33results about How to "Monitor behavior" patented technology

The invention discloses a passenger behavior monitoring method based on machine vision, which comprises the following steps: 1) acquiring video images of a passenger riding on an escalator; 2) extracting that DPM feature of the deformable component model to describe the passenger face; 3) detecting that passenger face of an escalator by using an SVM; 4) tracing that passenger face of the hand elevator by using the KCF; 5) using an improved nearest neighbor matching method to match the face detection and tracking results; 6) establishing a face target detection intensity model and correcting aface detection result; 7) monitoring that behavior of passengers in the escalator by analyze the detection intensity, speed magnitude and speed direction of passengers. The method of the invention candetect and track the face target of passengers riding on the escalator in real time, stably and accurately, and carry out behavior monitoring based on the face target information.

The invention discloses a cross-land ship track line correction method based on obstacle-avoiding path planning, belongs to the technical field of track analysis, and aims to solve the problems that a conventional method is low in correction efficiency on a large-area land and a great number of track lines. The cross-land ship track line correction method comprises the following steps: I, acquiring a wrong ship track line; II, analyzing a buffer range of a cross land so as to obtain a land buffer area; III, dividing the land buffer area into two parts by a wrong line section of the wrong ship track line, and forming a polygon as an obstacle-avoiding polygon by a relatively small part; IV, according to the start point and the final point of the wrong line section, acquiring a shortest obstacle-avoiding path as a modified path by using the obstacle-avoiding polygon, and replacing the wrong line section of the wrong ship track line by the modified path.

The invention relates to a method for generating a ship track curve based on voluntary observation ship (VOS) data, in particular to a method for generating the ship track curve with a large number of discrete points. The method comprises the following steps: reading VOS; recognizing the voyage according to the VOS track points; arranging the VOS track point data; connecting the VOS track curves; correcting the connection of the track curves according to the obstacle-avoiding path design; generating the VOS track curve. Through adoption of the method, the problem that the ship track curve or ship route is extracted a little can be solved; the ship track curve generation method is provided; a large number of discrete VOS point data can be used for generating into a continuous ship track curve which is beneficial for mastering the regional marine traffic distribution conditions and monitor ship behavior so as to ensure the marine traffic security as well as providing decision-making reference for the marine administrative authority; the method is of great significance on protecting the life and property of people, protecting the marine environment and ensuring the national core strategic interests.

The invention discloses a passenger behavior monitoring method and device, through the pressure sensor arranged on the inner wall of the stepping surface of the escalator step pedal, the first infrared sensor arranged on the left side of the stepping surface and the second infrared sensor arranged on the right side of the stepping surface The sensor collects the pressure signal, the first behavior signal and the second behavior signal in real time; the first behavior signal is used to instruct passengers to grasp the left handrail of the escalator, and the second behavior signal is used to instruct passengers to grasp the right handrail of the escalator ; If the duration of the collected results meets the following conditions and reaches the preset time threshold: the pressure signal is collected and the first behavior signal or the second behavior signal is not collected, it is judged that the behavior of the passenger is unsafe; When it is unsafe, the control indicator lights to remind. The passenger behavior monitoring method and device of the present invention can effectively remind passengers of their elevator riding behavior, thereby improving the safety of passengers when riding an elevator.

The invention discloses a safe production management method. The safe production management method comprises the following steps of S1, mounting an electromagnetic lock onto the door plank of every workshop, forming a lock slot matched with the locking piece of the electromagnetic lock in one side of a door frame hinged to the door plank, according to the operation level of the production requirements in the workshop, numbering the level of the workshop, mounting an identification device corresponding to the level of the workshop onto the door plank of the workshop, wherein the identification device on the corresponding door plank is connected with a controller, and the controller is connected with the electromagnetic lock on the corresponding door plank; S2, ensuring that every worker needs identity identification through the identification device before entering a workshop to avoid entering a workshop without sufficient authority. The safe production management method can monitor behaviors of workers, ensure safe production and assess work of the workers; the workers can query problems during the working process via receiving computers to timely solve the problems. The safe production management method can improve the working efficiency of the workers.

The invention discloses a software automatic test management system and method based on artificial intelligence, and belongs to the technical field of artificial intelligence. A false propaganda module is arranged to identify commodities actually sold by merchants based on a deep learning algorithm, calculate differences between the commodities actually sold by the merchants and commodities propagandized by the merchants, and judge whether the merchants propagandize falsely; setting a merchant malicious drainage module to construct a malicious drainage judgment model, and judging whether the merchant is maliciously drained or not; an automatic test module is arranged to realize that one script adapts to multiple sets of environment scenes through a parameterization mechanism of the system and packaged diversified components; by setting a merchant false propaganda module and a merchant malicious drainage model to assess and monitor merchant behaviors and maintain the reputation of the platform, by setting an automatic test module and modularly managing test scenes, the scenes are combined according to specific test requirements to automatically output a test report, and normal operation of the system after multiple times of data debugging is guaranteed.

The invention provides an employee operation risk prediction method based on logistic regression. The employee operation risk prediction method comprises the steps of S1, collecting operation risk point list data and employee information data; S2, classifying risk points in the operation risk point list data; S3, extracting operation risk events and employee information data of various risk pointsto form an operation risk data set; S4, labeling the staff according to the occurrence condition of the operation risk event; S5, performing data preprocessing on employee information data in each type of risk point operation risk data set; S6, based on employee tags, establishing a logistic regression model for each type of risk points; S7, training a corresponding logistic regression model by using employee information data in each type of risk point operation risk data set after data preprocessing; and S8, the trained logistic regression model being utilized to calculate the probability ofoccurrence of various operation risk events of the employees. According to the invention, employee information data is collected, employee behaviors are monitored, manual on-site inspection is not needed, and the labor cost is reduced.

The invention discloses a method for monitoring passenger behavior based on machine vision, comprising the steps of: 1) collecting video images of passengers riding an escalator; 2) extracting deformable component model DPM features to describe passengers' faces; 3) using SVM to walk the escalator Passenger face detection; 4) Use KCF to track the face of the escalator passenger; 5) Use an improved nearest neighbor matching method to match the face detection and tracking results; 6) Establish a face target detection intensity model, correct the face Face detection results; 7) Monitor the behavior of passengers in the escalator by analyzing the passenger detection intensity, speed and speed direction. The method of the invention can detect and track the facial objects of passengers taking the escalator in a real-time, stable and accurate manner, and conduct behavior monitoring based on the facial object information.

The invention relates to a method for generating a ship track curve based on voluntary observation ship (VOS) data, in particular to a method for generating the ship track curve with a large number of discrete points. The method comprises the following steps: reading VOS; recognizing the voyage according to the VOS track points; arranging the VOS track point data; connecting the VOS track curves; correcting the connection of the track curves according to the obstacle-avoiding path design; generating the VOS track curve. Through adoption of the method, the problem that the ship track curve or ship route is extracted a little can be solved; the ship track curve generation method is provided; a large number of discrete VOS point data can be used for generating into a continuous ship track curve which is beneficial for mastering the regional marine traffic distribution conditions and monitor ship behavior so as to ensure the marine traffic security as well as providing decision-making reference for the marine administrative authority; the method is of great significance on protecting the life and property of people, protecting the marine environment and ensuring the national core strategic interests.

The invention belongs to the technical field of pollution monitoring, and discloses a ship real-time pollution monitoring system and method of a Beidou short message; it includes a ship embedded pollution data processing set system module, a Beidou satellite navigation system module, a shore-based data processing system module, and a system based on The index code table mode message module of Beidou short message. The invention uses the message function of the Beidou satellite navigation system to transmit the various pollution detection data of the ship to the two-way data transmission between the ship and the shore, realizes the integrated real-time monitoring of the ship and the shore, and satisfies the requirements of the shore-based management department or the company on various pollution gases or pollutants of the ship. The demand for real-time monitoring of liquid discharge has the effect of reducing polluted water and direct discharge of harmful gases while reducing marine environmental pollution and atmospheric environmental pollution during ship navigation. The invention effectively solves the problem that the crew or the shipowner do not discharge in accordance with the regulations of the International Maritime Organization (IMO) related pollution prevention convention (such as the MARPOL convention), which makes the pollution of the ship more serious.

The invention discloses a universal face recognition safety door. The door opening and closing device comprises an opening and closing door and a power device located in the opening and closing door.The power device comprises a power cavity; a motor is arranged in the right end wall of the power cavity; a recognition device located in the opening and closing door is arranged above the power device. The recognition device comprises a telescopic moving cavity; a conversion groove is formed in the lower end wall of the telescopic moving cavity; according to the device, the height of a person canbe automatically sensed, so that the device hidden in a door is telescopically moved to recognize a human face, password recognition is automatically switched when human face recognition fails, and when password recognition fails, a monitor hidden above pops up to monitor the behavior of the person.

The present invention discloses a system for legitimately monitoring the audio and video multimedia conference, including: a monitoring control terminal, a monitoring answer terminal, an application server and a media server, wherein, the application server is used to realize the processing logic of audio and video multimedia conference service and the legitimate monitoring; the medium service apparatus can be used to realize the media processing of the audio and video multimedia conference and the legitimate monitoring; and the monitoring control terminal can be used to initiate monitor indication and perform monitor management. The present invention also discloses a method for legitimately monitoring the audio and video multimedia conference, which realizes legitimate monitoring function by using the apparatus and function in the audio and video multimedia conference service. The present invention is suitable for audio and video multimedia conference in the field of NGN or IMS communications.

The invention discloses a ship engine room on-duty monitoring and alarm system and an alarm method. The ship's engine room on-duty monitoring and alarm system comprises: a main control box, a panel and a touch screen are arranged on the main control box, and a controller is arranged in the main control box; Remote reset device, connected to the controller, used to monitor the behavior of cabin personnel, and send the monitoring results to the controller; extended alarm, connected to the controller, the controller does not monitor cabin personnel at any monitoring position within the specified time behavior, the extended alarm is controlled to issue an alarm. According to the ship engine room on-duty monitoring and alarm system of the present invention, the problem in the prior art that the behavior of the on-duty personnel cannot be effectively monitored can be solved.

The present invention provides a method for predicting employee operational risks based on logistic regression, comprising: S1, collecting operational risk point list data and employee information data; S2, classifying the risk points in the operational risk point list data; S3, extracting Operational risk events and employee information data of various risk points form an operational risk data set; S4, label employees according to the occurrence of operational risk events; Preprocessing; S6, based on the employee label, establish a logistic regression model for each type of risk point; S7, use the employee information data in the operation risk data set of each type of risk point after data preprocessing to train the corresponding logistic regression model; S8, use The trained logistic regression model calculates the probability of employees having various operational risk events. The invention collects employee information data, monitors employee behavior, does not need manual on-site inspection, and reduces labor costs.

The present application discloses a terminal maintenance management method, device, equipment, and storage medium. The method includes: when the terminal is in an offline state, monitoring USBKey insertion and extraction events; if the monitored event type is a USBKey insertion event, determine the USBKey According to the determined permission type of the USBKey, the defense mode of the corresponding security function is automatically set to the monitoring mode, and the behavior of the maintenance personnel is monitored and the violation log is recorded. This application uses USBKey as the identity authentication method, and automatically sets the defense mode of the corresponding security function as the monitoring mode. When the network is unstable or the terminal fails, it can avoid the impact of the security mechanism on the emergency maintenance operation, and at the same time, it will not hinder the maintenance personnel on site. To prevent untimely maintenance from affecting the normal operation of the business system, and record violation logs for auditing and tracking.

The invention discloses an android ransomware detection and defense method, device and equipment and a readable storage medium. The method comprises three parts of to-be-detected android application preprocessing, operation environment detection and detection strategy. The preprocessing of the to-be-detected Android application mainly comprises the steps of detecting a ransomware in the to-be-detected Android application and injecting a monitoring agent into the to-be-detected Android application; the operation environment detection mainly comprises the steps that the monitoring agent detects calling of the ransomware to a framework layer API and Native Library so as to monitor behaviors of the ransomware; the detection strategy is mainly used for judging whether the application is the android ransomware or not according to the android application behavior to be detected. According to the invention, the ransomware in the application can be effectively detected, and malicious behaviors during application running can be analyzed; therefore, Android ransomware attacks are resisted, the user equipment is protected from being damaged by the ransomware, and the safety of the user equipment is protected.

The invention discloses a kernel-based Android application real-time behavior analysis method and a behavior analysis system capable for implementing the method. The method comprises a system call monitoring initialization step, a kernel system call interception monitoring and parsing step, a parsing result-based information logging step and an information log-based application behavior reconstruction step. A system call is intercepted and parsed in a kernel, so that an application file, a network as well as inter-process communication and other particular behaviors of the Android system are reconstructed; the whole behavior analysis process is monitored in real time in the kernel, so that the accuracy of behavior obtaining is guaranteed; meanwhile, the kernel has the highest authority, so that malware is hard to evade the kernel; according to the method, no code in the Android system is modified, so that the performance loss is low; practice proves that a result of the method can serve as key evidence to be obtained and provides a reference for malware detection.