45 results about "Static behavior" patented technology

The present invention discloses a parallelized human body behavior identification method. According to the method, skeleton data of Kinect is used as input; a distributed behavior identification algorithm is implemented based on a Spark computing framework; and a complete parallel identifying process is formed. Acquisition of the skeleton data of a human body is based on scene depth acquisition capacity of Kinect and the data is preprocessed to ensure invariability of displacement and scale of characteristics; and a human body structural vector, joint included angle information and skeleton weight bias are respectively selected for static behavior characteristics and a dynamic behavior searching algorithm for a structural similarity is provided. On the identification algorithm, a neural network algorithm is parallelized on Spark; a quasi-newton method L-BFGS is adopted to optimize a network weight updating process; and the training speed is obviously increased. According to an identification platform, a Hadoop distributed file system HDFS is used as a behavior data storage layer; Spark is applied to a universal resource manager YARN; the parallel neural network algorithm is used as an upper application; and the integral system architecture has excellent extendibility.

Systems and methods for providing intelligent routing of customer inquiries via multi-channel communication tools. A dynamic router is provided that embraces interaction and manages resources of a back end system out to a portal. Such interaction can be via a chat session, a webpage, a telephone, or another manner of communication. When an individual (e.g., a customer or other individual) comes to a portal, the individual is dynamically routed to the preferred channel based on one or more of a variety of factors. A set of rules, customer information, and intelligent analysis combine to dynamically determine how to martial the resources to best service the individual. The routing provides a tailored experience specific to the particular individual rather than a static behavior that everyone would experience, and ensures that the communication takes place in a language that is desired by the individual.

Methods are disclosed wherein the structural health of a civil structure, such as, but not limited to, a bridge or the like is measured by electronic distance measurement from a plurality of stable locations to a plurality of cardinal points on the structure in a methodical manner. By measuring the coordinates of the cardinal points, the dynamic and long-term static behavior of the structure provide an indication of the health of the structure. Analysis includes; comparison to a Finite Element Model (FEM), comparison to historical data, linearity, hysteresis, symmetry, creep, damping coefficient, and harmonic terms.

Disclosed is a method and system for static behavior-predictive malware detection. The method and system uses a transfer learning model from behavior prediction to malware detection based on static features. In accordance with an embodiment of the invention, machine learning is used to capture the relations between static features, behavior features, and other context information. For example, the machine learning may be implemented with a deep learning network model with multiple embedded layers is pre-trained with metadata gathered from various resources, including sandbox logs, simulator logs and context information. Synthesized behavior-related static features are generated by projecting the original static features to the behavior features. A final static model may then be trained using the combination of the original static features and the synthesized features as the training data. The detection stage may be performed in real time with static analysis because only static features are needed. Other embodiments and features are also disclosed.

The invention discloses an SAR ADC (successive approximation register analog-to-digital converter) with resolution configurable. The SAR ADC comprises a capacitive-type ADC, a comparator, a resolution rate-configuring SAR control logic circuit and a clock circuit. Compared with the conventional resolution rate configuring technical scheme of the SAR ADC, the SAR ADC has the advantages that a switch is not required to plug in the capacitive-type ADC to configure digits of the capacitive-type ADC, and the resolution rate of the ADC is directly configured based on the SAR control logic algorithm; a configuring switch is omitted in a capacitor array, thus locating and wiring of the layout is convenient and simple, and less stray capacitance and stray resistance is introduced among key nodes such as an upper plate and a lower plate of a capacitor; better performance is imparted, noise floor, outputting signal frequency spectrum, of the SAR ADC is decreased to the normal level under resolution rate modes, harmonic waves are eliminated, and dynamic behavior and static behavior of the ADC are remarkably improved.

A method for monitoring system variables of an energy distribution or transmission grid includes measuring at least one of the system variables of a system variable vector, estimating the system variables using system equations reflecting a dynamic and static behavior of the system variables on the grid, and displaying the estimated system variables on a screen. To improve the accuracy of the estimated system variables, maximum log-likelihood estimates of the system variables are determined based on minimizing an objective function which includes a probability density function of the corresponding measurement error for each of the system variables for which measurements are taken. The objective function also includes system equations having as the system variable vector at least all of the system variables for which measurements are taken, and for at least one parameter of the state equations a corresponding predefined range of parameter values expressed as a parameter uncertainty.

The invention provides a personality prediction method based on microblog user behaviors. The method comprises the steps that first, an id list of microblog active users is acquired, personality questionnaires filled on line by tested users are acquired according to the id list of the active users through a 'talk to him' function of the microblog; second, according to the list of the tested users who fill the personality questionnaires, microblog data of the users are downloaded, and according to an established microblog network behavior system, corresponding static behavior features and dynamic behavior features are extracted from the microblog data; third, numeralization is conducted on the extracted dynamic behavior features of the users according to a time sequence analysis method to achieve a complete microblog feature set; fourth, according to a stepwise regression algorithm, a biggest obvious feature set is extracted from the microblog feature set to achieve feature selection; a personality prediction regression model is established for the selected features, and personality psychology indexes of the users are predicted.

A process for endowing a polymeric article with a surface layer of an ion-conducting polymer to yield electrical surface resistivity sufficiently low for electrostatic discharge applications is provided. The polymeric article contains one or more immobilized, polymeric components having amine functional groups. The presence of the ion-conducting polymer in the surface layer lowers the surface electrical resistivity into the range suitable for electrostatic discharge applications, between about 1×10⁵ and about 1×10¹²Ω/□. Plastic electrostatic dissipation materials produced by the inventive process may find use in the optical, electronics, automotive, entertainment, sporting goods, and medical sectors.

The invention discloses an equivalent wind speed method for processing the static power equivalent dispersion problem of a wind power station and the method is characterized by comprising the following steps: analyzing the output dispersion of each wind turbine of the wind power station, carrying out the statistic processing on the actual running data of each wind turbine, analyzing the position differences of each wind turbine and the dispersion of the inside wind energy of the wind power stations which are mutually affected, searching the wind turbine which selects the integral running action and the inside dispersion of the wind power station by the smallest error in a circulating way; confirming the equivalent wind speed, when each wind turbine is arranged in a regular manner, carrying out statistic processing on the wind speed at the locations of the four vertex angles of the wind power station to work out the equivalent wind speed and taking the N times of the output power of the wind turbine under the drive of the equivalent wind speed as the arithmetic of the total output power of the wind power station; adopting an average absolute percentage error to carry out relative analysis on the output of the equivalent model of the wind power station and the actual output of the wind power station based on the error analyzing by using the equivalent wind speed to describe the static behavior equivalence of the wind power station, thus evaluating the precision of the method and the advantages relative to the traditional method.

The invention provides a method for identifying the type of Internet of Things equipment. The method comprises the following steps: acquiring a network activity sample corresponding to to-be-identified equipment at the current moment; selecting a first preset number of first network data packets from the network activity sample; obtaining a first assignment corresponding to the first static feature from the static behavior data, and obtaining first data corresponding to the first dynamic feature from the dynamic behavior data; forming a static feature vector by the first static feature and thefirst assignment, and forming a dynamic feature vector by the first dynamic feature and the first data; combining the preset number of first network data packets, all the corresponding static featurevectors and all the corresponding dynamic feature vectors to obtain fingerprint data corresponding to the to-be-identified device; according to the fingerprint data corresponding to the to-be-identified device, judging whether the to-be-identified device is included in a first cluster corresponding to the current Internet of Things or not; and if so, determining that the device type of the to-be-identified device is consistent with the device type corresponding to the first clustering cluster.

The invention discloses an analysis method and device of APK (Android Packet) application software behavior. The method comprises the following steps: receiving an APK file and experience data uploaded by a user, wherein the experience data is the basic user information of the user under application software corresponding to the APK file; using the experience data to cause the APK file to dynamically run in a sandbox, recording the dynamic behavior of the APK file in a running process to construct a dynamic behavior set; carrying out static analysis on the APK file to construct a static behavior set; and according to the dynamic behavior set and the static behavior set, carrying out comprehensive analysis on the APK file to confirm the safety performance of the APK file. The analysis method is applied to solve the problems that a traditional monitoring way can not completely prevent illegal application software from stealing user privacy or carrying out random deduction and user experience is low due to complex and varied traditional application software once problems are found, recorded and prevented since software safety management in the prior art iscarried out in a software running process.

The invention provides a smali intermediate language-based static detection system and method. A preprocessing module is used for performing simple and quick preliminary screening analysis on mobile application software, judging whether the current mobile application software has a possible sensitive behavior or not, and judging whether a subsequent static behavior analysis program needs to be carried out or not; a rule library module is a rule which the preprocessing module depends on during sensitive behavior analysis; a sensitive behavior detection module performs detailed behavior detection on the mobile application software judged to have the sensitive behavior by the preprocessing module; and a result generation module is used for generating a report by basic information and sensitive information of the mobile application software and outputting the report. According to the smali-based detection system, the information completely reserved in the Android application software can be subjected to behavior analysis, so that the sensitive behavior existent in the application software is accurately detected out.

The invention discloses an Android malicious application detection method and system based on parallel ensemble learning, and the method comprises the steps: carrying out the reverse engineering of a to-be-detected Android application, obtaining a source code file and a configuration file of the to-be-detected Android application, and extracting static behavior characteristics from the source code file and the configuration file; screening the static behavior characteristics; constructing behavior feature vectors according to the screened static behavior features; and constructing a parallel integrated learning model according to the behavior feature vector and a machine learning algorithm, and detecting the Android malicious application according to the parallel integrated learning model. The system provided by the invention comprises an extraction module, a filtering module, a first processing module, a second processing module and a detection module. According to the method and the system provided by the invention, the Android malicious application can be comprehensively, efficiently and accurately detected by comprehensively extracting the static behavior characteristics, screening the static behavior characteristics and constructing the parallel integrated learning model.

The invention discloses a behavior recognition method and device based on deep learning, equipment and a storage medium. The method comprises the steps of collecting walking behavior information of pedestrians on a preset road section within a preset time range before a red light is turned on; extracting current static image information and current optical flow image information in the walking behavior information; performing behavior recognition on the current static image information through a deep learning static image behavior recognition model to obtain a static behavior recognition result; performing behavior recognition on the current optical flow image information through a deep learning dynamic image behavior recognition model to obtain a dynamic behavior recognition result; performing behavior recognition on the walking behavior information according to the static behavior recognition result and the dynamic behavior recognition result; and performing behavior recognition on the walking behavior information according to the static behavior recognition result and the dynamic behavior recognition result, thereby improving the behavior recognition accuracy.

The invention belongs to the technical field of mobile security in information security, and relates to a method for obtaining the encrypted data on an iOS platform. The method comprises the steps ofconstructing a continuously expanded encryption feature library by adopting a DBI technology according to a Crypto library and a third-party library built in the iOS; and when the iOS runs, extractingthe encrypted data and the key feature vector from the iOS application, and finally obtaining the encrypted data on the iOS platform. According to the method, the technology is more stable, the efficiency is higher, and the method is not influenced by the software reinforcement and the reverse debugging. Compared with reinforcement and confusion appearing in static analysis, a dynamic binary instrumentation tool breaks away from the static behavior characteristics and does not depend on static analysis any more, and has higher universality. Compared with anti-debugging behaviors appearing inconfusion and dynamic debugging, the relevant characteristics of debugging cannot be embodied in the program, and therefore the program cannot be detected more easily.

The invention discloses an apparatus for studying a sliding bearing under different working conditions. The apparatus mainly comprises a main shaft, a motor, a motor base, a shaft coupling, an antifriction bearing supporting device, a sleeve, a bearing bush, a positioning disc, a thermal imager, a fuel tank, a pedestal and a computer. When researches are carried out under different working conditions, the sleeve can be dismounted and subjected to damages to different degrees. The installation is simple and time can be saved. Furtherly, the apparatus utilizes the thermal imager which can be connected with a computer so as to convert temperature signals into a temperature distribution image. The temperature distribution and temperature changes of an oil film of the bearing bush can be observed on a display. The static behaviors of the sliding bearing can be studied according to the temperature changes and distribution under different working conditions. The apparatus designed by the invention is simple in structure and convenient to assemble. The apparatus substantially reduces experiment costs, lowers an experiment difficulty degree and is suitable for popularization and application.

The invention discloses a network data flow classification method and a system. The method comprises the following steps of collecting an information set containing a plurality of dimension information of a data flow to be processed; establishing a static behavior model and a dynamic behavior model of each piece of dimension information in the information set, wherein the static behavior model represents a value rule of the dimension information and the dynamic behavior model represents an association relation of the dimension information at one moment and at the next moment; using the staticbehavior model and the dynamic behavior model to acquire a static model distance and a dynamic model distance between a data flow to be processed and a data flow belonging to each target application type respectively; and based on the static model distance and the dynamic model distance between the data flow to be processed and the data flow belonging to each target application type, determining an application type of the data flow to be processed.

The invention belongs to the medical monitoring field and relates to a medical monitoring system. The medical monitoring system comprises a household monitoring device, an emergency calling device, anauxiliary calling device and a hospital monitoring device, wherein the household monitoring device is used for monitoring the daily behavior of a patient; the emergency calling device is used by thepatient to directly contact with a hospital, the internal portion of the emergency calling device is provided with patient medical record information, the emergency calling device is connected to thehousehold monitoring device, and the emergency calling device is provided with an emergency calling button and a confirmation button; the emergency calling button and the confirmation button are operated to directly transmit emergency calling information to the hospital; the auxiliary calling device is arranged in the household monitoring device and is used for transmitting internal information tothe family members of the patient; when the emergency calling device is not started, and the household monitoring device monitors a special behavior and a static behavior, the internal information istransmitted to the assigned communication equipment of the family members of the patient; the family members of the patient selects whether to start the emergency calling device through the assignedcommunication equipment; and the hospital monitoring device receives the emergency calling information so as to arrange medical resources. Through the system, the patient can conveniently contact witha hospital end, and the system is timely and conveniently.

The invention discloses a ruminant movement behavior identification method and system and a computer readable storage medium. The ruminant movement behavior identification method comprises the steps that the X-axis acceleration, Y-axis acceleration and Z-axis acceleration of an animal are acquired by an acceleration sensor in real time; the X-axis acceleration, Y-axis acceleration and Z-axis acceleration which are acquired in real time are calculated to obtain real-time resultant acceleration A, wherein the computational formula is shown in the description, Ax is the X-axis acceleration, Ay isthe Y-axis acceleration and Az is the Z-axis acceleration; the real-time resultant acceleration A is subjected to noise reduction treatment; the point value of the resultant acceleration A is obtained at the interval b; obtained movement behaviors of the animal are judged, wherein movement states of the animal include the static behavior, the walking behavior and the running behavior. According to the method, the ruminant movement behaviors can be monitored in real time, so that management and analysis of ruminants are facilitated.

The invention discloses polytrimethylene terephthalate fire resistant fiber and a production method thereof; the fire resistant fiber is prepared by melt spinning after polytrimethylene terephthalate and 2-carboxyethyl (phenyl) phosphinic acid are aggregated or blended. The fire resistant fiber keeps the characteristics of original PTT fiber such as softness, rebound resilience, anti-staining performance, anti-static behavior, normal pressure and temperature dyeing and the like; the fire resistant effect of the invention is superior to other polyester fire resistant products, and limited oxygen index can reach 38 percent; the PTT fiber has the function of functional fiber.