6results about How to "Avoid missed identification" patented technology

This invention relates to a dual-stack network asset discovery method based on multi-protocol collaborative detection and intelligent fingerprint analysis; it includes the following steps: multi-source parallel acquisition: collecting network layer information of various terminal devices in the intranet through command line interface or application programming interface; data cleaning and standardization: after acquisition, cleaning and standardizing the raw data; target device identification and detection strategy generation: based on the cleaned address list and combined with device information, identifying the target device type and automatically generating corresponding detection parameters; multi-protocol asset detection packet sending: sending detection packets to target IPv4 and IPv6 addresses according to configuration parameters; response data parsing and fingerprint recognition: performing structured parsing and multi-dimensional recognition on the received response data; dual-stack network data fusion and statistical analysis: after fingerprint recognition, fusing and analyzing the IPv4 and IPv6 detection results and constructing a unified asset database.

The present invention discloses a parking distance control method, storage medium and device including visual collision monitoring, which relates to the field of intelligent vehicle control. The method includes obtaining the distance information between the vehicle and the obstacle based on the ultrasonic radar arranged around the vehicle, and obtaining the PDC recognition result; obtaining the obstacle information based on the collected vehicle surrounding environment image recognition, and performing collision detection according to the obstacle information and the vehicle running trajectory; weighting and fusing the PDC recognition result and the collision detection result to obtain the final result for collision prompting. The present invention combines the obstacle distance information of the ultrasonic radar, and the two results are weighted and fused to obtain the final result and perform collision prompting, effectively avoiding the problem of missed recognition caused by unilateral failure of the radar or surround recognition.

The utility model provides a non-road mobile machinery supervision system which comprises an image acquisition device, an RFID recognizer and a main control device. The image acquisition equipment and the RFID identifier are respectively in communication connection with the main control equipment; the image acquisition equipment is used for acquiring a license plate image of a non-road mobile machine at a passing port of a target monitoring site and transmitting the license plate image to the main control equipment; the RFID recognizer is used for recognizing a license plate RFID tag of a non-road mobile machine at a passing port to obtain license plate information and transmitting the license plate information to the main control equipment; the main control equipment is used for sending the received license plate image and license plate information to the supervision center; wherein the number of the image acquisition devices is two, the monitoring directions of the two image acquisition devices are opposite, the monitoring direction of one image acquisition device faces the passing opening, and the monitoring range of the two image acquisition devices and the recognition range of the RFID recognizer jointly cover the area where the passing opening is located.

The invention provides a sensitive data recognition method and device.The method comprises the steps that in response to task creation operation, a sensitive data recognition task is created on a task creation page, and the data recognition task comprises a target data source and a target sensitive data recognition rule; the target sensitive data identification rule is obtained based on target data classification and at least one target data security grading configuration; in response to a trigger operation of the target control, executing a sensitive data identification task to obtain to-be-identified data from the target data source; and identifying the target sensitive data from the to-be-identified data by adopting the target sensitive data identification rule, thereby realizing the target sensitive data identification rule obtained by flexibly specifying a target data source in a task creation page and performing configuration based on target data classification and target data security classification by a user according to actual requirements. The pertinence and the accuracy of a sensitive data identification task are ensured, so that the high efficiency and the accuracy of sensitive data identification are improved.

This disclosure relates to the field of raw coal sorting technology, specifically to a material identification method, a material sorting method, a material identification device, and equipment. The material identification method includes: acquiring a target image of the material to be identified; determining the contour of the material to be identified based on the target image; inputting the target image into a target recognition model to determine multiple recognition boxes included in the target image and their corresponding material types; and determining the type of the material to be identified based on the contour, the multiple recognition boxes, and the corresponding material types. This method can avoid spatial misalignment problems, overcome the limitations of single features, and eliminate interference from impurities, thereby helping to improve the overall accuracy and reliability of material identification and enhancing the material identification's resistance to environmental interference.

The invention relates to the technical field of network security, in particular to a risk identification system based on text and image bimodal fusion, which is characterized in that for text modal information, enhanced coding is carried out on webpage texts by constructing a Chinese sensitive knowledge graph fusing voice, fonts and semantics so as to accurately identify variation sensitive words; webpage visual features are extracted from the image modal information and fused with an OCR text; a cross-modal attention alignment mechanism is introduced to realize deep semantic interaction and complementary verification of text and image features, and finally, risk classification is performed on the fused features, and a reliable result is output by adopting confidence coefficient calibration. According to the method, the identification precision of risks such as variation content and disguised secret words is remarkably improved, and the robustness and accuracy of risk identification are improved.