247results about How to "Timely identification" patented technology

The invention relates to a multi-feature fusion phishing webpage detection method, which comprises two parts such as a training process and a detection process. The multi-feature fusion phishing webpage detection method integrates three views of phishing webpage characteristics by combining a semi-supervised learning tri-training method, and mainly solves a problem that the existing phishing webpage detection methods mostly need to perform classification model training by using supervised learning through a large amount of annotation data. The method provided by the invention mainly combines a coordinated training algorithm, starts from webpage URL characteristics, webpage information characteristics and webpage search information characteristics, applies the idea of multiple views and multiple classifiers to phishing webpage detection, and achieves the purposes of reducing the total numbers of manual annotation training samples and timely recognizing a phishing webpage through coordinated training and learning of different classifiers.

The invention provides a recognition method of micro-short circuiting of batteries. Whether a series-connected battery pack has micro-short circuiting, which specific battery cell has micro-short circuiting and what time micro-short circuiting occurs can be judged by judging whether an off-group point exists in voltage derivative or voltage differential of each battery cell of the series-connected battery pack at the same time, and the condition that micro-short circuiting is internal short circuiting or external short circuiting can be distinguished with an information entropy judgment method. The recognition method of micro-short circuiting of the batteries plays a key role on safety improvement of products, such as an electric car and an airplane, utilizing the power battery pack.

The invention discloses a method for recognizing iris in human eye images, and the method comprises the steps: building a preset convolution neural network; selecting a plurality of human eye images in advance, and carrying out the preprocessing of the human eye images; carrying out the training of the preset convolution neural network till an obtained preset convolution neural network model is convergent; carrying out the second image preprocessing of a pair of to-be-tested human eye images, the iris recognition of which needs to be carried out, and obtaining corresponding to-be-tested iris film image pairs with the preset size; inputting the to-be-tested iris film image pairs into the trained preset convolution neural network model in the mode of two channels, obtaining the correlation score of the to-be-tested iris film image pairs, and judging whether the to-be-tested iris film image pairs are of the same type or not. The invention also discloses a device for recognizing iris in the human eye images. The method and device can carry out the timely and accurate recognition of the iris in the human eye images collected in a controllable scene and a non-controllable scene, meet the requirements of a user for the iris recognition, and can improve the work efficiency of the user.

The invention relates to a pressure-while-drilling measuring device and a measurement method thereof. The pressure-while-drilling measuring device is characterized by comprising an outer shell in which a central flow channel is formed; the outer shell is provided with a split-flow pressurization mechanism, an execution mechanism and an oil line reversing mechanism sequentially; the execution mechanism is provided with a pumping mechanism; the split-flow pressurization mechanism controls the opening and closing of the execution mechanism by using the acting force of slurry in the central flow channel and a split-flow piston; and the execution mechanism and the oil line reversing mechanism are matched with each other to push out and reset all sliding blocks in the pumping mechanism, so thatthe stretching and retraction of a probe can be realized, and bottom fluid is pumped by a pumping cylinder and a piston rod of the pumping mechanism and is measured. The pressure-while-drilling measuring device can accurately acquire the underground formation pressure in real time, staff can timely identify the complex underground geological factors by using the formation pressure data and further adjust the drilling parameters, and the complex conditions of leakage, collapse, overflowing, blowing and the like during drilling can be effectively avoided, so that the pressure-while-drilling measuring device can be widely used in the drilling process.

The invention discloses a multisource and multi-parameter fusion-based electric transmission/transmission equipment state abnormal mode recognition method and device. The method comprises the following steps of: obtaining original monitoring data; respectively sorting various pieces of state quantity data according to a time sequence; judging whether each piece of state quantity data is candidateabnormal data or not; when the state quantity data is the candidate abnormal data, generating a candidate abnormal data sequence at the current moment; and when the candidate abnormal data sequence does not accord with a preset normal data clustering feature, obtaining a plurality of monitoring data sequences in a first time period which comprises the current moment, and judging whether electric transmission/transmission equipment is abnormal or not according to the plurality of monitoring data sequences. The multisource and multi-parameter fusion-based electric transmission/transmission equipment state abnormal mode recognition method and device are capable of effectively reducing the algorithm complexity and space required for data storage and calculation, and can be used for rapid and effective recognition of various electric transmission/transmission equipment abnormal states.

The invention discloses a full-process three-dimensional dynamic safety management method of a building enterprise. According to the method, a bidirectional closed-loop operation mode is utilized. Through performing classification and identification processing on engineering projects which enter a safety risk evaluation database, an engineering project safety evaluation report is generated. An engineering project three-dimensional dynamic safety hazard monitoring model is established in a second-level enterprise layer and potential hazard early-warning information is issued. Real-time monitoring for sensor and video, and artificial regular checking and modification are performed at a project part. A safety accident is handled immediately. The three-dimensional dynamic safety hazard monitoring model is instantly updated. After the engineering project is finished, updating learning is performed on a safety risk evaluation database. According to the full-process three-dimensional dynamic safety management method, learning and reutilization are performed on safety management historical data of the building enterprise. Advanced forecasting, early warning and prevention are performed on the potential safety hazard. The safety event is reasonably handled immediately after occurrence. Safety of persons, fund and property in the engineering project of the building enterprise can be effectively ensured. Furthermore loss is reduced.

The invention discloses a multifunctional delivery process of cigarette finished products. A warehouse management system WMS is used for judging whether to carry out direct delivery from a warehousing system or not according to the inventory situation, when the inventory is insufficient, the delivery can be directly carried out from a workshop, when the inventory is sufficient, the direct whole tray ex-warehouse delivery or the delivery after unstacking can be selected according to the actual demands of ex-warehouse cigarette pieces. A bar code recognizer and an RFID reader and writer are arranged on a conveying line, thereby respectively carrying out information reading on the cigarette pieces and a tray and then conveying to different working positions. The multifunctional delivery process re-integrates the robot technology, the radio frequency identification technology and the cigarette piece carton confluence sorting technology, thereby effectively upgrading the flexibility of an automatic ex-warehouse system, increasing the delivery channel of the ex-warehouse system and carrying out direct delivery without warehousing. The delivery operation takes the whole tray as a unit for carrying out the automatic ex-warehouse delivery, thereby greatly increasing the efficiency of the logistics of the cigarette finished products. The multifunctional delivery process can further integrate the functions in the similar logistics field in the limited geographical space, thereby being more in line with the requirements on economy, simplification and efficiency.

The embodiment of the present invention provides an identifying and monitoring system for a license plate and a vehicle and a monitoring server. The identifying and monitoring system for a license plate and a vehicle is applied to the vehicle. The system comprises a first front camera, a second front camera, a first rear camera, a second rear camera and the monitoring server. The first front camera and the second front camera are used for taking a photo of a front license plate and a photo of a vehicle front end profile, and the first rear camera and the second rear camera are used for takinga photo of a back license plate and a photo of a vehicle back end profile. The monitoring server is used for performing three-dimensional reconstruction on the obtained front license plate photo, backlicense plate photo, vehicle front end profile photo and vehicle rear end profile photo to output a recognition result. The recognition result at least comprises a license plate number, a vehicle color and a vehicle type. Thereby, license plates and vehicles can be quickly identified, and vehicles with fake plates are fought.

The invention aims to provide a method and equipment for calling configuration information. The method comprises the following steps: acquiring a configuration information request of service equipment, wherein the configuration information request includes service identification information of the service equipment; acquiring target encrypted configuration information which is matched with the service identification information from a corresponding first database based on the configuration information request; decrypting the target encrypted configuration information in order to obtain corresponding target configuration information; and transmitting the target configuration information to the service equipment. Compared with the prior art, the method and the equipment have the advantages that different configuration information requests from different service equipment are managed centrally by a web server, so that only corresponding configuration information in the web server needs to be modified when service database information is changed; the service equipment can acquire newest corresponding target configuration information by sending the configuration information requests; and the resource consumption of data processing is saved on the whole.

The invention discloses a product defect automatic detection platform and belongs to the field of product defect detection. The structure of the product defect automatic detection platform comprises apedestal, a rotary workbench, a fixed workbench, a loading mechanical arm, an unloading mechanical arm, a middle mechanical arm, camera combination and a camera adjusting device; the camera combination is arranged on the camera adjusting device; the camera combination comprises three sets; two sets are arranged on the left side of the camera adjusting device; one set is arranged on the right sideof the camera adjusting device; the rotary workbench and the fixed workbench are arranged on the left side and the right side of the pedestal correspondingly; the loading mechanical arm is arranged on the left side of the rotary workbench; the unloading mechanical arm is arranged on the right side of the fixed workbench; the middle mechanical arm is arranged on the front side of the rotary workbench and the fixed workbench; the camera adjusting device is arranged on the back side of the rotary workbench and the fixed workbench; and the rotary workbench, the loading mechanical arm, the unloading mechanical arm, the middle mechanical arm and the camera combination are electrically connected with a controller. The product defect automatic detection platform completely replaces manual detection, obviously improves the detection efficiency of the products and obviously increases the detection accurate rate of the products.

The present invention discloses a method and device for identifying a malicious website, relates to the technical field of internet, and can efficiently identify the malicious website. The method of the present invention includes: first capturing user feature information input in a log-in page, then searching for a set of trusted domain names corresponding to the user feature information in a white list, finally comparing the domain name of the log-in page with all trusted domain names in the set of trusted domain names, and if the domain name of the log-in page does not belong to the set of trusted domain names, prompting the user with a warning. The present invention is mainly used in the procedure of identifying a phishing website.

Segmentation messages indicative of locations of upcoming events, such as the start and end of programs and program portions, and/or rights related to the programs and program portions, are used by cable systems and the like to store programs and program portions for later retrieval and transmission to customers on request. Storage, retrieval and management of programming is thereby facilitated. Methods and systems are disclosed.

The invention relates to the technical field of computers, in particular to an abnormal account recognition method and device, computer equipment and a storage medium. The method comprises the steps of obtaining user portrait data of a first user account meeting a first preset rule; determining a second user account meeting a second preset rule from the first user accounts according to the user portrait data and a trained clustering model; acquiring user equipment data of a second user account; and determining a third user account meeting a third preset rule from the second user accounts according to the user equipment data and the trained classification model, and determining the third user account as an abnormal account. According to the embodiment of the invention, abnormal users possibly having batch number brushing behaviors in the game can be timely and accurately identified.

The invention discloses an industrial process fault diagnosis method based on high order correlation and belongs to the field of industrial process monitoring. According to the method provided by theinvention, high order correlation information in measurement data of each sensor is obtained without supervision from an angle of representing learning through utilization of a stack sparse self-coding network, and three monitoring indexes SRE, M2 and C are provided for obtained high order correlation characteristics. In a hierarchical learning mode, according to the method, change of a small fault or an early fault in an industrial process is represented relatively finely, so detection of whether the fault occurs or not is facilitated. According to the provided monitoring indexes, whether process operation is kept in a control domain or not can be monitored and certain guidance for identifying a fault type is provided. In an unsupervised learning mode, influence of insufficient sample labels and imbalanced data in the industrial process is not influenced. The method has important practical significance in solving an industrial process monitoring problem in practice.

The invention relates to a method utilizing event-related potentials equipment to assist in screening mild cognitive impairment. The method adopts the event-related potentials technology to assist in screening mild cognitive impairment (MCI) and judging clinical intervention effect, adopts the learning-recognizing experimental mode to allow a testee to learn and recognize three emotional faces (positive, neutral and negative) during operation, and also utilizes event-related electrocortical potentials equipment to record the electroencephalogram of the testee. Collected data are calculated according to the unique algorithm, so that four indexes, such as the response accuracy, the N170 ingredient, the early-stage old/new effect and the late-stage old/new effect of the testee, become effective indexes for recognizing MCI, and the method is used for early-stage diagnosis and curative effect determination of MCI, is noninvasive, can be easily accepted by patients and is suitable for clinical popularization.

The invention discloses an intelligent community safety monitoring system and a safety monitoring method. The system comprises a monitoring cloud, a video monitoring unit, an entrance monitoring unit, an outlet monitoring unit, a field prompting unit, an automatic alarm unit and a hand-held terminal. The monitoring cloud is arranged in an equipment operation room; the video monitoring unit is connected with the monitoring cloud through an electric signal transmitted in the electronic connecting line; the entrance monitoring unit is installed at an entrance of a community and is connected withthe video monitoring unit via an electric signal transmitted in the electronic connecting line; the exit monitoring unit is installed at a community exit and is connected with the video monitoring unit through an electric signal transmitted in the electronic connecting line, the on-site prompting unit is installed on the community monitoring device, and the automatic alarm unit is connected withthe monitoring cloud through an electric signal transmitted in the electronic connecting line. According to the smart community safety monitoring system and the safety monitoring method, the identities of people entering and exiting the community can be identified in time, and the community comfort level index is improved.

The invention discloses a dangerous article detection method and device, a mobile terminal, and a computer readable storage medium. The method comprises the steps: transmitting a wireless signal, andreceiving a reflected signal of the wireless signal; determining whether there is a target object of a preset type in the articles reflecting the wireless signal or not according to the reflected signal; obtaining the image information of the target object if there is the target object of the preset type; and determining whether the target object is a dangerous article or not according to the image information. Through the scheme of the invention, the method can help a user timely understand the potential threats in the environment, and improves the safety of a user to a certain degree.

The invention discloses a real-time face recognition method, a real-time face recognition system and electronic equipment. The real-time face recognition method comprises the following steps: judgingwhether the central position of a face image region is located in a preset effective face region or not, and judging whether the face image region can be expanded or not to obtain an expanded face image region; and the expanded face image area is inputted to a face living body recognition network model to output the probability that the face in the image is a false face, and whether the probability of the false face is greater than a preset probability threshold is judged so as to perform face calibration operation on the face image area to obtain the calibrated face image area. And performingface recognition operation on the calibrated face image area through a face recognition network model, so as to select a face closest to the face in the image from a face database as display output.According to the invention, true and false faces can be distinguished in real time, and the recognition precision is high.

The invention discloses a method for site remaining intelligent video recognition of electric power operation tools and instruments. The method comprises the steps of collecting video images through a front-end camera; decompressing the video images collected, and decomposing the video images into YUV pictures; converting the YUV pictures into RGB pictures; decomposing the pictures frame by frame, randomly extracting multiple frames to make an analysis comparison; comparing a next picture frame with a last picture frame, updating the background environment in real time by utilizing self learning, and extracting target objects from the background environment so as to judge whether the tools and the instruments remain on the operation site. According to the method, the remaining conditions of the electric power operation tools and instruments can be recognized conveniently and timely, an alarm can be made actively against the conditions that the tools and the instruments remain on the electric power operation site due to negligence of workers, work of the workers is standardized, and the potential safety hazard is eliminated.

Perceptual visual quality of different image sets is automatically assessed. A computing device includes a processor and a memory coupled to the processor. The memory includes an image assessment module configured to obtain features from each of the image sets, and generate feature vectors corresponding to the obtained features. The image quality assessment module is configured to compute a set of quality scores corresponding to the feature vectors associated with each of the image sets. The image quality assessment module is also configured to automatically determine an image set having an optimal perceptual visual quality among the image sets using the corresponding set of quality scores.

The invention relates to a photoelectric data transmission system and method implemented through a single network card. The system comprises an electrical port, an optical port, a central processing unit, a PHY chip, an internal memory and a flash memory, wherein the central processing unit is used for inquiring, generating a control code according to a medium insertion state value and a data transmission state value, sending the control code to the PHY chip, receiving and storing data packets sent by the electrical port or the optical port into the internal memory and storing the data packetsinto the flash memory when data transmission is abnormal; the PHY chip is used for receiving an electric signal and an optical signal, modifying the medium insertion state value and the data transmission state value according to the electric signal and the optical signal, and receiving the control code to achieve soft handoff communication with the electrical port or the optical port. By means ofthe system and method, resources are saved, the data packets of the optical port and the electrical port can be recognized in time, and the integrity of the transmitted data can be ensured.

The invention provides a method and device for identifying fraud and electronic equipment, and the method comprises the steps: identifying to-be-identified behavior data based on a classification model; when the to-be-identified behavior data is abnormal, determining an auditing result of the to-be-identified behavior data; taking the to-be-identified behavior data as a positive sample and addingthe positive sample into a preset sample set; taking the to-be-identified behavior data as historical behavior data, and extracting outlier historical behavior data corresponding to outliers in the historical behavior data based on a preset outlier detection model; and when the outlier historical behavior data belongs to fraudulent behaviors, adding the outlier historical behavior data as a positive sample into the sample set, and then training the classification model again based on the updated sample set. Through the technical scheme provided by the embodiment of the invention, the number ofsamples in the sample set is increased, the classification model can identify novel fraud behaviors in time, and the identification effect of the classification model is improved.