15results about How to "Reduce computing pressure" patented technology

The application relates to the technical field of storage computing, and discloses a system, a method and an electronic device for directly searching data in a storage medium, the system comprising a large-scale vector database, a nearest neighbor search operation unit and a host computer, the large-scale vector database is arranged in the storage medium and is used for storing a vector set; the nearest neighbor search operation unit is arranged in the storage medium; the host computer is provided with a CPU and a cache unit; when the nearest neighbor search operation unit receives an NNS_CSD instruction sent by the CPU, the vector of the database is read, similarity measurement is carried out, and the search result meeting the condition is sent to the cache unit, the application directly searches data in the storage medium, the NNS_CSD instruction is used to start the calculation in the storage medium, the nearest neighbor search operation unit in the storage medium is used for vector reading and similarity measurement, compared with a traditional architecture, the migration of data is greatly reduced, and the overall performance is improved.

The invention discloses a complex dynamic industrial visual positioning method and system based on multi-agent collaboration, and relates to the technical field of machine vision, distributed visual agent nodes are deployed in an industrial dynamic operation scene, and node microsecond-level time synchronization, space joint calibration and communication networking are completed; the nodes synchronously collect industrial images according to a preset time sequence, and a standardized data set is generated through preprocessing; dynamic target feature extraction is completed based on an improved deep convolutional neural network, and cross-node feature matching is completed in combination with epipolar constraints; a multi-view geometric constraint model is constructed to solve the three-dimensional pose of the target, and a positioning result is generated through dynamic interference compensation optimization; and outputting a positioning result, completing closed-loop feedback, and dynamically adjusting node parameters to realize multi-agent collaborative global optimization. According to the invention, the precision and the anti-interference capability of visual positioning in a complex dynamic industrial scene are improved, the multi-node load balancing is optimized, and the visual positioning operation requirements of various industrial dynamic scenes can be met.

The application discloses a kind of based on thing networking's wisdom building energy consumption management and equipment monitoring system, belong to building intelligent management technical field.System uses layered distributed architecture, is composed of perception layer, network transmission layer, edge computing layer, platform application layer, terminal control layer;Perception layer realizes energy consumption, equipment, environmental global data acquisition, network transmission layer uses wired wireless dual-mode communication to guarantee data transmission, edge computing layer realizes local instant processing and emergency control, platform application layer realizes cloud big data analysis, visual management, intelligent strategy generation, terminal control layer realizes equipment automation regulation and control.The application overcomes the defects of traditional building management energy consumption waste, operation inefficiency, data isolation, insufficient intelligence, can realize building energy consumption accurate measurement, dynamic analysis, intelligent regulation and control, equipment full period monitoring, fault early warning, automation operation, effectively reduce building energy consumption, reduce operation cost, improve operation safety, applicable to various office buildings, shopping malls, communities, parks and other buildings, with excellent novelty, creativity and practicality, meet the development needs of green low-carbon building.

The application discloses an unmanned aerial vehicle obstacle avoidance method based on digital twinning in an unstructured scene, which comprises the following steps: S1, constructing a geometric perception digital twinning system; S2, collecting unknown obstacle information and performing geometric synchronization; S3, performing dynamic modeling and discretization on a virtual unmanned aerial vehicle; S4, constructing a pseudo-control input and a linear prediction model; S5, generating a safe flight corridor; S6, performing local re-planning; S7, establishing a disturbed system and an error system; S8, constructing a robust positive invariant set and performing constraint tightening; S9, constructing a space adaptive tube MPC optimization problem; S10, performing online space adaptive adjustment; and S11, outputting a control instruction and maintaining virtual-real synchronization. By mapping unknown obstacles in a physical space to a virtual space in real time, a safe flight corridor is constructed, local re-planning and space adaptive tube MPC are combined, and the unmanned aerial vehicle can realize safe obstacle avoidance, high-precision trajectory tracking and low control energy consumption in an unstructured environment.

The application discloses a kind of based on partial quantification's hybrid expert network optimization method, it is related to information technology field, including the following steps: S1, selected data sample set, carries out hybrid expert network sampling;S2, establishes the corresponding relationship of subnet and data set, selects high-frequency subnet and corresponding data set;S3, with corresponding data set to selected high-frequency subnet is iterated quantization processing.The application obtains the corresponding relationship of different data set and different subnet in hybrid expert network by carrying out data flow sampling to the reasoning process of hybrid expert network, then carries out quantization optimization to different subnet on corresponding data set, to reduce the calculation burden required for the overall optimization of hybrid expert network, to improve the service throughput of entire network.The data set corresponding to the subnet used frequently is used to carry out quantization processing on the subnet, i.e.to avoid quantization processing on the entire network, simple and efficient, improve the performance of entire network.

The present application relates to the technical field of pedal data processing, and particularly relates to a method and system for replacing pedal data in a playing file. The method comprises: obtaining a playing file of a piece of music; obtaining a score file corresponding to the piece of music; generating an insertion node according to the score file and a pedal insertion rule, and / or according to the playing file, wherein the pedal insertion rule comprises a chord rule; selecting replacement data of a pedal in response to a selection signal of a user, wherein the selection signal comprises a specified style or a specified pedal file; and inserting the replacement data into the insertion node to form a new playing file. The present application can meet the demand of users who want to reference pedal data of others by replacing pedal data, and greatly improves the efficiency of music production, teaching assistance, performance analysis and the like.

The utility model belongs to 3D camera technical field discloses an integrated edge calculation function's intelligent 3D camera, including 3D camera module, embedded system and communication module, embedded system integrates CPU, GPU and NPU's processor, wherein CPU is responsible for scheduling, data acquisition and transmission, GPU is responsible for point cloud generation, NPU is responsible for edge calculation, through the collection of three -dimensional data inside the camera, point cloud generation and edge calculation, only the result transmission to external device after processing, significantly reduce data transmission and the processing burden of external device. The utility model compact structure, powerful, has provided efficient edge calculation solution for industrial field, can promote system efficiency and response speed, be applicable to the defect detection, size measurement, robot navigation etc. Variety of scene, have remarkable practical value and popularization prospect.

This application discloses a method, apparatus, and electronic device for fine-tuning a large model based on hybrid experts, belonging to the field of artificial intelligence technology. It addresses the problem that current large model technologies struggle to meet the application needs of multi-task scenarios in network management. The method includes: initializing a hybrid expert network for a pre-trained large model, the hybrid expert network comprising a task-level gating network and multiple task-level expert groups (each group containing a character-level gating network and multiple character-level experts), the hybrid expert network being embedded in specific layers of the pre-trained large model; inputting training data and a first prompt word into the pre-trained large model, guiding the pre-trained large model to output sample prediction results through the first prompt word; determining the loss result of the pre-trained large model based on the true label results corresponding to the training data, the sample prediction results, and the target loss function; and fine-tuning the network parameters of specific layers of the pre-trained large model based on the loss result to obtain a network management model for multi-task scenarios.

This invention relates to a training method, system, and readable storage medium for streaming image semantic segmentation models, belonging to the field of image segmentation technology. The training method includes dividing a streaming dataset into multiple data subsets based on a streaming data partitioning strategy; training multiple image semantic segmentation models based on each data subset; wherein each data subset corresponds one-to-one with an image semantic segmentation model, and each image semantic segmentation model has a identifiable category used to identify the data category of the corresponding streaming data; integrating the multiple image semantic segmentation models into a final segmentation model based on the identifiable categories of the image semantic segmentation models and their dynamic voting weights; the final segmentation model identifies the data category of the input streaming data and performs semantic segmentation according to the dynamic voting weights of the image semantic segmentation models. This invention can improve the segmentation performance of streaming image semantic segmentation models using minimal storage and training resources.

The application discloses a battery cooling method and device based on an energy storage system, and is applied to a server of the energy storage system. The method comprises the following steps: acquiring the cooling demand and preset storage amount of each battery cluster in a plurality of battery clusters; determining a battery cluster with unmet cooling demand in the plurality of battery clusters as a target battery cluster; when it is detected that the storage amount of refrigerant in a liquid storage device of the target battery cluster is the preset storage amount of the target battery cluster and the cooling demand of the target battery cluster is unmet, performing at least one adjusting and detecting operation until the cooling demand of the target battery cluster is met. The refrigerant in the liquid storage device of the battery cluster with met cooling demand is called to enable the battery cluster with unmet cooling demand to be sufficiently cooled, and the refrigerant in the entire energy storage system does not need to be calculated and adjusted, so that the calculation pressure is reduced, and the cooling speed is accelerated.

This invention relates to the field of drone rescue technology, specifically a collaborative intelligent detection system and method for drone-based rescue. The system includes a detection module, a lightweight detection module, an unloading module, and a communication module. The method involves: the detection module capturing an image of the current area; the lightweight detection module, based on a lightweight detection model and the captured image, determining whether there is a trapped object in the current area, and obtaining a local detection result; the unloading module, based on an unloading model, determining the accuracy of the local detection result. If accurate, the local detection result is sent to the rescue command center via the communication module; otherwise, the current area image is sent to the rescue command center via the communication module for manual identification, and the unloading model is continuously updated based on the manual identification result and the local detection result. This addresses the technical problems of existing drone-based rescue systems, such as the high computational pressure on the drone side and the limited detection performance due to reliance on a single detection method.

This invention relates to the field of medical management system technology, specifically disclosing a prognostic management system for patients with autoimmune diseases. It adopts an edge-cloud collaborative architecture, comprising a multimodal edge data acquisition and preprocessing module, an edge-end real-time status monitoring module, a cloud-based progressive prognostic assessment module, an intervention intensity matching and adverse reaction early warning module, an intervention effect closed-loop correction and federated learning module, and a doctor-patient shared decision-making and data feedback module, all connected sequentially. This invention simultaneously collects multi-dimensional patient data, achieving a comprehensive understanding of the patient's condition. Simultaneously, it performs preliminary data quality control and real-time status monitoring at the edge, reducing the computational burden on the cloud and enabling timely identification of sudden abnormalities in the patient's condition and triggering local early warnings. By calculating the effective contribution coefficients of each modality of data, the impact of different data on prognosis can be dynamically assessed, improving the effectiveness of data utilization.

The application discloses a multi-layer multi-scale grid and a dynamic auxiliary positioning method based on the same, and belongs to the field of wireless positioning. The method comprises the following steps: performing grid division on a target GNSS reference station network coverage area to obtain longitude difference dl, latitude difference db and height difference dh of the target GNSS reference station network coverage area grid; determining a multi-layer multi-scale grid of the target GNSS reference station network coverage area; based on the multi-layer multi-scale grid, a data center receives rough position information sent by a user, searches for a grid point closest to the user as a positioning service grid, and sends information of a virtual observation station of the positioning service grid to the user, so that real-time positioning is completed. The application solves the centimeter-level positioning demand of the service end for a large number of users from the principle of VRS technology, overcomes the problems of low terminal RTK fixing rate and poor accuracy in a complex terrain area, reduces the calculation pressure of the service end, has simple algorithm and strong practicability, and effectively reduces the construction and operation and maintenance cost caused by simply relying on the accumulation of server and other hardware facilities.

This invention relates to the field of aircraft landing technology, and specifically to an aircraft landing assistance method and system. The method includes acquiring first information and second information, where the first information is the initial three-dimensional coordinates of the aircraft, and the second information is the three-dimensional coordinates of a hovering point, which is located directly above a preset area of ​​the landing platform; planning the aircraft's flight path based on the first and second information to obtain flight path information; acquiring first projection image information in real time during flight based on the flight path information, the first projection image information including a projection image of the aircraft onto the preset area of ​​the landing platform; and adjusting the flight path information based on the first projection image information to assist the aircraft landing. This invention determines the aircraft's attitude relative to the landing platform based on the continuously changing first projection image, thereby planning the aircraft's flight path during the gradual landing phase and ensuring that the aircraft maintains the correct landing attitude during the hovering phase.

The application discloses a target user screening method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining front-end behavior data and back-end storage data of a candidate user; screening the front-end behavior data and the back-end storage data according to candidate influencing factors to obtain target behavior data and target storage data; determining a comprehensive influence degree according to the target behavior data and the target storage data; and judging whether the candidate user is a target user according to the comprehensive influence degree. The technical scheme of the application improves the data operation efficiency, reduces the operation pressure of the operation equipment, avoids the error caused by determining the influence degree only according to the target behavior data or only according to the target storage data, improves the accuracy of the final operation result, improves the accuracy of selecting the target user, avoids the influence on non-target users in subsequent marketing, and reduces the marketing cost.