68results about How to "High judgment accuracy" patented technology

An electro-optical device includes: a screen on which an image is displayed; a first substrate and a second substrate that are provided opposite to each other; liquid crystal that is sandwiched between the first substrate and the second substrate; an electrostatic capacity detecting unit that outputs a detection signal whose level corresponds to the value of a capacitance that is formed by the liquid crystal, a first electrode, and a second electrode; an image displaying unit that includes the liquid crystal, a third electrode, and a fourth electrode, the image displaying unit controlling the transmission factor of the liquid crystal for displaying an image on the screen; a first memory unit that memorizes the level of the detection signal outputted by the electrostatic capacity detecting unit in a state in which a detection target object is not in contact with the screen as reference data; a second memory unit that memorizes the level of the detection signal outputted by the electrostatic capacity detecting unit in a state in which a judgment is made as to whether the screen is contacted or not as detection target data; a difference data generating unit that generates a difference between the reference data that has been read out of the first memory unit and the detection target data that has been read out of the second memory unit as difference data; and a judging unit that judges whether the detection target object is in contact with the screen or not on the basis of the difference data.

The invention discloses a manual alphabet identification method based on an RGB-D image, and belongs to the technical field of behavior identification of computer vision. According to different types of hand texture information of different types of manual alphabets, histogram-of -oriented-gradient characteristics and super-normal-vector characteristics of an RGB-D image video frame obtained through an RGB-D camera are extracted; a principal component analysis and a linear discrimination analysis are combined for characteristic attribute optimizing processing, so that a characteristic attribute with saliency is obtained, and BoW sparse representation is conducted on the characteristics; a data contrast mining technology is used for obtaining representative exemplars in all the types of manual alphabet; finally, a hierarchy judgment policy based on a greedy thought is adopted, the manual alphabets easy to classify are quickly classified through a nonparametric k-Nearest Neighbor Algorithm classifier firstly, and the manual alphabets difficult to classify are judged through a trained support vector machine model based on templates. Compared with the prior art, the manual alphabet identification method is high in both identification accuracy and identification efficiency.

Judgment means for judging which of a plurality of image types, predefined by one or more items out of radiographed parts, radiography directions, and radiography methods a target image belongs to, according to characteristic quantities of the target image is generated and prepared through machine learning using sample images belonging to each of the image types, and an image type of a radiograph included in an input image is judged by applying the judgment means to the radiograph.

The invention discloses an electroencephalogram signal quality real-time judgment method, and relates to the field of electroencephalogram signal digital signal processing.The method comprises the following steps that electroencephalogram signal fragments corresponding to a generated time window are obtained; the average value of the electroencephalogram signal fragments in the current time window is calculated, and the standard difference of the electroencephalogram signal fragments in the current time window is calculated through the average value; the volatility judgment result of the electroencephalogram signal fragments in the current time window is obtained through the calculated standard difference; by means of the volatility judgment result of the current electroencephalogram signal fragments and the volatility judgment result of original electroencephalogram signal fragments, the quality of the current electroencephalogram signal is judged.By means of the method, the electroencephalogram signal quality can be rapidly and effectively judged and analyzed in real time, and accuracy of follow-up electroencephalogram application analysis is effectively ensured.

The invention provides a fault diagnosis system. The fault diagnosis system includes an execution terminal, a controller, a fault diagnosis module, a first output terminal and a background server; the execution terminal is arranged in a vehicle and is connected with the controller, and monitors the operation signals of various components in the vehicle; the controller is connected with the fault diagnosis module, monitors the fault diagnosis module, and transmits monitored first monitoring signals and received operation signals to the fault diagnosis module; the fault diagnosis module monitors the controller, receives the first monitoring signals and the operation signals, and performs diagnosis; and the background server receives abnormal signals and judges the fault condition of the vehicle. Thus, the controller and the fault diagnosis module in the fault diagnosis system can monitor each other and give feedback to each other, so that errors in detection results caused by the damage of the controller or the fault diagnosis module can be avoided.

The invention provides a sound and picture synchronization judgment method and device, a terminal and a computer readable storage medium, and belongs to the technical field of audio and video processing. The method comprises: obtaining first audio data corresponding to a target video frame of the first multimedia data received from a server, and determining first fingerprint information of the first audio data, comparing the first fingerprint information with at least one piece of second fingerprint information, and if the first fingerprint information is the same as any one piece of second fingerprint information, determining sound and picture synchronization of the first multimedia data. Because the fingerprint has uniqueness and can be used as an identifier of the audio data, the methodextracts the fingerprint of the audio data and judges the sound and picture synchronization according to the fingerprint, manual observation is not needed, the sound and picture synchronization judgment efficiency can be improved, errors caused by manual judgment can be avoided, and the judgment accuracy is improved.

The invention discloses a blood gas acid-base analysis method, which comprises acquiring blood gas parameters of arterial blood; and substituting the blood gas parameters sequentially into a preset simple acid-base imbalance judgment condition, a dual acid-base imbalance judgment condition and a triple acid-base imbalance judgment condition, judging whether an acid-base imbalance condition exists,and outputting the judgment result. This method is used to determine the acid-base imbalance and, on the basis of a calculation formula of a body compensation prediction value, the relevant arterialblood gas value and serum electrolyte detection data are obtained, the judgment of the acid-base balance can be more accurate than that by a manual method and takes less time in the prior art, and theaccuracy rate of the clinician's judgment on the type of acid-base imbalance of a patient and the success rate of the rescue of critically ill patients can be greatly improved. The method of the invention can quickly and accurately judge the results to win the rescue time for the patient against time and, at the same time, greatly improves the work efficiency of the clinician, which is conduciveto early formulation of a diagnosis and treatment plan.

The invention provides a detection system and a detection method for an aircraft landing gear. The system comprises an image preprocessing module used for pre-processing a the image of a to-be-detected aircraft landing gear; an aircraft target detection module used for detecting an aircraft target in the image; a feature extraction module used for extracting the lower boundary features of the aircraft target; a landing gear suspicious region detection module used for detecting a suspicious landing gear region in the aircraft target; and a landing gear detection module used for detecting the aircraft landing gear. According to the technical scheme of the invention, whether the aircraft landing gear is laid down or not can be rapidly detected, and the engineering implementation is easily realized. The landing gear detection accuracy is high. Meanwhile, the blank of the current research in the above aspect is filled up. The system and the method provide the position and quantity information of aircraft landing gears more stably.

The invention discloses an intelligent shopping system which comprises a control center and a mobile terminal. The control center forms data association with the mobile terminal based on wireless signal transmission. The system comprises a database, an acquisition module, an alarm module and an accounting module, all of which are associated with one another based on a software framework. Based ondata association, the system further comprises a navigation module, a recommendation module, a judgment module and an inspection module. The navigation module forms a navigation map corresponding to areal scene by taking a Bluetooth beacon base station as a data unit, the commodity position is associated with the identification beacon, and the positioning engine plans a navigation route based onthe beacon. The recommendation module takes a user operation state as a trigger node, various types of preset informationare logically combined to form multiple data sets, the data sets are preferentially arranged based on customer records or merchant records, and the display terminal preferentially displays the data sets associated with the trigger node. The judgment module forms a shopping behavior judgment basis based on the association of images and quality with image sensing as a commodity identification means and code scanning and code scanning judgment as a behavior remedy means. The judgment module and the acquisition module carry out self-learning based on an algorithm of a deep neural network.

The invention discloses a shallow buried weak-cementation top plate working face overlying strata zoning dividing method and application. Firstly, the rock stratum fracture condition is objectively analyzed according to the relationship between the maximum tensile stress borne by all rock stratums and the ultimate stress and the relationship between the ultimate deflection and the separation layeramount; secondly, rock stratum layer positions where cracks are produced are objectively analyzed according to the maximum deflection generated when a rock stratum weak-cementation rock stratum at the upper portion of a fracture rock stratum produces cracks and the ultimate deflection and separation layer amount generated during fracturing, and how much zones the shallow buried weak-cementation top plate working face overlying strata is divided can be judged accordingly; the judgment process is based on real calculation data, no artificial factor is doped in the judgment method, development of a diversion fissure zone is highly accurately predicted, and a guiding effect on the field is truly achieved. By comparing the development height of a complete fracture zone of the working face overlying strata rock stratum or the highest range of an overlying strata crack damage zone with the position of a water-bearing stratum, whether a working face can achieve water retention exploitation ornot can be accurately evaluated, and a basis is provided for mine safety work.

A system and method for preventing a mobile terminal from uploading information abnormally is provided. The system includes: a real-time monitoring module, configured to monitor the standby state of mobile terminal and a transmission power in the standby state in real time, and notify a comparing module of the standby state and transmission power in the standby state; the comparing module, configured to: after receiving the notification, compare the transmission power of mobile terminal in the standby state with a transmission power of mobile terminal in a theoretical standby state, notifying a software prompting module of the comparison result; the software prompting module, configured to: when the comparison result is that the transmission power of mobile terminal in the standby state is greater than the transmission power of mobile terminal in the theoretical standby state, prompt a user there is a risk of malicious information leakage in the current state.

The invention relates to a gas stove dry-burning-prevention method. When a diffuse reflection photoelectric switch detects that a person exists in front of a cooking bench, a dry-burning-prevention device is not started; when the diffuse reflection photoelectric switch detects that no person exists in he cooking bench, and an infrared sensor detects that the person exists in front of the cooking bench, according to the fire magnitude, delay sound alarm is carried out, and if unmanned operation is carried out, the dry-burning-prevention device is started; when the diffuse reflection photoelectric switch detects that no person exists in the cooking bench, and the infrared sensor detects that the person does not exists in front of the cooking bench, the dry-burning-prevention device is started; after the dry-burning-prevention is started, according to a sheltered photosensitive diode, the position of a rotary knob is judged, the current fire magnitude is determined, if the current fire islarge, after it continues for T1, an alarm is given out, a motor is controlled to rotate, and the rotary knob is rotated clockwise until the rotary knob is closed; if the current fire is the medium heat, after it continues for T2, the alarm is given out, and the motor is controlled to be rotated; and if the current fire is the small fire, after it continues for T3, the alarm is given out, and themotor is controlled to rotate.

The invention relates to the technical field of distribution automation fault research and judgment, and discloses a fault research and judgment method based on an edge calculation FTU and a fault indicator, which comprises the following steps: acquiring recording data of a plurality of cycles before a fault recording starting moment and a plurality of cycles after the fault recording starting moment, and calculating fault waveform samples collected by the FTU based on the edge calculation; a first half-wave waveform research and judgment criterion is used as a main criterion of internal and external faults, a sample waveform correlation criterion is used for checking and rechecking internal and external recording samples of a first half-wave waveform research and judgment criterion conclusion, and the first half-wave waveform research and judgment criterion is used as an auxiliary criterion of first half-wave waveform research and judgment, comprehensive research and judgment are carried out, and a position node where a single-phase earth fault occurs is determined. Compared with the prior art, the method has the advantages that the accuracy of fault detection in different single-phase earth fault environments can be improved to the greatest extent by utilizing mutual complementation and mutual verification of two research and judgment criteria.

The invention discloses a method for detecting refrigerant leakage of an air conditioner. The method comprises the steps of determining whether the air conditioner needs the refrigerant leakage detection or not according to the detected outdoor refrigerant concentration of the air conditioner; determining whether the running current of a compressor is reduced or not according to the outdoor temperature and the running current value I of the compressor; simultaneously starting a timer and a counter to work; determining whether the refrigeration effect of the air conditioner is invalid or not; detecting whether a pressure sensor of an exhaust port of the compressor breaks down or not; determining the actually measured saturation temperature corresponding to the average value of the exhaust pressure value according to the average value of the exhaust pressure value, and determining whether the air conditioner has a suspected refrigerant leakage or not according to the actually measured saturation temperature; correcting the refrigerant flow value Q per unit time according to the information stored in a parameter storage space and the running current value of the compressor; and determining whether the flow ratio of the corrected refrigerant flow value per unit time to the actual mass flow is smaller than a preset ratio value or not, and if yes, turning off the air conditioner andkeeping the current rotating speed of a fan. The method has the beneficial effects that (1) the determining accuracy rate of the refrigerant leakage of the air conditioner is higher; and (2) the refrigerant leakage is comprehensively detected, and air exhausting is continuously carried out when the refrigerant leakage is determined.

The invention relates to a job log monitoring method and device, computer equipment and a storage medium. The method comprises the steps of obtaining to-be-analyzed job log data of a job log center; the to-be-analyzed job log data is data obtained by processing log data generated during operation of the target job; inputting the to-be-analyzed job log data into a log analysis model to obtain a job log data analysis result, and judging whether the target job is interrupted or not based on the job log data analysis result to obtain a first judgment result; the log analysis model is a bidirectional gating circulation unit network with a multilayer structure; if the first judgment result is that the target job is not interrupted, inputting the to-be-analyzed job log data into an alarm tracking model to obtain a second judgment result corresponding to an uninterrupted job log data analysis result; and if the second judgment result is abnormal alarm, outputting abnormal operation data for the target operation. By adopting the method, the monitoring efficiency can be improved, and the identification error rate is reduced.

The invention relates to a living body detection method and device based on a near-infrared camera, and the method comprises the following steps: collecting image data which comprises a color image obtained through a visible light camera and a near-infrared image obtained through the near-infrared camera; positioning a face area on the image data; judging whether the color image is a real face ornot according to the color of the face region in the color image, and traversing pixel points in the face region in the color image according to a screening condition; counting the number of the pixelpoints meeting the screening condition, if the number of the pixel points meeting the condition exceeds a number threshold value, continuing the next step, and otherwise, ending the detection; judging whether the near-infrared image is a real face or not according to the brightness of the face region in the near-infrared image, and traversing pixel points in the face region in the near-infrared image according to a screening condition; counting the number of the pixel points meeting the screening condition, and if the number of the pixel points meeting the condition exceeds a number thresholdvalue, considering that the near-infrared image is a real face; otherwise, ending detection.

The invention provides a method for judging a blockage degree of a dust filter screen of an air conditioner. The method for judging the blockage degree of the dust filter screen of the air conditionercomprises the following steps that the humidity of an environment in which an indoor unit of the air conditioner is located is acquired to obtain an indoor humidity value; current of a motor of an indoor fan of the indoor unit is acquired to obtain a measured current value; a current judgment threshold corresponding to the indoor humidity value is acquired; and according to the measured current value and the current judgment threshold, the blockage degree of the dust filter net is judged. According to the method for judging the blockage degree of the dust filter screen of the air conditionerand the air conditioner, the judgment accuracy of the blockage degree of the dust filter screen is improved, the misjudgment is reduced, and the user experience is improved.

The invention relates to the related technical field of false image detection, provides a two-dimensional depth false image generalization detection method, system and device, and a storage medium, and firstly overcomes the difficulty that an image is difficult to carry out generalization detection by using a unique detector due to a large difference between a DeepFake technology and a GAN network technology in the prior art. Through the detection method, the limitation of a current detection method based on a spatial domain is overcome, frequency domain information is extracted for detection, and the detection performance is improved. According to the method, common up-sampling features of various different two-dimensional false image generation methods are utilized, and the problems that a false image detector is weak in generalization and poor in effect in an actual application scene are solved by using frequency domain conversion and neural network technologies.