2560results about How to "Reduce false positive rate" patented technology

A system and method for detecting duplicate checks during processing. The duplicate detection may be performed by a financial institution, such as a bank. The method may be implemented on a computer based system. The duplicate detection method may be automated. The method may be applied to incoming check files prior to processing of the check data to prevent processing of duplicate checks. The system and method may use a function, such as a hash function, to perform the duplicate detection. Other functions, such as a Bloom filter which may use multiple hash functions, may be used to perform the duplicate detection.

The invention discloses a name routing fast matching search method and device. The device mainly comprises a tree-bitmap and a Blond filter. The tree-bitmap is used for storing the first m layers of name routing, and performing fast longest prefix matching on the first m layers of request content name reaching a router; the Blond filter is used for storing the rest of the prefix of the name routing, and performing longest prefix matching on the rest of the request content name reaching the router. According to the different prefix length of the name routing to be updated, the tree-bitmap and the Blond filter can be updated respectively or simultaneously by the method. According to the invention, the characteristics of fast searching, little required storing of the tree-bitmap and the characteristics of high time efficiency and spatial efficiency are utilized, the routing addressing problem based on the content name in the novel network system is solved, and the requirements of little occupied memory, fast matching speed and fast updating speed of the future network routing are met.

The invention discloses a real time filtrating method for large-scale garbage message based on the content, including the steps as following: 1, pre-filtrating by using the black list and the white list; 2, carrying out the online filtrating by using the filtrating module based on the frequency; 3, carrying out the fast filtrating for the message content by using the method of twice hashing; 4, carrying out the pretreating of the message text for suspicion message, and converting the same into the phase vector; 5, judging the suspicion message by using the method of combination of Naive Bayesian classifier and support vector classifier. The invention can greatly improve the filtrating speed of garbage message, and efficiently reduce the produced erroneous judgement rate in the conventional key word filtrating method; can efficiently solve the problem of group sending garbage messages with malicious intent in the short time; can efficiently avoid to mistake the common message as the garbage message so as to reduce the erroneous judgement, and efficiently improve the filtrating accuracy of whole system by analyzing the message content on the semantics.

The invention discloses a method, a system, a client and a server for detecting a phishing fraud webpage based on a feature library. The method includes the steps: acquiring a feature ID (identification) corresponding to each content fragment according to a plurality of content fragments of an extracted page, matching the feature ID corresponding to the content fragments with the feature ID in the feature library, preliminarily identifying the page, considering the page as a possible malicious page if the feature ID corresponding to the content fragments is matched with a feature ID in the feature library, and calculating an assessment score of the page according to information of the page; processing page access behaviors according to comparative results of the assessment score of the page and a set threshold value. According to the scheme, a plurality of content fragments in the page and multi-term page information are combined when the page is identified, and the scheme efficiently identifies malicious/fraud/phishing pages by the aid of the feature library and comprehensive scores of the page information without relying on a black and white list database of the server.

The invention discloses an intelligent household control system based on a multichannel interaction manner. The intelligent household control system comprises a controller and a control network, wherein the controller comprises a front-end sensor, a signal preprocessing module and a core processing chip, wherein the front-end sensor comprises a front-end camera and an audio sensor; the signal preprocessing module comprises a video preprocessing module and an audio preprocessing module; the core processing chip comprises a lip language identification module, a human face identification module and a hand gesture identification module and a voice identification module; and the control network comprises a controller communication module arranged on the controller and a household appliance communication module arranged on a household appliance. The intelligent household control system disclosed by the invention makes use of advantages of various technologies in respective application field, learns from each other, makes various technical modules relatively independent and mutually fused and realizes stability and operation comfortability.

The invention discloses a portable partial discharge ultrasonic cloud detection device, which comprises an ultrasonic sensor, a temperature sensor, a humidity sensor, an atmospheric pressure sensor, a signal processing module, a wireless network device, a display and an earphone. The sensor transmits the signal to the signal processing module, and the processed signal is transmitted to the cloud server through the wireless network device, and the signal is subjected to anti-interference processing and characteristic parameters are extracted and stored in the partial discharge signal characteristic database. For analysis, the operator monitors the sound in the earphone and makes a diagnosis based on the results of the cloud server. The diagnosis result is displayed on the monitor, and the device detects and alarms at the same time. The invention uses the data analysis, processing and storage capabilities of the cloud detection principle to detect the partial discharge in the equipment early and prevent the occurrence of major accidents through online monitoring or inspection of the partial discharge of the high-voltage equipment.

The invention provides a multi-type workpieces batch visual measuring system and a method, and belongs to the field of industrial detection automation. The measuring system comprises a data processingterminal, a workpieces detecting unit, an image acquiring unit, a control unit and the like. The measuring method comprises the following steps of: judging whether the to-be-detected workpieces are put into a detecting platform or not; obtaining a local depth image; obtaining a global image; identifying the type and number of the workpieces; and completing the size parameter measurement requiredby the measurement task. According to the multi-type workpieces batch visual measuring system and method, multiple kinds and multiple workpieces can be simultaneously detected at the same time; compared with traditional measurement means, the type and quantity of the workpieces, speed and accuracy and the like in measuring are significantly improved.

The invention discloses an online detection method and protection device for direct current system arc faults. Characteristics of current alternating components of a power circuit in the power-on starting process, the normal work process and the overload fault process of the power circuit and characteristics of the current alternating components of the power circuit during arc generating are combined, selected arc current characteristic components include peak-to-peak values and standard deviations of a time domain and a frequency component power sum within the range from 1 kHz to 100 kHz after noise of specific frequency points of a load is filtered, mahalanobis distance values of the real-time characteristic components and the characteristic components in the power-on starting process, the normal work process and the overload fault process of the power circuit through a mahalanobis distance algorithm, and the mahalanobis distance values are compared with a threshold value set in the learning process to detect whether a single arc is generated or not. By means of the technical scheme, the online detection method and protection device have advantages of being high in university, high in detection rate and low in misjudgment rate, and can be widely applied to low-voltage and high-voltage electric power systems and photovoltaic cell systems of airplanes, electric vehicles and ships, and civil high-voltage direct current power distribution systems.

The invention relates to a monitoring and filtering method and a system for utilizing an internet short message gateway to send spam messages. The method comprises the following steps: step 1, the content pre-treatment of key words is carried out; step 2, the content pre-treatment of the contents of short messages is carried out; step 3, after being carried out the content pre-treatment, the key words and the contents of the short messages are matched with each other, and the statistics of the matched sum of weighted values is carried out; step 4, the short messages with the sum of the weighted values which is in line with the preset conditions are filtered. The method can overcome the interference of the anti-filtering technology, improve the filtering success rate of the spam messages, solve the problem of carrying out the wrong filtering of the normal short messages and improve the accuracy of the judgment on the filtering of the short messages with the sending number.

A touch control screen comprises a display, at least two touch control units and a control unit. The display has a display surface. The touch control units are configured beside the display surface. Each touch control unit comprises a light source and an image sensor. The light source is configured beside the display surface and suitable to emit a beam by facing a sensing space before the display surface. The image sensor is configured beside the display surface and the sensing surface of the image sensor faces the sensing space. The image sensor is suitable to capture a light spot in the sensing space and generate an image signal. The control unit is electrically connected with the light sources and the image sensors and suitable to receive the image signals from the image sensors, as well as judges the position of the light spot relative to the display surface according to the image signals. A touch control module and a control method are also disclosed.

The invention provides a focus image detecting device. The focus image detecting device comprises an image obtaining module which obtains a medical image to be detected; A detection module that detects a lesion of the medical image according to the trained neural network model; Wherein the neural network model comprises an M-level neural network structure cascaded in sequence, and when training, anegative sample input to the second to M-level neural network structures comprises a false positive sample of the upper-level neural network structure, and M is a positive integer greater than 1.

The related garbage mail process system compromises: a garbage mail filter module in SMTP, a virus analysis module, a mail-box monitor 1, a trust database 2, and a trustness level judgment module 3 for calling the trustness value and comparing with the reference value, wherein the filter module modifies the mail trustness value according to all other process results. This invention improves system process capacity, and enhances protection on illegal access.

The invention discloses a recognition and counting method for cells, comprising nine steps: preprocessing an image in a micron-order microscopic acquisition environment; extracting cell holes from the preprocessed image; performing closed hole filling of cells by using the knowledge of a connected domain; extracting a contour point sequence of cells from the image filled in step 3; filling non-closed holes of cells by adopting a non-closed hole filling method based on circularity determination; performing chamfer distance transformation on the filled image; performing extreme value uniqueness marking on cell hole positions; segmenting the image after extreme value uniqueness by using a marked watershed method; and quantifying and marking the segmented result. The method has the advantages that the influence of image noise can be greatly reduced, the phenomena of over-segmentation and discontinuous segment lines are eliminated, the segmentation effect is improved, and the cell recognition rate is improved.

The embodiment of the invention provides a slow disk detection method and a slow disk detection device. The slow disk detection method provided by the invention comprises the following steps of: carrying out slow disk event detection for at least twice on the condition whether each hard disk in a storage array is a slow disk in a detection period; after the detection period is finished, acquiring times that a slow disk event occurs to each hard disk and determining the hard disks of which the times exceed a preset threshold into the slow disks, wherein the detection comprises the process of acquiring input output IO response time of each hard disk in the storage array, comparing the IP response time of each hard disk with a slow disk event judgment threshold and determining that the slow disk event occurs to the hard disks of which the IP response time exceeds the slow disk event judgment threshold, and the slow disk event judgment threshold is an average value of first m pieces of IP response time in the IP response time of the hard disks from big to small.

The invention provides a static analysis method and a static analysis device for an Android application program and relates to the technical field of security detection. The static analysis method includes: S1, unzipping an application program to be detected to obtain a Smali file; S2, traversing the Smali file to acquire a source code information and structuring a control flow diagram and a data flow diagram of the source code information; S3, traversing the control flow diagram and the data flow diagram according to a malicious behavior judging engine to respectively match an API (application program interface) of the application program with another API in a predefined malicious behavior library and marking the successfully matched API of the application program as the malicious behavior API; S4, calculating the malicious measuring value of the application program to be detected; S5, matching the malicious measuring value with a predefined malicious degree index to acquire risk level of the application program to be detected. Through behavior analysis and comprehensive judgment of combined rules, misjudgment rate of virus detection upon the Android application program can be reduced.

The invention relates to a battery management system with safety management. The battery management system with the safety management determines the safety state of a battery through a voltage sensor,a temperature sensor, a flammable gas sensor, a flame sensor and a smoke sensor, and can select a fire-extinguishing strategy according to the thermal runaway situation in the event of a thermal runaway. A main control unit can command a fire-extinguishing device to spray a gas fire-extinguishing medium and cool the battery when the temperature of a battery box exceeds a temperature threshold, when the rate of temperature change is too fast, when the voltage of the battery box exceeds a voltage threshold, when the rate of voltage change is too fast and when the concentration of flammable gasexceeds a threshold; and the main control unit can command the fire-extinguishing device to spray a solid fire-extinguishing medium when a naked flame is in the battery box or the concentration of smoke in the battery box exceeds a threshold.

The invention discloses a rapid lens flaw detection method and an apparatus thereof. The method comprises the following steps: equally dividing the surface of a lens to be detected into n<2> parts, respectively obtaining the images of all the parts, and obtaining n<2> images within a preset time which is used for controlling the image obtaining rate; 2, carrying out median filtering, black hat transformation and binary processing on the n<2> images respectively, and partitioning off defective images; 3, carrying out opening operation on the defective images to filter out non-flaw interference parts; and 4, drawing contours of the defective images subjected to non-defective interference filter, there are flaws on the surface of the lens to be detected if there is a counter, and no flaws are on the surface of the lens to be detected if there is no counter. The rapid lens flaw detection method provided in the invention allows scratches on the lens to be clearly detected through a surface defect detection method based on the mathematical morphology under the high speed motion of a platform, and defect types to be effectively discriminated, and has the characteristics of fast speed, objective detection result and the like.

The invention discloses an automobile and a driver fatigue early warning detecting method and system for the automobile. The driver fatigue early warning detecting system comprises a video collecting module, a facial recognition module, an eye detecting module and a judging module, wherein the video collecting module is used for collecting image information of passengers inside the automobile, the facial recognition module is used for processing the image information of the passengers inside the automobile to obtain facial characteristic parameters of a driver and obtaining facial position information of the driver according to the facial characteristic parameters of the driver, the eye detecting module is used for obtaining eye area information of the driver according to the facial position information of the driver and obtaining eye characteristic parameters of the driver according to the eye area information of the driver to detect eye characteristic information of the driver, and the judging module is used for judging whether the driver is in the fatigue state or not according to the eye characteristic information of the driver. According to the driver fatigue early warning detecting system, the driver inside the automobile can be automatically recognized, fatigue processes and movements of different drivers can be studied, the fatigued characteristics of the driver are memorized, and whether the driver is in the fatigue state or not is judged.

The invention discloses a method for the online monitoring of a fault of an insulator based on the thermal infrared imaging technology, and the method comprises the steps: employing a rectangular frame point selection method for a steel cap part, and employing line point selection for an insulator string part for coordinate and temperature conversion; obtaining four types of temperature parameter characteristic quantities through employing an insulator fault detection algorithm: a low-value insulator characteristic quantity, a zero-value insulator characteristic quantity, an insulator pollution accumulation characteristic quantity and an insulator damage characteristic quantity; selecting two three-layer PNN probability neural networks for the feature level fusion of the steel cap part and the insulator string part through combining with environment temperature, humidity and pollution conditions; giving a local information fusion judgment result; and submitting the result to a decision-making level for global decision marking. The method improves the precision of an information fusion model, clearly divides a fault and a non-fault, reduces the misjudgment rate, employs the plurality of characteristic quantities for monitoring, and combines the data of the plurality of characteristic quantities and the insulator fault judgment model to carry out the fault discrimination. Therefore, the method improves the reliability of the monitoring data.

The invention provides a method for detecting a disturbance state of a driver by utilizing a driver model. The method comprises the following steps: obtaining driving environment information of an automobile by an external sensor and judging a driving intention according to a ration between the position of the automobile and a lane boundary; when the driving intention is to keep the lane, calculating a change volume of a turning angle of a steering wheel by the driver model according to the driving environment information and the automobile state information and calculating and outputting an opening degree of an accelerator according to the present automobile speed and an expected longitudinal acceleration confirmed by a time interval between the automobile and the front automobile; when the driving intention is to change the lane, calculating the change volume of the turning angle of the steering wheel by the driver model according to the driving environment information and the state information and calculating and outputting the opening degree of the accelerator according to the present automobile speed and the expected longitudinal acceleration calculated on the basis of a lateral acceleration; comparing the turning angle of the steering wheel and the opening degree of the accelerator calculated by the driver model with a practical control data of the driver obtained by an internal sensor and judging if the driver is disturbed; and repeating the steps till stopping.