14results about How to "Eliminate duplication" patented technology

The present disclosure belongs to the technical field of video quality evaluation, and particularly relates to a video quality evaluation method, system, device and medium based on multi-modal parallel analysis, which comprises the following steps: receiving a course video to be audited, loading user preset audit parameter configuration; unpacking the course video to be audited to obtain an initial video coding stream and an initial audio coding stream, simultaneously performing audio track integrity checking, terminating the audio analysis process based on the checking result, only performing video analysis, or simultaneously performing video and audio analysis audit processes; pre-processing the initial video coding stream and the initial audio coding stream; based on an asynchronous parallel architecture, performing multiple audit tasks on the standard image frame sequence and the standard audio data in parallel to obtain multiple output results; converging the multiple output results, performing cross-modal space-time alignment and fusion deduplication processing to obtain a processing result; and generating a structured audit report according to the processing result. The present application improves the efficiency and accuracy of video quality evaluation.

This invention relates to the field of computer vision, specifically to a monitoring method based on cascaded target detection, comprising: acquiring a monitoring screen; recognizing the monitoring screen using a trained first YOLO model and cropping out target region images; recognizing each target region image using a trained second YOLO model and obtaining target information therein; and summarizing the target information to a host computer; the target information includes a region number, and the step of obtaining the region number includes: locating target character information in each target region image using a trained second YOLO model; recognizing the located target character information using OCR technology, and confirming the region number based on the recognition information; the step of summarizing the target information to a host computer includes: when any target region fails to be recognized within a preset time period, summarizing and transmitting the target information corresponding to that target region to the host computer; after successful transmission, restricting other target information carrying the region number of that target region from being uploaded again.

The invention relates to a virtual resource delivery method and device, computer equipment and a readable storage medium. The method comprises the steps of obtaining a virtual resource delivery order uploaded by a to-be-delivered enterprise; the to-be-delivered enterprise characterizes the identity verification and authorization based on the block chain technology, and the authorized enterprise passing the identity verification carries out the uplink processing of the virtual resource delivery order, and under the condition that the hash value corresponding to the virtual resource delivery order is detected in the distributed account book, the virtual resource delivery order is sent to the distributed account book. And generating a virtual resource delivery request corresponding to the virtual resource delivery order, and finally responding to the virtual resource delivery request, and executing virtual resource delivery according to the virtual resource delivery order through a preset smart contract. According to the method, the blockchain technology is used as a technical basis for executing virtual resource delivery, so that the problems of order forgery and repeated pledge are completely eradicated, meanwhile, multiple nodes participate in the delivery process of the virtual resources, the credibility of virtual resource delivery is ensured, and thus the credibility of virtual resource delivery is improved.

The application relates to the field of intelligent operation unmanned planes, and discloses a plant protection unmanned plane cooperative operation spraying area control method, which constructs a multi-unmanned plane cooperative hanging type spraying system; a Lagrange method is used to establish an underactuated dynamics model of a single plane hanging load system, and mutual constraints among the multi-unmanned planes are considered under the multi-unmanned plane framework; a barrier Lyapunov function (BLF) is designed, and full-range constraints are applied to single plane load displacement and relative distances among the multi-unmanned planes; RBF neural network is used to compensate system nonlinearity and external disturbance on line; an adaptive thrust control law of multi-plane coordination is designed, high-precision trajectory tracking of each unmanned plane, strict constraints of load displacement, and collision-free guarantee among the medicine boxes are realized; the application can effectively eliminate the collision risks among the unmanned planes and among the medicine boxes by pre-planning reasonable trajectories, and can avoid medicine waste caused by repeated spraying.

The application discloses a front-end page generation method and device, a program product and electronic equipment, and relates to the technical field of front ends, and the method comprises the following steps: analyzing annotation data of back-end code to obtain an analysis result, wherein the analysis result at least comprises a page identifier and component data of L page components, L is a positive integer, the page identifier is used for representing a function implemented by the back-end code, and the type of each page component is one of the following: a form type and a table type; determining a page template corresponding to the back-end code based on the page identifier, wherein the page template comprises at least one of the following: a form page sub-template and a table page sub-template; generating target front-end code based on the component data of the L page components and the page template; and generating a target front-end page corresponding to the back-end code based on the target front-end code. The application solves the technical problems of low generation efficiency and inconsistent page styles of front-end pages in the prior art.

This invention relates to the field of drug sorting and screening technology, and discloses a drug storage device and intelligent drug sorting method based on AI deep learning. The device includes a drug storage unit, a data acquisition and display unit, a decision management unit, a storage environment control unit, a drug screening unit, and a drug output and recycling unit. The data acquisition and display unit is used for user input of stored drug information, high-definition photography of the drugs, and the use of AI recognition technology to achieve visual recognition and measurement of the drug's appearance and dimensions. Continuous deep learning improves the accuracy of drug appearance recognition, facilitating the drug screening unit's selection of drug quantities. The drug screening unit automatically sorts and selects the required quantity of drugs for patients at specific times, based on different drug dosage regimens. This invention effectively solves the problem of low patient medication adherence, is highly practical, reliable, has low implementation costs, and targets a large beneficiary group.

The invention discloses a power head structure of a large-aperture casing drilling machine. The power head structure comprises a box body, and an input gear shaft, a middle idle gear and a connecting cylinder are arranged in the box body; one end of the input gear shaft is connected with the planetary reducer, and the input gear shaft is meshed with the middle idle gear to transmit power; the connecting cylinder is connected with the box body through a first tapered roller bearing, a thrust ball bearing and a deep groove ball bearing, and an output gear meshed with the middle idle gear is arranged on the outer side of the connecting cylinder; the top of the connecting cylinder is provided with an upper transparent cover connected through a labyrinth seal, and the bottom of the connecting cylinder is provided with a hydraulic clamping device. The high-speed-ratio power transmission device is simple in structure, stable, reliable and convenient to maintain, power transmission with the high speed ratio of 130 or above can be achieved, and high-torque output is conducted; casing running operation can be synchronously completed in the drilling process, and the jamming risk is greatly reduced; repeated links of pulling out of a hole and running a casing pipe are omitted, the construction period is shortened by 40%-60%, and the working efficiency is greatly improved.

This invention relates to a heterogeneous store-and-forward switching method and system for multi-port CAN Ethernet. The method includes: uniformly setting each physical port as a logical port; in an interrupt service routine, appending a source port identifier and internal formatting to the received lightweight packets and storing them in a receive buffer queue; in the device's main loop, retrieving packets from the receive buffer queue, delaying device management frames in the packets to a security context, and executing a forwarding process for the remaining frames; in the forwarding process, matching the source port with a forwarding rule set to generate an output port bitmap, and then calling the matching sending backend to construct a forwarding path according to each target port type in the output port bitmap; dividing the maintenance tasks of the switching device into time slices, executing them in rotation during each main loop cycle, and limiting the duration of each execution. This invention achieves efficient and reliable store-and-forward switching for multi-port CAN Ethernet heterogeneous networks under harsh environments.

The application relates to the technical field of AI engine and discloses a cross-modal AI processing platform and a method thereof, wherein the method comprises the following steps: generating a relay context carrying a modal type set and a target model name according to a platform API key in a request header, and determining target channel configuration information and an alternative channel identifier from a registered channel in a channel capability table; performing message list field structured remapping, non-support parameter elimination and channel API key injection processing on a request body to obtain a target channel format request message and send the target channel format request message to a service endpoint in the target channel configuration information to obtain a downstream channel response message; and performing reverse structured remapping and streaming push data frame standardization processing to obtain a standard format response message and return the standard format response message to a request initiator, so that the technical problem of repeated development of multiple sets of protocol adaptation codes in the prior art is solved, and fine operation control of the cross-modal AI engine aggregation platform is realized.

The invention discloses a multicast monitoring method and device under a cross-device aggregation group, equipment and a medium, and relates to the technical field of communication, and the method comprises the steps: receiving an Internet group management protocol (IGMP) report message or a leaving message of an aggregation link; updating a multicast member port list of the equipment according to the IGMP report message or the leaving message; and sending the IGMP report message or the leaving message to a cross-device aggregation group (MLAG) opposite-end device through an inter-device dedicated control channel, so that the MLAG opposite-end device synchronously updates a multicast member port list. According to the method, the cooperative work of the multicast monitoring protocol on two virtualized devices can be completed.

The application belongs to the technical field of power systems, and discloses a high-frequency vibration signal cooperative processing method and system, which comprises the following steps: receiving a high-frequency vibration signal and writing the signal into a real-time buffer according to a signal channel to generate waveform statistical features; performing dynamic subscription and dynamic unsubscription operations on the signal channel, applying a delay operation to the dynamic unsubscription operation, reading target waveform data in a time window, and generating a set of intercepted segments; performing batch learning and coordinated processing on the set of intercepted segments according to an optimal path to obtain batch learning samples; writing the waveform statistical features, the set of intercepted segments and the batch learning samples into an asynchronous archiving queue and generating an archiving file; in an offline stage, performing intersection interception operation on a target interception interval and an original data block interval determined by a data block index in the archiving file to generate an offline segment file for offline review, export and reanalysis. The application reduces invalid event processing and full-amount rule evaluation, and improves system response efficiency.

The present application relates to the technical field of intelligent conference collaboration, and especially relates to a task adaptive allocation method and system in intelligent conference collaboration. A knowledge matching network is constructed based on task knowledge dependency and participant knowledge graph, and a knowledge propagation path is deduced, necessary knowledge nodes and gap nodes are identified, and a knowledge complementarity degree is calculated. According to the analysis result and the collaboration granularity characteristics, a task set is reconstructed through a bidirectional adjustment mechanism, tasks are decomposed and a knowledge transmission interface is established, or tasks are aggregated and a knowledge sharing mechanism is established. According to the reconstructed task structure and the cognitive switching cost, a cognitive state transition graph is constructed, a task execution sequence with minimum cognitive switching cost is planned, a time window is aligned, and a task allocation instruction is generated. The present application improves the adaptability and execution efficiency of task allocation, and reduces the cognitive switching cost.

This invention provides an automated loading and unloading operation method based on the linkage of multiple intelligent systems, including: constructing a generalized three-dimensional ship model using ship design software; activating three major systems: loading computer, intelligent liquid cargo management, and intelligent energy efficiency; and activating standard data interfaces between the systems; inputting the three-dimensional ship model into the loading computer system to generate a visualized target ship model; collaboratively collecting data from the target ship model; generating multiple compliant loading schemes based on the target ship model and the data collected collaboratively by multiple systems; obtaining the optimal loading scheme based on the comprehensive score calculated from the loading schemes; inputting the optimal loading scheme into the intelligent liquid cargo management system to execute intelligent loading and unloading operations at port, thereby improving the efficiency of system data collaboration and reducing the instability of manual loading and unloading operations.