99 results about "Core set" patented technology

The invention belongs to the technical field of artificial intelligence and information retrieval, and particularly relates to a group-level core set selection method for a large model recommendation system. The method comprises the following steps: defining a core set selection task, and taking test loss after minimizing subset fine tuning as an optimization target; the method comprises the following steps: constructing an agent optimization target: based on an optimal transmission theory and gradient norm analysis, considering the distribution difference between a candidate subset and a verification set, and constructing an upper bound of agent test loss; initialization-re-refining calculation: by introducing a special cost matrix, converting an original problem into a p-median problem, and optimizing by using a greedy and sample exchange strategy; and label enhancement: according to a joint distribution category decomposition principle, further improving the category coverage capability and the performance stability of the core set in a label recommendation scene. According to the method, the data scale and computing resource consumption required by fine tuning can be remarkably compressed while the recommendation performance is kept, and key support is provided for efficient deployment of a large language model in a recommendation system.

The invention discloses an EPC full-process technology management method, and the method comprises the following steps: S1, taking a BIM model as a core, integrating geometric data, cost data, progress data and operation and maintenance data, and forming a digital twinborn model; s2, structuring the national standard, the industrial standard and the enterprise construction method into executable rules, and embedding the executable rules into the digital twin model to form a construction specification knowledge graph; s3, collecting construction site data in real time through an IoT sensor network, fusing the construction site data into the digital twinborn model, and driving the digital twinborn model to dynamically update; s4, performing progress prediction, resource optimization and risk early warning through an artificial intelligence AI algorithm based on the dynamically updated digital twinborn model, and outputting a decision instruction; and S5, the acceptance records and quality data of the key processes are stored based on the block chain technology, so that whole-process quality tracing and closed-loop management are realized, and the problems of information isolated island, progress lag, cost increase, quality tracing difficulty and the like in a traditional EPC project are effectively solved.

The invention discloses a dynamic weight-based zero-value adaptive zero-carbon power supply station evaluation method and system, and the method comprises the steps: firstly constructing a multi-dimensional index framework system, and collecting historical data to construct an index core set; dividing two types of data sets, and calculating the subjective weight and reliability of each index; calculating zero-value structure parameters and separating non-zero samples according to the two types of data sets to obtain PCA basic weights, calculating double-cluster fusion entropy and credibility and calibrating objective weights in combination with traditional entropy and missing rate penalty factors, calculating dynamic fusion coefficients and fusing subjective and objective weights based on subjective reliability to obtain final weights, and finally obtaining the final weights of the double-cluster fusion entropies and the credibility of the double-cluster fusion entropies and the credibility of the double-cluster fusion entropies and the credibility of the double-cluster fusion. And performing weighted summation to obtain an index score, and evaluating the power supply station according to the index score. According to the method, the problem of weight distortion caused by zero value interference in a traditional evaluation method is effectively solved through targeted distinguishing processing on zero values, a dynamic adjustment mechanism based on index characteristics is constructed, accurate adaptation of subjective and objective weights is achieved, and the accuracy and robustness of an evaluation result are improved.

The invention provides a task migration method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-migrated task object from a processor core with a task migration demand; obtaining load information and core temperature information of each processor core in a processor core set to which the processor core with the task migration requirement belongs; according to the load information and the core temperature information, inter-core migration is carried out on the task object between the processor cores twice or more, and the range of the inter-core migration comprises the processor cores with task migration requirements. The performance stability of the processor core after receiving the task object is improved, the possibility that the performance of the processor core is abnormal due to the fact that the processor core receives the task object is reduced, the stability of the core temperature of each processor core is improved, and the core temperature control effect of each processor core is optimized.

In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a UE. The UE receives, at a time point, DCI scheduling two or more downlink data channels. The UE receives, within a threshold processing time from the time point, a first control signal in a first CORESET according to a first TCI state. The threshold processing time is allocated for the UE to decode the downlink control information. The UE receives, subsequent to the first CORESET, data according to the first TCI state (a) until an end of the threshold processing time when a second CORESET in which the UE is configured to receive a second control signal does not exist in the threshold processing time or (b) until the second CORESET when the second CORESET exists in the threshold processing time.

To provide a prismatic cell that can at least improve the lithium deposition phenomenon. [Solution] A rectangular cell is provided, comprising a housing and two core sets housed within the housing. Each core set comprises at least two cores stacked along a first direction, the outer circumferential surface of each core along the winding direction comprises two planar regions and a first corner region and a second corner region connected to the opposing ends of the two planar regions, respectively, the core adjacent to the housing along the first direction in the core set being the first core, the core adjacent to another core set being the second core, each core set further comprising a first insulating strip, the first insulating strip covering at least a portion of the first corner region of the second core, and one end of the first insulating strip extending through the first corner region of the first core to the first planar region.

The application discloses a hybrid scheduling system of a FaaS platform based on KVM virtualization, which is based on a lightweight user mode scheduling mechanism, and realizes task scheduling and dynamic load balancing through the cooperative work of four core modules, i.e., a pre-execution processor, a task detector, a task distributor and a load balancer. The pre-execution processor analyzes the hybrid execution time of different task types under different scheduling methods, and provides data support for scheduling decisions; the task detector monitors the submitted tasks in the system in real time and judges the task types; the task distributor makes a distribution decision in combination with pre-processing information, task characteristics and real-time load proportion; and the load balancer ensures the load balancing between scheduling sets through real-time load monitoring, and avoids the overload of single-core sets. The application can reduce the average execution time of tasks of the FaaS platform in a high-concurrency scenario, improve the resource utilization rate and task execution efficiency, and provides an efficient and reliable solution for serverless computing task scheduling.

A laminated core set for a rotor, having at least one first laminated core and at least one second laminated core, each having internal toothing for fastening to a rotor shaft and forming a magnet carrier. The magnet carriers have recesses for receiving magnets. A circumferential orientation is a relative position between the recesses and the internal toothing of a laminated core and the circumferential orientation of the first laminated core is different from the circumferential orientation of the second laminated core. A rotor for an electric machine is provided having such a laminated core set and a rotor shaft to which the laminated core set is attached such that the recesses of axially adjacent laminated cores are arranged rotated by a predetermined angular offset.

The utility model discloses a kind of automatic core-dropping machines for box molding line, including shell, its inside is provided with integrated suction cup assembly, the integrated suction cup assembly includes sealing plate, the sealing plate is arranged in the inside of shell, the bottom of the sealing plate is fixedly connected with several groups of suction cups, positioning block is fixedly connected on the side wall of one side of sealing plate, integrated suction cup assembly is formed modular assembly structure with shell by sealing plate, cooperate the quick locking design of locking assembly and positioning block, without the aid of tool, the positioning and fixation of integrated suction cup assembly can be completed, when different specifications of suction disc need to be replaced to adapt to different sand core, only need to be removed the constraint of positioning block by locking assembly and positioning rod, integrated suction cup assembly of old can be quickly taken down and new component is installed, greatly simplify replacement operation process, effectively shorten equipment downtime, significantly improve the continuous operation efficiency of production line.

The invention discloses a method and device for cross-edge federated domain incremental learning, a medium and equipment, and the method comprises the steps: screening out a core sample set from first old domain data through employing a core set playback algorithm based on a K center heuristic mode; balancing the learning of the new task knowledge and the retention proportion of the core sample set by adopting a mixed strategy of elastic weight consolidation and progressive knowledge distillation to obtain new domain data and second old domain data after feature balance; based on a cross-domain feature alignment algorithm of maximum mean value difference, minimizing the distribution difference of the new domain data and the second old domain data in the feature space to obtain new domain representation with consistent features; and calculating a model update quantity difference value based on the new domain representation with consistent features and the data of the static equipment in the new edge environment, and performing dynamic weighted aggregation on the new domain representation with consistent features based on the model update quantity difference value to obtain a cross-edge federated domain incremental learning model. According to the method, the problem that old knowledge is forgotten due to the fact that cross-edge equipment enters a new edge system to participate in federal training is solved.

The application provides a core set calculation method for a graph structure, relates to the field of graph structure, and constructs a citation network graph and generates an adjacency vector of each node, calculates a DOPH signature of each adjacency vector, and then performs clustering division based on the DOPH signature, calculates by using a GA error, and accelerates by using a clustering-based method, and meanwhile, the application combines a reverse reachable set of the node, selects the node to form a core set, so that the application constructs the core set capable of representing the information of the whole graph structure based on the propagation characteristics, local structure similarity and global role information of the nodes in the graph. Further, the framework introduces a graph adaptive sampling strategy and an adjustable covering mechanism, can dynamically balance the calculation efficiency and the representation accuracy according to the task requirement, and thus realizes the automatic balance between the effect and the cost.

The invention relates to a multi-core CPU load balancing scheduling method based on dynamic queue migration and electronic equipment, and the method mainly comprises the following steps: firstly, initializing a physical core set, establishing a corresponding virtual machine identification task queue for each physical core, and sorting according to a core number; when a vCPU allocation request of a virtual machine is received, the queue length of each physical core is calculated, and a virtual machine identifier is inserted into a corresponding physical core queue according to a shortest queue priority principle; counting the queue lengths of all physical cores, and calculating the longest queue length and the shortest queue length; judging whether load unevenness (no idle physical core and inconsistent queue length) exists or not, if so, executing differentiated queue rebalance according to length difference, and migrating tasks in a long queue to a short queue; and finally, updating the binding relationship between the vCPU and the physical core to ensure that the load balancing takes effect. Compared with the prior art, the method has the advantages that the computing resources of the virtual machine are distributed fairly, and the physical core utilization rate and the overall system throughput are improved.

This invention discloses an automatic modulation recognition core set selection method based on Forgot Quality Score (FoQuS), belonging to the interdisciplinary field of wireless communication signal processing and deep learning. Addressing the shortcomings of existing methods in automatic modulation recognition tasks, such as neglecting the time-frequency structure and signal-to-noise ratio distribution of signals and using a single evaluation metric, this invention proposes a method that records the prediction trajectories of samples during multiple training rounds, calculates the number of changes in fusion correctness, the number of rounds of persistent errors, and the ratio of accuracy to loss value using the Forgot Quality Score (FoQuS), and dynamically selects a core set based on this score in a hierarchical manner. Retraining the model using the core set significantly reduces the training data size while maintaining recognition performance, demonstrating strong generalization ability and high practical value.

The utility model relates to the technical field of cosmetics, in particular to a core-replaceable cosmetic glass bottle which comprises a rubber base, the upper end of the rubber base is movably connected with a cosmetic glass bottle body in a sleeved mode, and two finger grooves are formed in the outer surface of the cosmetic glass bottle body. The upper end of the cosmetic bottle glass bottle body is fixedly connected with a connecting assembly, and a replacement core set is movably clamped in the connecting assembly. According to the cosmetic glass bottle with the replaceable core, due to the arrangement of the replaceable core set and the connecting assembly, the replaceable core is very convenient to mount and dismount, a consumer can replace the replaceable core conveniently, time and energy are saved, the replaceable core body in the replaceable core set can be replaced independently, and after cosmetics in the replaceable core body are used up, the replaceable core body can be replaced independently. A consumer does not need to discard the whole glass bottle and only needs to purchase a new replacement core group for replacement, so that the waste of glass packaging is greatly reduced, and the resource consumption and the environmental pollution are reduced.

The application provides a spin lock deadlock detection method of a multi-core operating system, and the method comprises the following steps: acquiring an operating system processor core set, and sequentially searching variables of each processor core; removing processor cores without spin lock information to be acquired in the variables to form a to-be-detected core set; using a bitmap dyeing method to cyclically search whether a processor core running a detection program in the to-be-detected core set acquires a spin lock, if yes, a deadlock occurs, if not, the processor core is removed, and other processor cores are sequentially detected until the to-be-detected core set is empty, the multi-core operating system does not have a deadlock, and the detection ends. The method designed by the application has the advantages of high efficiency, accuracy, simplicity and convenience, can detect a deadlock problem as early as possible and timely feedback, and enables a user to take corresponding deadlock release measures according to a feedback result, so that the system can continue to run.

The present invention relates to downlink assignment for a downlink control channel. Disclosed are an apparatus, method, and system for downlink assignment of a downlink control channel. A method includes: receiving at least two downlink control channel candidates, which carry the same downlink control information (DCI) and correspond to a transport block (TB); in response to receiving the at least two downlink control channel candidates, determining an associated core set for reception of the TB; based on the associated core set, determining a physical uplink control channel (PUCCH) resource for the TB; and sending a hybrid automatic repeat request response (HARQ-ACK) corresponding to the TB on the determined PUCCH resource.

The utility model discloses a manual core setting clamp which comprises a movable part, a fixed part, a limiting part, a wrench, a limiting rubber sleeve and a connecting rod, the movable part, the fixed part and the connecting rod form a frame structure with four vertical rods, and a transverse rod of the movable part penetrates through a sleeve, so that the movable part can rotate along the axis of the sleeve relative to the connecting rod. The other end of the connecting rod is connected with the center of the transverse rod of the fixing piece in a welded mode, the limiting piece is connected to the lower portion of the outer side of the sleeve in a parallel welded mode, the end of the wrench is provided with a bending section in the same direction, the middle section of the wrench is long-strip-shaped, the end of the wrench is fixed to the transverse rod of the movable rod, and the middle section of the wrench is located below the connecting rod. When automation equipment breaks down, an operator can use the manual core setting clamp to carry out core setting operation, long-time shutdown of a production line is avoided, and production continuity is ensured; an operator can quickly and accurately complete core setting operation, so that the production efficiency is improved, and the operation safety is improved.

In at least one embodiment, processing can include: partitioning a first set of CPU cores into a plurality of CPU core subsets each associated with a single corresponding one of a plurality of predefined I / O types; classifying each of a plurality of I / O requests as one of the plurality of predefined I / O types; for each of the plurality of I / O requests, selecting a CPU core from a first CPU core subset of the plurality of CPU core subsets based, at least in part, on the first CPU core subset having a corresponding one of the plurality of predefined I / O types that matches an associated one of the plurality of predefined I / O types of said each I / O request; and processing the plurality of I / O requests on their selected CPU cores.

The invention belongs to the technical field of defect detection, and provides a zero-sample visual defect rapid detection method based on a core set strategy, which comprises the steps of image acquisition and preprocessing, multi-scale feature extraction, initial core set construction, core set expansion and screening, and similarity scoring. According to the method, the small-scale core set is introduced into the zero sample scene, so that the time performance of the algorithm in the actual working scene is improved, and the real-time performance is guaranteed; an initial core set is obtained through a sparse downsampling method, feature distribution information can be represented more accurately and fully, and it is ensured that core set features obtained from the interior of test data can be closer to overall real distribution of the test data; the general distribution rule of the defect features in the test data is extracted, and whether the data defects exist or not is evaluated according to the general distribution rule, so that the dependence of a conventional zero sample method on external source data information is avoided, and the generalization and robustness of the method are effectively improved.

The present disclosure provides a data screening method, device, equipment and medium, relates to the field of data processing, in particular to the fields of big data, intelligent search and artificial intelligence. The specific implementation scheme is: determining a data screening mode according to the target quantity, the target data set and the processor core set; assigning the target data set to a processor core in the processor core set according to the data screening mode; using each processor core, sequentially selecting a to-be-compared data set according to the assigned data, and sequentially performing a comparison operation on each to-be-compared data set using a single instruction multiple data instruction to obtain a comparison result of each to-be-compared data set; and using each processor core, determining a screening result of data in each screening range according to the comparison result of each to-be-compared data set. The embodiment of the present disclosure can adapt to a single instruction multiple data instruction to improve the data screening efficiency.

The embodiment of the application discloses a control method, comprising: monitoring the load of a processor core set of an electronic device, the processor core set comprising at least one processor core; and adjusting the configuration information of the processor core set based on at least the load; wherein the processing capacity of different processor core sets is the same or different. The embodiment of the application also discloses a control device.

The invention relates to QOS and isolation for a multi-chip GPU. One embodiment provides a graphics processor comprising a system interface and a plurality of core particles coupled with the system interface. Each of the plurality of cores may be configured to be assigned to a partition of the plurality of partitions. A core grain of the plurality of core grains includes an interface to a memory device, a cache memory coupled to the interface to the memory device, and a graphics core cluster coupled to the interface to the memory device and the cache memory, the graphics core cluster including a plurality of graphics cores configured to execute graphics and compute a workload.

The invention provides a graph structure-oriented core set calculation method, and relates to the field of graph structures, and the method comprises the steps: constructing a citation network graph, generating an adjacent vector of each node, calculating a DOPH signature of each adjacent vector, carrying out the clustering division based on the DOPH signatures, carrying out the calculation through a GA error, and carrying out the acceleration through a clustering-based method. And meanwhile, a core set is formed by combining a reverse reachable set of the nodes and the selected nodes, so that the core set capable of representing total graph structure information is constructed on the basis of propagation characteristics, local structure similarity and global role information of the nodes in the graph. Furthermore, a graph self-adaptive sampling strategy and an adjustable coverage mechanism are introduced into the framework, the calculation efficiency and the representation precision can be dynamically balanced according to task requirements, and therefore automatic balance between the effect and the cost is achieved.

The invention relates to the technical field of sand core casting, and discloses a core setting clamp with a pre-core-assembling mechanism, the core setting clamp comprises a core assembling mould main body, two sides of the top end of the core assembling mould main body are sequentially connected with a fixed side core assembling device and a movable side core assembling device in a staggered manner, and the top ends of the fixed side core assembling device and the movable side core assembling device are provided with positioning components in a staggered manner; two positioning components are arranged on the core assembly mould main body, a sand core mould is placed on each of the two positioning components, a matching component is arranged at the joint of the two sand core moulds, vertical mould height direction positioning devices are fixedly connected to the periphery of the core assembly mould main body, clamping arms are arranged at the tops of the mould height direction positioning devices, and mould horizontal direction positioning devices are symmetrically and fixedly connected to the two sides of the middle of the core assembly mould main body. Through the cooperation of the fixed side core assembly device and the movable side core assembly device and in combination with sand core positioning, the guide plate, movable side positioning and the like, it is ensured that two sand core molds are accurately aligned in the combination process, and deviation caused by manual operation or multiple times of transfer is avoided.

A method for wireless communication at a user equipment (UE) and related apparatus are provided. In the method, the UE receives a physical downlink control channel (PDCCH) transmission in a control resource set (CORESET) spanning multiple symbols from a network entity. The PDCCH transmission includes multiple demodulation reference signals (DMRS) and has a DMRS pattern based on the duration of the CORESET. The DMRS pattern is in at least one of the time domain or the frequency domain. The UE further performs a channel estimation based on the DMRS.

The invention relates to configurable architecture bandwidth throttling of workloads for GPU virtualization. One embodiment provides a graphics processor comprising: a memory interface; the graphic core cluster comprises a plurality of graphic cores; and an interconnection architecture for interconnecting a plurality of hardware clients including the plurality of graphics cores. The interconnect architecture includes a plurality of architecture ports coupled with the plurality of graphics cores. The architecture port is configured to limit bandwidth available for an associated graphics core via a bandwidth throttler circuit coupled with the architecture port.