloses an OPGW DC ice-melting system, and the system comprises an ice-melting ground line, an ice covering measurement sensor, an ice covering measurement host, an ice-melting measurement host, a DC ice-melting power supply, a 485 concentrator, a switcher, a monitoring terminal, and an optical cable joint box. The ice-melting ground line is connected with the ice covering measurement host through the optical cable joint box, and the ice covering measurement sensor is connected with the ice covering measurement host through a single-mode optical fiber. The ice covering measurement host, the ice-melting measurement host and the DC ice-melting power supply are respectively connected with the 485 concentrator. The ice covering measurement host and the ice-melting measurement host are connected with the monitoring terminal through the switcher. The system achieves the overtemperature monitoring in a long-distance circuit ice melting process and circuit ice melting control under the different conditions in a deicing period through employing the technology of distributed optical temperature measurement and the technology of on-line analysis. The system achieves the ice covering monitoring of a power transmission rod tower under the on-site passive conditions, electromagnetic radiation resistance conditions and severe monitoring conditions through employing the technology of optical fiber grating ice covering measurement, and has a higher practical value.

The invention discloses a face attribute classification method based on multilayer depth feature information. The method includes the following concrete steps: S1, assuming that x is a face image of any angle; S2, using a local feature area extraction algorithm to convert an original image into local information; S3, using a multilayer feature extraction algorithm to extract multilayer feature information; and S4, utilizing a multi-feature fusion algorithm to realize self-adaption and fusion of multidimensional information. The invention provides a face attribute classification technology based on multilayer depth information. The method can effectively identify attributes of a person in a face image, thereby achieving intelligent video monitoring and intelligent judgment functions. A deep learning method is adopted to train face attribute samples, and a network model is divided into a common convolution layer, a feature extraction layer and an attribute classification layer. In the feature extraction layer, multilayer features are connected and multidimensional information is fused, which is helpful for extracting features that exhibit better distinguishing capabilities.

The invention provides a numerical control rolling machine tool for outer circle rolling machining of a torsion shaft. The numerical control rolling machine tool comprises a machine tool body, an outer circle rolling head, a dual centre locating device, a shifting fork connecting part, an internal spline clamp sleeve, a full closed protection cover, a displacement measurement system, a precise oilmist cooling system, a numerical control system and a hydraulic system. The outer circle rolling head of the machine tool adopts a multi-rolling-wheel symmetric rolling device structure, and when outer circle rolling machining of the torsion shaft is carried out, a workpiece bears multiple equal pressures in the radiation direction; a displacement sensor is mounted in a hydraulic cylinder of theouter circle rolling head, the change value of the rolling diameter in the outer circle rolling process is worked out through the rolling cylinder displacement value fed back by the displacement sensor, and intelligent judgment on the limiting position of the outer circle rolling arc end can be achieved; and the shifting fork connecting part replaces a traditional chuck, a transmission structure is optimized, meanwhile, worker operation is more convenient, the machine tool is more suitable for streamlined production operation, and the rolling machining efficiency is higher.

The embodiment of the invention discloses a case litigation time intelligent examination method and device, and the method and device are characterized in that the method comprises the following steps: automatically extracting case element information; and inputting the case element information into a pre-constructed litigation time examination model for calculation, and displaying a calculation result. The intelligent legal element analysis technology realizes accurate extraction and automatic judgment and confirmation of elements, reduces the dependence on confirmation of a party and the manual workload of a legal officer on information confirmation, and helps the legal officer to improve the case handling efficiency.

The invention discloses a mail pushing method and apparatus of risk events, a computer device and a storage medium. The method comprises the following steps: correspondingly obtaining a non-financialimpact severity parameter or a comprehensive impact severity parameter by operating a risk loss event, when the non-financial impact severity parameter or the comprehensive impact severity parameter exceeds a preset level threshold, obtaining corresponding event information according to an operation risk loss event, filling the event information in a mail template to obtain a major operation riskevent reporting reminding mail, obtaining mail receiver information according to an event category corresponding to the operation risk loss event, and sending the major operation risk event reportingreminding mail to a corresponding information receiver according to the mail receiver information. By adoption of the method, the intelligent judgment on the non-financial impact severity parameter orthe comprehensive impact severity parameter is achieved, and when the non-financial impact severity parameter or the comprehensive impact severity parameter exceeds the level threshold, the major operation risk event reporting reminding mail is automatically filled and is sent to the receiver so as to notify the receiver for processing.

The invention relates to the field of control of a gas dispenser and particularly relates to a self-feedback control method of a gas dispenser. The self-feedback control method comprises the following steps of: initializing a system and calculating an instantaneous pressure changing rate; when the instantaneous pressure changing rate is greater than a pre-set value, maintaining the gas leakage of the inner part of a pipeline of the gas dispenser; if the inner part of the pipeline of the gas dispenser does not leak gas, setting a gas dispensing amount or a gas dispensing volume and a charging pressure rated value; sampling a flow of a mass flow meter and a pressure value of a pressure-limited sensing device in real time; calculating a predicated charging pressure value of a terminal by an electric controller through using a predicated charging pressure algorithm; comparing the predicated charging pressure value with a pre-set charging pressure rated value; if the predicated charging pressure value is equal to the pre-set charging pressure rated value, finishing the gas dispensing; reading a pressure value of the terminal by the pressure-limited sensing device when the gas dispensing is finished and comparing the pressure value with the pre-set charging pressure rated value; and revising a weighted value of an output layer of the predicated charging pressure algorithm according to the error of the values and the flow when the gas dispensing is stopped. According to the self-feedback control method disclosed by the invention, the adaptive capacity of the gas dispenser to a pipeline environment is improved and the self-feedback control of the gas dispenser is realized.

The invention discloses an IGBT (Insulated Gate Bipolar Translator) short circuit protection detection circuit based on a driving chip. The detection circuit comprises an isolated driving circuit, wherein the isolated driving circuit comprises an isolated driving chip and a second resistor; the output pin of the isolated driving chip is connected with one end of the second resistor; the other endof the second resistor is connected with the base of an IGBT to be detected; the isolated driving chip further comprises an input pin and an overcurrent detection pin DESAT; the input pin is connected with a PWM (Pulse-Width Modulation) driving signal of a host; the overcurrent detection circuit comprises a first resistor, a first voltage regulator tube and a first diode; the overcurrent detection pin DESAT is connected with one end of the first resistor and the cathode of the first voltage regulator tube respectively; the other end of the first resistor is connected with a positive power supply; the anode of the first voltage regulator tube is connected with the cathode of the first diode; and the anode of the first diode is connected with the collector of an IGBT to be detected. The detection circuit has high IGBT short circuit protection reliability, a simple structure and high portability.

The invention discloses an automatic recognition method of transshipment of a horizontal transport vehicle and a cable crane in concrete construction. The automatic recognition method comprises the steps that step I, locating devices are mounted in a hanging grider of the cable crane and a driving cab of the transport vehicle; step II, the three-dimensional position of the hanging grider of the cable crane and the three-dimensional position of the driving cab of the transport vehicle are acquired in real time through the locating devices; step III, a monitoring device is mounted at a hydraulicturning plate of the transport vehicle, and a discharge state N of the transport vehicle is acquired in real time; step IV, the effective maximum distance L of the hanging grider of the cable crane and the center of the driving cab of the transport vehicle is acquired through measuring shape characteristics of the transport vehicle and characteristics of a hanging cage of the hanging grider of the cable crane in real time; step V, the real-time position of the transport vehicle and the hanging cage of the hanging grider of the cable crane, and the discharge state of the transport vehicle aretransmitted to a system server; and step VI, the discharge state of the transport vehicle and the real-time distance of the transport vehicle and the hanging cage of the hanging grider of the cable crane are analyzed and calculated through the system server, and warning information is sent.

The invention provides a medication decision support method and device based on a graphic state machine. The method comprises the steps of: acquiring a medication consultation statement of the user; extracting a symptom information entity, an allergy information entity and a disease information entity in the medication consultation statement through word segmentation and semantic recognition; forming a graph state machine set which is high in response speed to a target event through three independent graph state machines; analyzing the incidence degree information in the medication consultation statement of the user by using a neural network model and an emotion word segmentation dictionary, and comparing the incidence degree information with the incidence degree information spoken by the user to obtain a corrected value of the incidence degree; removing excessive judgment or underestimated judgment, caused by user emotion factors, on the incidence degree through the correction value, and obtaining accurate incidence degree information; and achieving medication decision support aiming at accurate incidence degree information through the medication decision support device. According to the invention, intelligent judgment on the incidence degree irrelevant to the individual cognitive level of the patient can be realized, and the medication accuracy is improved.

The invention discloses an impedance detection module used for a medical equipment cloud system. The impedance detection module is applicable to the specific medical equipment cloud system, and an equipment terminal in the system comprises a control module, a man-machine interaction module, a waveform power amplification module, a DDS waveform generation module, a direct current bias module, an impedance detection module, a communication module and a storage module. The impedance detection module achieves intelligent adjustment of an interface; intelligent judgment of the terminal is achieved.Operation instruments of a doctor can be carried with the doctor. The impedance detection module is applicable to the specific medical equipment cloud system.

The invention provides a method for automatically acquiring the type of a bank card. The method includes the following steps: an dynamic link library of an upper computer and a card reader interacts with each other through communication, after the card reader receives a relevant command, simultaneously turning on a magnetic card data acquisition module, a contact-type IC card data acquisition module and a non-contact type IC card data acquisition module, conducting module polling through a task scheduling mechanism, when relevant operations of a user are detected, through a data processing unit of a relevant module, uploading data package of the relevant operations to the upper computer in a set format, when the upper computer detects the relevant operations, acquiring card-related information by analyzing the data format, using the type of the current card to perform follow-up business operations. According to the invention, the method obviates the need for operation workers to perform related business operation when the type of the bank card is unknown, and increases work efficiency.