31 results about "Sorting network" patented technology

The application discloses a kind of parameter agile radar signal intelligent sorting methods, first, original radar signal is detected, and pulse description word sequence is obtained, the pulse description word sequence obtained is preprocessed, then feature extraction module based on multi-branch hollow convolution, feature fusion module based on attention mechanism, radiation source mapping module based on transpose convolution are cascaded, and intelligent deep sorting network is constructed, then the sequence after pre-processing is used as the input of intelligent deep sorting network, and the intelligent deep sorting network is trained, finally, the parameter agile radar signal is sorted using the intelligent deep sorting network after training is completed.The method of the application can realize the accurate sorting of parameter agile radar, effectively solve the "batch" problem, has the advantages of flexible, accurate and strong generalization ability, can adapt to parameter overlap, noise and pulse loss and other complex situations.

The invention discloses a data processing device, a data processing method, a chip and electronic equipment, and relates to the technical field of data processing. The data processing apparatus includes: a storage module configured to store data; the calculation module is coupled to the storage module and is configured to access an original data vector stored in the storage module, and the original data vector comprises m data elements; splitting the original data vector based on the target k value to obtain a plurality of first data vectors; performing odd-even merging sorting on the data elements in the first data vectors to obtain a plurality of first ordered data vectors; and merging and sorting the data elements in the plurality of first ordered data vectors to obtain top-k data elements in the m data elements. According to the data processing device, the data processing method, the chip and the electronic equipment provided by the invention, the top-k data elements can be obtained without a special hardware sorting network.

The invention discloses a data sorting device and method, a chip, electronic equipment and a storage medium, and the device comprises a controller which is used for obtaining a plurality of first data groups; a parity sorting network for sorting the first data set into a second data set; the data selector is used for acquiring a target data group; the controller is used for comparing the target data set with the ith second data set at an interval of N bits to obtain an (i-1) th third data set; when the TopN is sorted, the double-adjustment merging network is used for sorting the (i-1) th third data group into the (i-1) th fourth data group; when i is equal to the number of the plurality of first data groups, taking the (i-1) th fourth data group as a TopN sorting result; and during full sorting, the double-adjustment merging network is used for carrying out iterative merging on the sorted fourth data group to obtain a full sorting result. The method can be compatible with TopN and a dual-tone full-sorting algorithm, and saves computing resources.

Techniques for filter and sort versions of software instances executing on computing devices in a network are disclosed. The system receives an instruction to execute an operation on software instances that satisfy numerical criterion and non-numerical criterion. A standardizing function is applied to the numerical criterion to determine a standardized numerical criterion. The system accesses version number values corresponding to software instances on the computing devices in the network. By applying the standardizing function to numerical version numbers of the version number values, the system determines standardized numerical version numbers for the version number values. The system filters the standardized numerical version numbers based on the standardized numerical criterion. The system identifies software instances with (a) associated standardized numerical version numbers that meet the standardized numerical criterion and (b) non-numerical components that meet the non-numerical criterion. The system executes the operation on the software instances that meet the criteria.

System, comprehensive: a plurality of processor clusters, wherein a given processor cluster comprises one or more processors; a large number of graphics processing units; a variety of storage controllers configured to control access to storage devices; a multitude of agents; and a multitude of network switches coupled to the multitude of processor clusters, the multitude of graphics processing units, the multitude of memory controllers, and the multitude of agents, wherein: a first subset of the multitude of network switches is interconnected to form a network of a central processing unit (CPU) between the multitude of processor clusters and the multitude of memory controllers, a second subset of the multitude of network switches is interconnected to form an input / output (I / O) network between the multitude of processor clusters, the multitude of agents, and the multitude of memory controllers, a third subset of the multitude of network switches is interconnected to form a loosely sorted network between the multitude of graphics processing units, selected agents of the multitude of agents, and the multitude of memory controllers, The CPU network, the I / O network, and the loosely sorted network are independent of each other. the CPU network and the I / O network are coherent and The network with loosened sorting is incoherent and has reduced sorting constraints compared to the CPU network and the I / O network.

This invention discloses a multi-agent collaborative decision-making method for ramp merging based on spatiotemporal interaction capture and action priority, belonging to the field of intelligent transportation technology. The method includes: acquiring a sequence of observation information from multiple agents and obtaining a spatiotemporal interaction code through temporal encoding and self-attention interaction encoding; gating the spatiotemporal interaction code based on ramp merging features (TTMP); inputting the enhanced code into a policy priority ranking network, sampling the action generation order using Plackett-Luce, and then reordering the enhanced code, before inputting it into a decoding policy network with cross-attention to form a spatiotemporal interactive Plackett-Luce multi-agent reinforcement learning model. The model then autoregressively generates actions for each agent according to the reordered order and integrates them to form a joint action, generating vehicle control commands to control vehicles to perform collaborative driving in the ramp merging area. This invention can dynamically model the multi-vehicle interaction relationship and the action priority dependency between individual decisions in a strong interaction scenario of ramp merging, thereby improving the stability of collaborative decision-making and traffic efficiency.

This application discloses a data processing apparatus, a data processing method, a chip, and an electronic device, relating to the field of data processing technology. The data processing apparatus includes: a storage module configured to store x sets of original data vectors, each original data vector containing m data elements, where x and m are positive integers; and a computation module including a single instruction multiple data (SIMD) execution unit and a vector register group, the SIMD execution unit being coupled to the vector register group, and the vector register group being coupled to the storage module. The computation module is configured to: determine whether x is an integer multiple of the SIMD processing capability, split x, and obtain the top-k data elements in the original data vectors based on different data strategies. The algorithm of this application is flexible, requires no dedicated hardware sorting network, avoids dependence on dedicated hardware, and improves programming flexibility and versatility, facilitating the expansion and migration of large models across different hardware platforms.

A quantum source coding method includes: initializing a quantum register having a plurality of nodes: loading a unary-coded message into the quantum register; loading an address state into an address register of each message node of the quantum register; sorting the message nodes based on a data register such that the message nodes form a message-sorted sequence; and applying, for each message node at an end of the message-sorted sequence, a CNOT gate to the address state of each of the register's message nodes and output nodes. The method also includes: unsorting the message nodes; sorting the nodes based on the address register such that the nodes form a fully-sorted sequence; applying, for each pair of adjacent nodes in the fully-sorted sequence having the same address state, a CNOT gate to the data registers of each pair; and unsorting the nodes to return the fully-sorted sequence to the initial sequence.

The invention discloses an off-line reinforcement learning strategy optimization method and system based on empirical quantile sorting, and aims to solve the problems that in a traditional method, strategy optimization greatly depends on an absolute value of a Q value, and training is unstable. According to the method, a ranking function is introduced to replace a Q function to serve as a strategy supervision signal, target Q values are ranked through an empirical cumulative distribution function (ECDF), normalized quantile labels are generated, and relative advantages of actions are described. By constructing a sorting network and minimizing the mean square error between the output of the sorting network and a sorting label, the sorting supervised learning of the action quality is realized. In the strategy updating stage, the strategy is dynamically optimized by combining the sorting score and the behavior cloning loss, and the strategy offset problem is relieved. The method focuses on the relative ranking relation of the Q values rather than absolute values, improves the training robustness and generalization ability, is excellent in performance in multiple offline tasks, and has good engineering application prospects.

The invention discloses a real-time task arbitration method of a heterogeneous OS cluster and related equipment, and relates to the technical field of computers, the method comprises the following steps: collecting a resource request signal, task priority data, a global timestamp and a resource identifier of a multi-core processor through a hardware interface; performing standardized mapping on task priority data, and dynamically calculating an effective priority based on waiting time; aiming at concurrent resource request signals of resources of the same resource identifier, arranging the resource request signals in a descending order according to effective priorities through a hardware sorting network, and performing timestamp defeat on the highest priority group by adopting a global timestamp; sending a resource authorization signal to the winning core and configuring a bus route; and dynamically adjusting a priority weighting parameter according to the historical arbitration data. According to the method, various data are collected through a hardware interface, then calculation is effective, then the global timestamp is adopted to carry out decision arbitration, and a priority hardware-assisted cross-OS real-time arbitration scheme can be realized.

The invention relates to the technical field of supply chain management, in particular to a supply chain sorting line optimization method and system based on artificial intelligence, and the method comprises the steps: obtaining the logistics demand information of each piece of goods, and generating a theoretical sorting network corresponding to each piece of goods on a supply chain map through a line analysis model, according to the theoretical sorting network on the supply chain map, expected popularity features are generated for all the sorting sites, sorting line selection is conducted on the theoretical sorting network of all the cargoes based on the expected popularity features of all the sorting sites, and theoretical sorting lines are generated for all the cargoes.

Embodiments rank entity importance in monitored networks by analyzing network traffic to collect metrics representing relationships between entities. Network monitoring engines construct network graphs where nodes represent entities and edges represent relationships based on collected metrics. The system employs graph clustering algorithms to partition entities into logical clusters based on interaction patterns. Within each cluster, entities may be ranked by topological importance using metrics to identify primary entities that represent their clusters. Monitoring resources may be allocated preferentially to primary entities from each cluster. The topology-based ranking approach distributes monitoring resources throughout the network.

The invention provides a Top-K acceleration device and method based on RISC-V vector extension. The method comprises the following steps: generating configuration information in a configuration information lookup table through a software algorithm; the method comprises the following steps: in a hardware process, receiving a VTOPK instruction and decoding the VTOPK instruction so as to parse an operation parameter; according to the analyzed operation parameters, corresponding gating configuration information is loaded from the configuration information lookup table; according to the loaded gating configuration information, dynamically activating a comparison and exchange unit in the full-function double-modulation sequencing network through a gating clock technology; reading input vector data from the vector register file; performing anti-disruption processing and sequence processing on the input vector data; inputting the processed input vector data into the activated sorting network to carry out Top-K selection operation; and writing the result of the Top-K selection operation back to the vector register file so as to solve the problem that the Top-K selection algorithm cannot consider performance, flexibility and universality at the same time.

The invention discloses a real estate data processing method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a real estate right certificate image into a real estate right certificate recognition model, carrying out the semantic segmentation of the real estate right certificate image in a semantic segmentation network, and obtaining a plurality of image regions, geometric information and semantic tags; extracting text blocks in the image area in the text block sorting network, sorting the text blocks according to geometric information to obtain a text block sequence, extracting text contents from the text blocks in the text block sequence in the text recognition network, filling the text contents and semantic tags into a structured data template to obtain structured real estate data, and storing the structured real estate data in the text recognition network. According to the method, the structured real estate data is encrypted and then stored in the database, so that the structured real estate data is obtained by extracting the text content from the real estate certificate through the real estate certificate identification model and filling the text content into the structured data template, manual input is not needed, and the input efficiency and accuracy of the real estate data are improved.

The invention discloses a deep learning-based rice hull separation method, which comprises the following steps of performing multi-angle image acquisition and preprocessing on rice batches to obtain standardized image data; the images are input into a dynamic feature reconfigurable sorting network for automatic identification and feature extraction, and particle space and attribute features are obtained; inputting the feature representation into a dynamic graph convolutional neural network containing a dynamic gating multi-head decision inference layer for sorting inference, and outputting a sorting decision result; performing automatic re-judgment or rejection judgment on a low-confidence result; and automatically generating process parameters based on the final decision, and issuing the process parameters to sorting equipment to complete rice hull separation operation. The full-process intelligent self-adaptive separation of rice husks can be realized, and the separation precision, reliability and automation level are improved.

The present application proposes a general multi-bit parallel list decoding method for polar codes, comprising: obtaining a polar code to be decoded and dividing it into M bit groups; sequentially placing the M bit groups into a decoder for decoding to obtain a decoding result, including: performing parallel metric calculation on the currently placed M bit group to obtain 2 M L path metrics; construct a master-slave sorting network for the decoder; exchange the path metric values ​​selected from the master-slave sorting network to obtain L path metric values; use the M-bit values ​​corresponding to the obtained L paths as the decoding decision for that path, and then as the decoding result for the current M-bit group; obtain the decoding results for all M-bit groups, and then use the smallest path among the L smallest paths in the decoding results of all M-bit groups as the final decoding path, and the sequence of all M-bit values ​​corresponding to this path as the decoding result of the polar code. The present invention, which adopts the above scheme, solves the technical problems of complexity and performance in list sorting for polar code decoding.

The application discloses a face acne detection method based on sampling effectiveness of enhanced sorting precision, which is applied to the technical field of computer vision and image processing, and aims at the problem of low detection precision of existing face acne detection technology. The artificial neural network of the application uses a multilevel convolutional neural network to perform feature extraction on an input image, and obtains a feature map F of the input; features are extracted from the feature map F again according to a foreground candidate frame obtained through preliminary regression, instance segmentation, classification and regression are performed, and an instance segmentation result M, a classification score P and a frame regression result B are obtained; features are extracted from the detection frame after final regression again, a sorting score T of the frame regression result B is learned, sampling is performed by an instance sampler and a background sampler to obtain training samples, and then the sorting network is used to train the sorting score, the classification score P is fused, and a final score S is obtained; and the face acne detection can be effectively performed by using the method.

The invention discloses a radar signal intelligent sorting method based on a semantic segmentation network, and the method comprises the steps: firstly detecting and receiving an original radar signal, obtaining a pulse description word sequence, carrying out the preprocessing of the arrival time, the center frequency and the pulse width in the pulse description word sequence, and carrying out the mapping of a dual-channel image, then constructing a radar signal intelligent sorting network based on a UNet semantic segmentation network and a multi-scale attention mechanism, then taking an image obtained through mapping processing as the input of the intelligent sorting network, carrying out reflection mapping on a segmentation result output by the network to obtain a radar signal sorting result, and training the constructed intelligent sorting network to obtain a radar signal sorting result; and finally, the radar signals are sorted by using the trained model. According to the method, accurate sorting of the parameter agile radar signals in the feature overlapping environment can be achieved, the problems of batch increasing and batch missing are effectively solved, and the method has the advantages of being flexible, accurate and high in generalization ability and can adapt to the complex conditions of parameter overlapping, noise, pulse loss and the like.

The application discloses a data sorting device and method based on a fixed structure sorting network, wherein the method comprises a cache unit, a multiple selection logic unit, a data exchange network and multiple sorting networks; the multiple selection logic unit is used for receiving multiple selection control information, selecting a data matrix output by the sorting network or a data matrix stored in the cache unit based on the multiple selection control information, and transmitting the selected data matrix to the data exchange network; the data exchange network is used for performing data exchange and data rearrangement on the data matrix based on exchange network control information; and the sorting network is used for calling a cut sorting function to alternately perform row sorting or column sorting on the data matrix to obtain a sorted data vector. The application can realize efficient sorting processing on different sizes of input data, and improves the universality, scalability and hardware resource utilization efficiency of the sorting network.

The application discloses an LTE terminal-based RRC link communication intelligent monitoring method and system, relates to the technical field of communication, and comprises the following steps: acquiring network communication parameter information, acquiring network load data according to the network communication parameter information, sorting network load data of the same kind according to time sequences based on time stamps corresponding to the data according to the network load data, and acquiring data time sequence information corresponding to each kind of network load data. The application accurately analyzes the fluctuation condition of network load data through a time sliding window, is convenient for subsequent monitoring of the network load condition, selects a suitable network load monitoring frequency through a network load feature set, realizes accurate monitoring of the network load, provides a data basis for setting of RRC timing time, acquires an RRC link monitoring frequency through RRC timing time information, and ensures the stability and reliability of the RRC link.

The invention relates to the technical field of decoding in communication, in particular to a sorting method and device, a decoder, communication equipment and a storage medium. The method is applied to a decoder, and comprises the following steps: determining a sub-path sequence corresponding to each main path according to the number M of information bits of parallel decoding and the number P of frozen bits in each decoding; p belongs to [0, M); the positive integer is a non-negative integer; determining a metric value of each sub-path in the sub-path sequence, and taking the metric value of each sub-path in the sub-path sequence as a to-be-sorted sequence; determining a sorting network according to the total amount of the metric values in the L to-be-sorted sequences, and sorting the metric values in the L to-be-sorted sequences by using the sorting network to obtain the minimum L metric values; wherein the sorting network comprises M-P sorting layers, and the sorting layers are used for sorting the measurement values and filtering half of data according to a descending order. By adopting the method provided by the invention, the time delay of metric value sorting in a multi-bit SCL decoding process can be reduced.

Systems and methods for automatic generation of highlights of video. The system includes a video processor to select one type of the video to be analyzed and split video clips from the video. The video processor recognizes positive clips, negative clips, and auxiliary clips. A spatio-temporal encoder is configured to select, from the recognized clips, a main positive clip, a main negative clip, and auxiliary positive and negative clips, and generate a three-dimensional (3D) embedding vector of each clip. The selected clips are processed by a ranking network having a self-attention layer. The self-attention layer, using a query head, a key head and the value head produces self-attention resultant vector on which an activation function is performed. A rank value is thus obtained for the selected clip. Based on the rank value, video highlights are generated.

The invention discloses a method for realizing any programmable electrical connection based on a minimum sorting network, and belongs to the technical field of electrical connection. According to the method, the problems of huge number of relays, complex system and high cost in a traditional full-connection matrix are solved by combining a minimum sorting network and a small number of relays. According to the specific scheme, the method comprises the following steps: sorting ports by using a minimum sorting network according to a connection requirement, so that the ports of the same connected group are adjacent; and arranging single-pole single-throw relays among the sorted port sequences, and realizing connection by controlling the states of the relays. According to the invention, the number of relays is significantly reduced, the complexity and energy consumption of the system are reduced, and the number of switching ports can be greatly increased. The method is suitable for testing equipment, a modularized electronic and electrical system, a power supply and distribution system, a programmable wire harness and other scenes requiring dynamic full exchange of ports.

The application discloses a data sorting device, method, chip, electronic equipment and storage medium. The device comprises a controller configured to acquire a plurality of first data groups; a parity sorting network configured to sort the first data groups into second data groups; a data selector configured to acquire a target data group; the controller is configured to compare the target data group with an i-th second data group at intervals of N bits to obtain an i-1-th third data group; when TopN sorting is performed, a double-adjusted merging network is configured to sort the i-1-th third data group into an i-1-th fourth data group; when i is equal to the number of the plurality of first data groups, the i-1-th fourth data group is taken as a TopN sorting result; when full sorting is performed, the double-adjusted merging network is configured to iteratively merge the sorted fourth data groups to obtain a full sorting result. The application can be compatible with TopN and double-adjusted full sorting algorithms and save computing resources.

A data ordering device includes a plurality of inputs N and a plurality of outputs M. There is a sorting network coupled between the plurality of inputs N and the plurality of outputs M. There are one or more latches comprising a buffer coupled between each input of the plurality of inputs N and a corresponding input of the sorting network. There are one or more latches comprising a buffer coupled between each output of the plurality of outputs M and a corresponding output of the sorting network. There is an input for a control signal operative to initiate a sorting of data between the plurality of inputs N and the plurality of outputs M. The data ordering device is coupled to a core of a central processing unit.

The present invention relates to a fresh produce recognition method based on temporal reordering. On the basis of the traditional fresh produce recognition method, a timestamp buffer is set and maintained during the training and inference process to record the correct category and timestamp of each sample in the past recognition sequence. In addition to image feature extraction, we additionally query the most recent appearance time and frequency of all categories from the timestamp buffer to obtain additional temporal features of all categories. We splice image features and temporal features, and re-predict the confidence of all categories through the temporal reordering network, so that the fresh produce recognition algorithm can learn the features of the changes between different codes of the same product, cope with the immediate changes in product codes in real applications, and effectively improve the recognition rate of the fresh produce recognition model.

The invention relates to an image restoration model training method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a sample image, and repairing the sample image through an image repairing model to obtain a repaired image; determining restoration loss based on the real image and the restoration image corresponding to the sample image; outputting a quality parameter for the repaired image through the target sorting network, and determining sorting loss according to the quality parameter; the target sorting network is obtained by training based on a plurality of reference images, the plurality of reference images are obtained by repairing the same original image according to different repairing modes, and quality parameters corresponding to the plurality of reference images are matched with a good-bad relationship between repairing effects corresponding to the plurality of reference images; and performing parameter adjustment on the image restoration model based on the restoration loss and the sorting loss to obtain a trained image restoration model. By adopting the method, the training effect of the image restoration model can be improved.

The invention provides a physical field reconstruction model fusion method, which belongs to the technical field of physical field reconstruction, and comprises the following steps: a low-precision reconstruction network extracts a low-precision physical field vector of working condition information, and a sequence generation network extracts sequence sequence information; a first encoder in the large-scale differentiable sequencing network processes a low-precision physical field vector to obtain precision vector information, and a second encoder processes sequential sequence information to obtain sequential vector information; the precision vector information and the sequence vector information are spliced to obtain hidden variable information, and the hidden variable information is decoded by a decoder to obtain a sequencing differential vector; and after processing by the high-precision physical field reconstruction model, obtaining high-precision physical field vector data. According to the method, the low-precision physical field vector and the sequential sequence information are processed based on the large-scale differentiable sorting network, sequence optimization of the input working condition information is achieved, physical field features can be conveniently extracted by a high-precision physical field reconstruction model, and the physical field reconstruction precision of the model is improved.

The application discloses a data processing device, a data processing method, a chip and an electronic equipment, and relates to the technical field of data processing. The data processing device comprises a storage module configured to store data; and a calculation module coupled to the storage module and configured to: access an original data vector stored by the storage module, wherein the original data vector comprises m data elements; split the original data vector based on a target k value to obtain a plurality of first data vectors; perform odd-even merge sort on data elements in each of the first data vectors to obtain a plurality of first ordered data vectors; and perform merge sort on data elements in the first ordered data vectors to obtain top-k data elements in the m data elements. The data processing device, the data processing method, the chip and the electronic equipment provided by the application can obtain the top-k data elements without a special hardware sorting network.

The present invention is a known radar signal sorting method based on the principle of gated recurrent networks. The scheme is as follows: signals are classified based on a known radar database to generate an original dataset; the original PDW stream data is processed to construct a joint feature vector; the processed joint feature vector is divided into a training sample set and a test sample set; a radar signal sorting network based on the principle of gated recurrent networks is constructed; the network is trained using the training sample set according to a set loss function and optimization method to obtain a trained sorting network; and the trained sorting network is tested using the test sample set. Using only PDW stream data, the present invention can effectively extract the timing characteristics of the pulses before and after the PDW stream, and can also obtain relatively accurate classification results in high pulse loss environments, with good pulse loss resistance.