1292results about How to "Improve the accuracy of judgment" patented technology

An article for detecting physiological function and posture status is disclosed. The article touches body directly or indirectly; wherein at least a group of non-posture physiological sensors are configured on this object and at least a switch, tension sensor, pressure sensor or pressure applicator are coupled with or touch this object; the switch, tension sensor, pressure sensor or pressure applicator are configured on a different or the same object with the physiological sensors, or divided into two parts that contact each other while external force applied; the non-posture physiological sensors sense the physiological function and posture status of the user.

The invention discloses a contextual model regulating method and device for intelligent household equipment. The method comprises the steps that audio information is acquired; if the fact that the audio information is determined to meet a triggering condition for performing model regulation is responded, the contextual model of the intelligent household equipment is regulated to a target contextual model corresponding to the audio information. According to the contextual model regulating method and device for the intelligent household equipment, the contextual model of the intelligent household equipment can be automatically regulated according to the audio information, manual control of a user is not needed, the contextual model regulation efficiency is improved, and convenience is brought to the user.

An embodiment of the invention discloses a method and a device for text classification. The method comprises: acquiring an affective characteristic word from an input text; acquiring an affective aptitude degree of the affective characteristic word according to a synonym storehouse constructed in advance; and classifying the text according to the affective aptitude degree of the affective characteristic word. The embodiment of the invention is used to acquire the affective aptitude degree of the affective characteristic word in the text for text classification according to the synonym storehouse constructed in advance and improves the accurate degree of judging the affective aptitude degree of the words.

The invention relates to an insulation health state evaluation method of a dry type transformer for a coal mine underground power supply system. According to the method, evaluation is carried out based on monitoring quantity determining, feature quantity extraction, feature quantity processing, fault diagnosis, health state evaluation, database establishment and state early warning-based multi-information source fusion; the development degree of an insulation local defect is monitored through using the change laws of related feature quantities in a discharge evolution process of the insulation defect; and diagnosis of the risk of the insulation local defect is realized based on a particle swarm optimization algorithm-based support vector machine, so that a comprehensive evaluation result of the overall health state and insulation local deterioration degree of the dry type transformer can be obtained. According to the method of the invention, corresponding variable weight values are assigned for the feature quantities, and therefore, high applicability and high judgment accuracy can be realized, early, accurate and quick prediction of potential faults and identification of fault types can be benefitted, the operating state and possible defect development trend of the transformer can be comprehensively evaluated, and the reliability and continuity of the operation of the transformer can be improved.

When a monitor apparatus judges that a vehicle has stopped at a predetermined position (step 705), the monitor apparatus transmits pseudo position information of the vehicle (dummy data) to an automatic charging apparatus (step 725). The automatic charging apparatus calculates a charge amount on the basis of the dummy data, and transmits the result of the calculation to the monitor apparatus. The monitor apparatus receives the result (step 735) and judges on the basis of the result whether the automatic charging apparatus is in an anomalous state (step 740). Since the above-described successive operations are performed only when the vehicle stays, the status of another automatic charging apparatus not monitored is not misidentified as the status of an automatic charging apparatus to be monitored.

The embodiment of the invention discloses a detection method and apparatus. The method comprises: a template image and a tested image are inputted into a trained Siamese network and forward calculation is carried out to obtain feature vectors of the template image and the tested image; similarity of the feature vectors of the template image and the tested image is calculated; and according to the similarity, whether the tested image and the template image match each other is determined. Because the Siamese network can extract high-grade features of the image, whether the tested image and the template image match each other can be determined accurately by inputting the images into the trained Siamese network; and the determination accuracy is high.

The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which comprises the following steps: step 1, selecting a data sample required by anexperiment, and dividing the unified standardized sample data into a test sample and a training sample according to a specific proportion; Step 2: building and initializing the DBN deep belief networkfault diagnosis model; Step 3, inputting a large number of unlabeled samples or unlabeled samples in the pre-training set from the bottom of the model, and pre-training the RBM in the model by usinglayer-by-layer unsupervised greedy learning; Step 4: the whole model being fine-tuned by genetic algorithm; Step 5, the fault diagnosis model of the high-voltage circuit breaker obtained by training being classified to the fault samples of the test set in step 1, so as to obtain the fault classification result, and the diagnosis accuracy rate of the model being counted. The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which can train a large amount of data samples to realize the fault diagnosis function of the high-voltage circuit breaker.

The invention relates to a parking lot management system and management method. The parking lot management system comprises a server, a number of UWB positioning parking cards and at least three UWB positioning base stations. The server comprises a storage unit which is used for storing a virtualized parking lot digital model which models all parking spaces in a parking lot to coordinate the parking spaces. The UWB positioning base stations are connected with the server through cables. The precise coordinates of the UWB positioning base stations are measured in advance and stored in the server as known parameters. The real-time position coordinates of the UWB positioning parking cards are calculated through a three-point positioning method. The server further comprises a comparing calculation unit which is used for comparing parking space coordinates in the parking lot digital model according to the real-time position coordinates of the UWB positioning parking cards to determine whether a car is parked in a parking space.

The invention provides a driving style estimation method based on driving pattern transition probability, wherein the method includes the steps: step 1, acquiring actual driving data of a driver, wherein the actual driving history data at least include the steering wheel rotary angle, the vehicle speed, the longitudinal acceleration speed and the transverse acceleration speed; step 2, according to the actual driving data, dividing driving behaviors into N driving behavior patterns; step 3, determining the driving behavior pattern transition probability, wherein the driving behavior pattern transition probability is the transition probability between arbitrary two driving behavior patterns in the N driving behavior patterns; and step 4, taking the driving behavior pattern transition probability as a training sample training classifier, to perform driving style estimation through the classifier.

The invention discloses a pair of intelligent glasses with the blinking detection function and an implementation method of the intelligent glasses. The intelligent glasses comprise a glasses frame, a glasses bridge, eyeglasses, nose supports and glasses legs, wherein the nose supports and the glasses legs are respectively provided with a myoelectricity sensor; the glasses bridge is provided with a vibration reminder, and each glasses leg is provided with a myoelectricity signal processing device and a camera. The implementation method includes the following steps that 1, an eye change myoelectricity signal is collected through the myoelectricity sensors; 2, the collected myoelectricity signal is sent to a signal processing circuit for processing, and myoelectricity signal features are obtained; 3, the obtained myoelectricity signal features are compared with preset myoelectricity signal features, one-time blinking is judged if the obtained myoelectricity signal features are coincident with the preset myoelectricity signal features, and next judgment is carried if the obtained myoelectricity signal features are not coincident with the preset myoelectricity signal features; 4, the number of blinking times within a unit time is obtained, and the blinking frequency is obtained; 5, whether a user blinks abnormally or not is judged according to the blinking frequency, and the vibration reminder vibrates for reminding if it is judged that the user blinks abnormally. The intelligent glasses with the blinking detection function and the implementation method of the intelligent glasses can effectively protect the eyes in time.

The invention provides a depth neural network system and a method based on modulation mode identification of underwater acoustic communication. The system comprises: a data preprocessing part for preprocessing data of a plurality of modulation modes transmitted through underwater acoustic communication; A first layer neural network generates a feature extraction set of the first layer according toa plurality of modulation mode data transmitted from the pretreated underwater acoustic communication; The second layer neural network generates the second layer high-level feature set; The third layer neural network generates higher level feature set, the fourth layer neural network classifies and identifies the initial data by the feature set extracted in front; The fifth layer is the neural network layer, which generates the final modulation mode judgment and outputs the identified modulation mode. The depth neural network system and method based on the modulation mode recognition of underwater acoustic communication can simulate the actual use situation, improve the use effect in the actual underwater acoustic communication, more conveniently and efficiently complete the modulation recognition of underwater acoustic communication, and improve the accuracy of recognition and judgment.

The invention discloses a flexible screen with the bending state detectable and capable of improving working efficiency and accuracy of judgement. The flexible screen comprises a basic device and a detecting device, wherein the basic device comprises a basic layer and light emitting layer attached to the basic layer, the detecting device is arranged on the basic device or in the basic device and is used for detecting at least one parameter value when the flexible screen is bent, and specifically, the at least one parameter value is used for determining the bending state of the flexible screen. The invention further discloses a method and an electronic device for detecting the bending state of the flexible screen.

An airbag apparatus includes a controller, a prediction unit, and a sampling-period control unit. The controller conducts sampling of acceleration values output from a plurality of acceleration sensors disposed on a vehicle and controls inflation of an airbag based on the sampled acceleration values. The prediction unit predicts a collision direction in which collision with another vehicle would occur. When the prediction unit predicts the collision direction, the sampling-period control unit shortens a sampling period for the acceleration sensor disposed in the predicted collision direction in comparison with sampling period for the other acceleration sensors. After the sampling-period control unit shortens the sampling period, the controller determines whether or not to inflate the airbag, based on the sampled acceleration values output from the acceleration sensor disposed in the predicted collision direction.

The invention provides an identification method for turnout faults. The method comprises steps as follows: a curve of each action of a turnout is collected; the obtained turnout action curves are divided into normal curves and fault curves; for the normal curves and the fault curves, one normal curve and one fault curve with the most representative characteristics are selected as representative curves of the normal curves and the fault curves respectively; similarity 1 of a to-be-identified curve and the representative normal curve and similarity 2 of the to-be-identified curve with the fault representative curve are calculated with a similarity algorithm; the similarity 1 and the similarity 2 obtained through calculation are compared, if the similarity 1 is larger than the similarity 2, the curve is a normal curve, and if the similarity 1 is smaller than the similarity 2, the curve is a fault curve. According to the identification method for the turnout faults, the problems of missing report and mistaken report caused by the fact that the turnout fault type is judged through artificial experience in the prior art are solved, so that the turnout fault category is automatically identified, repair efficiency and system reliability are improved, and traffic safety is guaranteed.

The present application relates to a blockchain data processing method and apparatus, a computer device and a storage medium. The method comprises: acquiring node information of each node in a blockchain, wherein the node information comprises block information; according to the block information of each node, determining a corresponding node irreversible block, and determining the initial chain height corresponding to the blockchain according to the node irreversible block corresponding to each node; taking the initial chain height as the current chain height, and acquiring the historical confirmation chain height of the blockchain; when the current chain height is greater than the historical confirmation chain height, obtaining a validity verification result of the current chain height according to the block information of each node; according to the validity verification result, updating the current chain height; and according to the updated current chain height, the historical confirmation chain height, and the initial chain height, determining the working state of the blockchain, so that the accuracy of determination of the working state of the blockchain is improved.

An air conditioner refrigerant circuit performs a cooling operation in which an outdoor heat exchanger functions as a condenser of the refrigerant compressed in a compressor and an indoor heat exchanger functions as an evaporator of the refrigerant condensed in the outdoor heat exchanger. Further, an outdoor expansion valve is disposed at a position that is at once downstream of the outdoor heat exchanger and upstream of a liquid refrigerant communication pipe in the refrigerant flow direction in the refrigerant circuit in the cooling operation, and shuts off the refrigerant flow. A refrigerant detection unit is disposed upstream of the outdoor expansion valve and detects the amount or the amount-related value of refrigerant accumulated upstream of the outdoor expansion valve.

Provided is an online monitoring method for lubricating oil of a wind-power transmission. The online monitoring method for the lubricating oil of the wind-power transmission comprises the following steps that performance analysis is carried out on a tribology system of a gear case of the wind-power transmission, and a comprehensive information monitoring method which is based on three aspects, namely an abrasion, a lubricating oil physical and chemical performance and pollution is proposed; an integral information monitoring system is established through testable analysis, and viscosity, water and an abrasive grain are adopted to be used as testable characteristics corresponding to the three classes of information of the abrasion, the lubricating oil physical and chemical performance and the pollution; by utilizing the embedded type integral sensor technology, real-time obtaining of the information is achieved; by adopting a TCP/IP network communication protocol, remote monitoring is achieved; a relation model of the abrasion, a lubrication oil product and the pollution are established, and inducements of the abrasion or lubricating malfunctions are speculated. Online perfect information obtaining is achieved, the analysis on origins of malfunctions is provided, the effective monitoring method for a running state of the gear case of the wind-power transmission is achieved, and according to positioning of an abrasive malfunction, an oil replacing suggestion and other maintaining suggestions, the important engineering significance for lowering the triology malfunction and prolonging the complete machine service life is achieved.

The invention provides a method for preventing an HttpFlood attack. The method includes the steps that a firewall generates and maintains a challenge list; the firewall establishes TCP connection with a user and judges whether a source IP address of a get message received from the user exist in the challenge list; if the source IP address of the get message received by the firewall does not exist in the challenge list, the firewall intercepts the get message and establishes a JavaScript redirection page according to the get message and adds the source IP address of the get message, the address of a get request page and the generated address of the generated JavaScript redirection page into the challenge list; when the firewall detects that an entry in the challenge list does not have a redirection access in a preset duration, the firewall adds the source IP address of the entry into a blacklist so as to prevent the subsequent traffic of the source IP address. The invention further provides the firewall for preventing the HttpFlood attack. Through the method, the firewall will not make a misjudgment, so the judgment accuracy rate is high.

A method for determining the position in a vehicle of a first device in communication with a microprocessor may include receiving, at the microprocessor, a first set of inertial data from at least one sensor of the first device; receiving, at the microprocessor, a second set of inertial data from at least one sensor of a reference device disposed within the vehicle; and determining, using the microprocessor, the position of the first device in the vehicle by comparing the first set of inertial data with the second set of inertial data.

The invention discloses an XLPE cable partial discharge defect type identification method. The method comprises the following steps: obtaining the de-noised XLPE cable ultrahigh frequency PRPS graph; extracting and computing four dimension statistical characteristic parameters and six non-dimension characteristic parameters of the PRPS graph; inputting the characteristic parameters to SOM neural network model; determining the win nerve cell, continuously learning through updating the weight vector of the win nerve cell by the SOM neural network, until the input sample corresponding to the output layer win nerve cell is stable; and outputting the type identification result of the SOM neural network. The XLPE cable partial discharge defect type identification method is capable of overcoming the defects of the traditional method that the convergence speed is slow and the judgment accuracy is bad, satisfying the visual requirement of the fault analysis, and improving the intelligent level of the XLPE cable partial discharge detection system, has the characters of rapid detection speed, simple process and high diagnosis accuracy, and is good for accurately evaluating the running state of the XLPE cable by the maintenance worker.

The present application relates to the field of natural language processing technology and provides a contract intention judgement method and apparatus, a computer apparatus, and a storage medium. Themethod comprises the following steps of: acquiring voice data from a terminal; obtaining a speech text by performing speech recognition of speech data, extracting keywords from speech text, matchingthe extracted keywords with preset keywords corresponding to preset text, and obtaining text matching score; extracting the speech feature vector from the speech data, and inputting the extracted speech feature vector into the trained fraud risk prediction model to obtain the fraud risk coefficient value; acquiring image data from a terminal, performing face recognition on the acquired image datato obtain a face recognition score; acquiring scene identifiers corresponding to the current business scenario, and acquiring corresponding target audit rules according to the scene identifiers; according to the text matching score, fraud risk coefficient value, face recognition score and target audit rule, judging the intent to sign the contract.

The invention belongs to the technical field of road traffic operation state detection and control, and relates to a road congestion state detection method based on computer vision. The road congestion state detection method specifically comprises the technological steps of firstly classifying and marking data sets formed by processing a large number of collected images to serve as training sets for neural network training, then constructing a convolutional neural network according to the data sets by using a migration model training method, then classifying intercepted real-time traffic monitoring video images through the convolutional neural network, judging the vehicle density state, and finally calculating the optical flow field by using an optical flow algorithm so as to judge the traffic congestion state. The detection method is scientific in design principle and accurate in information collection, the image recognition accuracy reaches 98% and above, the monitoring effect is good, the cost is low, the effect is good, the data calculation method is simple, the judgment accuracy is high, the application is convenient, and the real-time traffic state can be effectively judged.

The invention provides a system and a method for real-time monitoring and communication of a housebound pregnant woman. A sensing device is used for sensing the uterine contractive pressure of the pregnant woman and physiological states, such as fetal heart rate, fetal movement, and the like of a fetus and generates a sensing signal; a computer-aided monitoring system carries out analytical processing and generates an analytical signal; a long-range electronic device downloads and displays the analytical signal from the computer-aided monitoring system, and the physiological states of the pregnant woman and the fetus can be judged to be abnormal or not through the analytical signal displayed by the electronic device, thus the physiological states of the pregnant woman can be monitored and known in a long range and real time, and the troubles of the pregnant woman staying in hospital for a long time for miscarriage prevention and other demands or going to the hospital back and forth frequently during pregnancy are reduced.

The invention provides a city signal control intersection traffic state detecting and evaluating system based on data characteristic and a method and an application thereof. The system comprises a vehicle state detection unit, a control state monitoring unit, a signal collecting unit, a microprocessing unit, a data transmitting unit, a data processing unit and a traffic state display unit, wherein, the vehicle state detection unit and the control state monitoring unit are connected with the signal collecting unit in parallel; then the signal collecting unit is also connected with the microprocessing unit, the data transmitting unit, the data processing unit and the traffic state display unit sequentially; the microprocessing unit is also connected with a real time data storage unit signal; and the control state monitoring unit is also connected with a traffic signal lamp signal. The method is applicable to various traffic engineering technology activities carried out by traffic real time data analysis, and the method has the advantages of intuition, easy application, high judgement accuracy and wide application range.