14results about "Data selection" patented technology

The invention discloses a power system end-to-end unit combination method of an object number fusion driving space-time attention graph neural network. The method comprises the steps of obtaining operation data of a power system; constructing a space-time self-attention graph convolutional neural network, and constructing a unit commitment model based on the space-time self-attention graph convolutional neural network; operation data of a power system are input into a unit combination model for two-stage model training, and in the first stage, model parameter initialization is guided based on a physical mechanism, integer variable local relaxation and supervision pre-training fusion strategy; in the second stage, target guidance, physical mechanism constraint and integer variable local relaxation are adopted to realize secondary adjustment of model parameters; introducing an adaptive penalty term updating algorithm to obtain a trained unit commitment model; and realizing a unit commitment decision of the power system based on the trained unit commitment model. According to the method, time sequence and space constraints in the unit commitment problem can be effectively processed, and end-to-end unit commitment rapid decision is realized.

The present invention relates to a method for generating simulated sonar images. The method first improves the CycleGAN network, including segmenting the input and output images of the generator G and the generator F using the Otsu algorithm and the Unet network respectively, and fusing the segmentation results. Calculate the SSIM loss based on the fused images of the input and output of the forward generator G and the reverse generator F, and add it to the generator loss of the CycleGAN network. Then, use the simple sonar simulation images and real sonar images for training, and use the trained improved CycleGAN network to generate stylized simulated sonar images. Using the improved CycleGAN network to generate simulated sonar images can reduce the differences between the simulated images and the real images in terms of structure, edge features, etc., thus ensuring that the simulated sonar images are more similar to the real images.

The invention discloses an image processing method and device, electronic equipment and a storage medium. The method comprises the steps of displaying an editing interface of a to-be-printed image; in response to an image segmentation operation on the to-be-printed image, segmenting the to-be-printed image to obtain a plurality of first segmented images; in response to an image parameter adjustment instruction for each first segmented image, respectively obtaining a second segmented image corresponding to each first segmented image; and generating a three-dimensional model based on each second segmented image. A user can perform corresponding segmentation according to different requirements, and personalized image parameter adjustment is performed on each first segmented image, so that the three-dimensional model better meets the requirements of the user, and the use experience of the user is improved; the mutually independent image parameter adjustment can also improve the adjustment accuracy when different areas of the to-be-printed image are adjusted in 3D printing, and it is ensured that details in the generated three-dimensional model are richer.

This disclosure provides methods, devices, and systems for data management. The present implementations more specifically relate to a data orchestration system that can dynamically reconfigure a data processing pipeline based on telemetry received from various steps or data operations in the pipeline. For example, the telemetry may indicate a success, failure, time of entry, time of exit, or total duration of a given step or data flow in the processing pipeline. In some aspects, the data orchestration system may dynamically invoke new data flows based on the received telemetry. In some implementations, the new data flows may allocate additional memory and / or processing resources for the data processing pipeline. In some other implementations, the new data flows may deallocate memory and / or processing resources for the data processing pipeline. Still further, in some implementations, the new data flows may trigger an alert to a user or manager of the data processing pipeline.

This disclosure provides methods, devices, and systems for data management. The present implementations more specifically relate to a data orchestration system that can dynamically or programmatically produce a data processing pipeline. In some aspects, the data orchestration system of the present implementations may infer or otherwise determine the steps to be included in a data processing pipeline with little or no input from a user. In some implementations, the data orchestration system may select the steps based, at least in part, on a set of rules and policies defined by a user. The data orchestration system may further enable the user to modify the recommended data flows in the preconfigured data processing pipeline. In some aspects, the data orchestration system may aggregate data regarding usage, flow, and / or steps across multiple users to detect usage patterns, define repositories, and / or recommend data flows (such as by training a machine learning model).

The invention introduces a method for accessing randomized data, performed by a processing unit, includes: obtaining user data sets corresponding to one word line from a host side; calculating a randomization seed according to a page number of a specific page on the word line for each user data set; generating a randomized sequence by using a randomization algorithm according to each randomization seed; performing a logical bitwise XOR computation on each user data set and a corresponding randomized sequence to generate a first randomized data set; and programming each first randomized data set into a designated physical address including a corresponding page number on the word line in the flash module.

The system and method utilize a machine-readable garment identification tag (12) at a first station (78) to input information about a specific garment (10) into a computer system (80). Garment data from the garment identification tag (12) is assigned a garment identifier (44) and printed or formed on a hanger neck sleeve member. The hanger neck sleeve member (44) provides a consistent scan point across all subsequent classification stations (84) in the system (70). This eliminates the need to search for the location of the garment tag (12) for scanning at classification stations (84) following the initial station (78). Each hanger neck sleeve member (44) has a machine-readable code (46) assigned to the associated garment (10) and is positioned at the neck (30) of the hanger (16) for that garment (10). The position of the hanger neck sleeve member (44) on the neck portion (30) of the hanger (16) makes it significantly easier to access and read than the garment tag (12).

The application provides an implementation circuit, method and electronic equipment of an SM3 algorithm, wherein a plurality of carry-save adders for performing three-parameter addition operation and three-parameter XOR operation are arranged in the implementation circuit of the SM3 algorithm, so that the multi-parameter operation in the compression operation is completed through the carry-save adders, and therefore, various multi-logic operations such as the calculation of the intermediate variable FF and the calculation of TT1 can be realized through the carry-save adders, the repeated logic structure in the existing implementation circuit of the SM3 algorithm is saved, the number of registers required by the implementation circuit of the SM3 algorithm is reduced, and the circuit area of the implementation circuit of the SM3 algorithm is reduced.

The invention relates to a method for accessing randomized data, a computer readable storage medium and a device. The method comprises the following steps of: acquiring a plurality of groups of user data corresponding to a word line from a host end; for each group of user data, calculating a randomized seed according to a page number of a specific page in a word line to be written; using a randomization algorithm to generate a randomization sequence according to each randomization seed; performing logic exclusive-or operation on each group of user data and the corresponding randomized sequence to generate randomized data; and writing each randomized data into the specified physical address of the corresponding page number of the word line in the flash memory module. Through the dynamic calculation of the randomized seed according to the page number, the occupation of a rare non-volatile space for storing the randomized seed table can be avoided.

This invention discloses an end-to-end unit combination method for power systems driven by a spatiotemporal attention graph neural network based on physical data fusion. The method includes: acquiring power system operating data; constructing a spatiotemporal self-attention graph convolutional neural network (SINNN), and building a unit combination model based on the SINNN; inputting the power system operating data into the unit combination model for two-stage model training; the first stage guides model parameter initialization based on a fusion strategy of physical mechanisms, local relaxation of integer variables, and supervised pre-training; the second stage uses goal guidance, physical mechanism constraints, and local relaxation of integer variables to achieve secondary adjustment of model parameters; introducing an adaptive penalty term update algorithm to obtain the trained unit combination model; and realizing power system unit combination decisions based on the trained unit combination model. This invention can effectively handle the temporal and spatial constraints in the unit combination problem, achieving rapid end-to-end unit combination decisions.

The present invention relates to a location code generator and methods therefor. The location code generator is configured for receiving an input of types and subtypes of locations in a warehouse, as well as inputs of particular locations to be omitted, and automatically generates location codes for each of the locations. The location code generator further automatically generates checking codes that meet the requirements of avoiding repeatability conflicts, proximity conflicts, and predictability conflicts. The location code generator automatically associates generated checking codes with the generated location codes. The location code generator is further configured for generating printed stickers of the generated location codes and associated checking codes.

A system and method utilizes a machine readable garment identification tag (12) at a first station (78) to enter information on the specific garment (10) into a computer system (80). The garment data from the garment identification tag (12) is assigned to a garment identifier (44) which is printed or formed on a hanger neck sleeve member. The hanger neck sleeve member (44) provides a consistent scan point through all the subsequent sorting stations (84) in the system (70). This eliminates the need to search for the position of the garment tag (12) to scan in sort stations (84) subsequent to the initial station (78). Each hanger neck sleeve member (44) has a machine readable code (46) that is assigned to the associated garment (10) and is placed on the neck (30) of the hanger (16) for that garment (10). The position of the hanger neck sleeve member (44) on the neck (30) of the hanger (16) makes it readily accessible and readable, significantly more so than the garment tag (12) in these regards.

A multi-port memory device in communication with a controller includes a memory array for storing data provided by the controller, a first port coupled to the controller via a first controller channel, a second port coupled to the controller via a second controller channel, a processor, and a processor memory local to the processor, wherein the processor memory has stored thereon instructions that, when executed by the processor, cause the processor to: enable data transfer through the first port and / or the second port in response to a first control signal received from the first controller channel and / or a second control signal received from second controller channel, decode at least one of the received first and second control signals to identify a data operation to perform, the identified data operation including a read or write operation from or to the memory array, and execute the identified data operation.