16results about How to "Easy to code" patented technology

The invention relates to the technical field of nuclear power plant safety, in particular to a nuclear power plant fault diagnosis method based on data balancing, which establishes a data set balancing technology for deep learning through SA-TimeGAN, can effectively solve the problem of data imbalance caused by large normal data volume and small fault data volume in a nuclear power plant, and improves the fault diagnosis accuracy of the nuclear power plant. According to the method, firstly, small sample fault data are preprocessed, then, SA-TimeGAN is used for conducting adversarial training on the multiple types of small sample fault data, generated fault samples are added into an original training data set to achieve balance of sample data, and finally, the balanced data set is input into a CNN-BiLSTM diagnosis model for training, so that fault diagnosis is achieved. According to the method, the recognition capability of the model on minority classes of fault samples is effectively enhanced, and real data distribution is approached through adversarial training, so that high-quality synthetic data is generated.

The invention discloses an automatic ICD coding method and system based on hierarchical feature optimization and prediction correction, and relates to the technical field of natural language processing, and the method comprises the steps: inputting a current electronic medical record text into a pre-trained automatic ICD coding model for coding, and obtaining a corresponding ICD code; the automatic ICD coding model comprises a text representation module, a coding representation module, a synonym fusion attention module, an initial prediction module and a prediction correction module which are connected in sequence; the text representation module processes input medical record text features by using a cascade convolutional network, the synonym fusion attention module introduces synonym fusion attention to enable ICD coding synonym description and electronic medical record text deep semantic representation to interact, and the prediction correction module based on a mask auto-encoder is further introduced. According to the method, the initial prediction result can be optimized and reordered, and the coding combination which most accords with the semantic and dependency relationship is selected, so that the prediction accuracy is improved, the coding efficiency is improved, and the automatic ICD coding problem is solved.

This disclosure provides a cross-channel distributed video encoding and decoding method and system based on multidimensional attention, which can be applied to the field of video encoding and decoding technology. The method includes: acquiring a group of video images to be transmitted, the group of video images including a first key reference frame, a second key reference frame, and at least one intermediate video frame; encoding the first key reference frame and the second key reference frame into first encoded data and second encoded data, respectively; encoding each intermediate video frame into third encoded data based on a frame encoder; extracting multi-scale features from each third encoded data based on a multidimensional attention mechanism; processing the multi-scale features into fourth encoded data based on a multi-channel feature extraction mechanism; processing at least one fourth encoded data into a first bitstream; and converting the first encoded data and the second encoded data into a second bitstream, so as to transmit the video image group to the decoder via the first bitstream and the second bitstream.

The utility model relates to the technical field of coding, and discloses a coding device for a waxy corn processing line, which comprises a base, a support frame and a support column are fixedly arranged on the base, a box body is fixedly arranged at the top end of the support frame, a motor II is fixedly arranged at the top end of the box body, and a threaded rod is fixedly connected to the output end of the motor II. And the threaded rod is in threaded connection with a sliding block. According to the device, the air cylinder is started to drive the connecting rod on the fixing block to rotate, the connecting rod rotates sequentially through the first rotating shaft, the first gear, the second gear and the second rotating shaft, and then the first limiting plate and the second limiting plate are driven to rotate, so that the positions of the first baffle and the second baffle are changed, and the time of each packaging bag can be delayed through work of the first baffle and the second baffle; and meanwhile, a second motor is started to drive a sliding block to move up and down in a sliding groove through a threaded rod, so that the coding mechanism is driven to move, the coding mechanism rotates to a proper position for coding, and the coding position is kept fixed and unified.

An image encoding / decoding method, a bit stream transmission method, and a computer-readable recording medium for storing a bit stream are provided. An image decoding method according to the present disclosure is an image decoding method performed by an image decoding device, and may comprise the steps of: reconstructing a picture from a bitstream; and transforming the reconstructed picture based on one of the at least one candidate transformation, where the at least one candidate transformation corresponds to a rotational transformation or a symmetric transformation for the picture.

The utility model provides a kind of brake pad code spraying device, including workbench, rotatable disc is rotationally equipped on the workbench, coaxial lower fixed disc is fixedly equipped on the rotatable disc, coaxial rotating block is fixedly equipped on the lower fixed disc, the upper fixed disc of adjustable height is equipped on the rotating block, the driving part for driving rotatable disc to rotate is equipped on the workbench, arc plate for making brake pad adhere to upper fixed disc and lower fixed disc in vertical state is equipped on the workbench, vertical fixed link is equipped on the workbench, the code sprayer for being used to code spraying to brake pad is adjustably equipped on the fixed link. The device has the advantages of low cost, simple operation, strong practicability, etc.

The utility model relates to the technical field of sample classification, in particular to a food sampling inspection sample classification coding device which comprises a storage box, a plurality of ejection mechanisms are connected to the bottom of the inner wall of the storage box, vertical grooves and inserting grooves are formed in the two sides of the storage box, moving mechanisms are arranged in the two vertical grooves, and the moving mechanisms are arranged in the inserting grooves. A storage frame is connected between the two moving mechanisms, the multiple ejection mechanisms all extend into the storage frame, and locking mechanisms are arranged on the two moving mechanisms. A plurality of sampling tubes embedded in the storage frame can be easily ejected out from the corresponding transparent plates by a worker, so that the worker can conveniently take the collected sampling tubes and clearly know the serial number of each sampling tube, samples are classified, and meanwhile, the sampling efficiency is improved. And the convenience of taking out the plurality of sampling tubes is also improved.

The invention discloses a video coding method, a video coding device and a video player. The method comprises the following steps: acquiring target video data and target multi-dimensional perception data of a target object, wherein the target multi-dimensional perception data is information which is associated with the target video data and has a plurality of dimensional features and attributes; aligning the time sequence of the target multi-dimensional perception data with the time sequence of the target video data one by one to obtain reference multi-dimensional perception data; the time sequence of the reference multi-dimensional perception data is consistent with that of the target video data; and performing combined coding on the target video data and the reference multi-dimensional perception data to obtain coded video data. According to the embodiment of the invention, the problems of easy data loss and non-visual data viewing are solved, and subsequent efficient and rapid data analysis is realized.

The invention provides a multi-modal salient target detection method combining dynamic routing with multiple asymmetric windows, and belongs to the field of image processing. The method comprises the following steps: S1, processing visible light and thermal infrared image pairs by using two parallel neural network branches to form visible light and thermal infrared feature maps of each layer; s2, performing division by using windows with different sizes, and obtaining large feature maps and small feature maps of different layers; s3, applying a dynamic path selection strategy to acquire high-level features after weighted aggregation, acquiring global features and acquiring enhanced features of different layers; s4, the aligned features of different layers are obtained; and S5, combining the zeroth layer of the visible light and thermal infrared feature map to obtain a predicted saliency map. According to the method, features of different layers are dynamically selected and weighted, multi-size window modeling is carried out for correlation of different modes of unaligned salient regions by utilizing a visual attention mechanism, the problem that a data set needs to be aligned in RGBT salient target detection is solved, and the prediction performance is excellent.

The present invention discloses a coding device for a product tracing system, comprising a device body and a positioning mechanism, wherein the positioning mechanism comprises a first clamping block and a second clamping block, wherein the first clamping block and the second clamping block are respectively located at two sides of a top end of the device body, a first slide groove is provided on one side of a top surface of the device body, one end of the first clamping block is located inside the first slide groove, one end of the first clamping block located inside the first slide groove is fixedly connected with a slide rod, and a first spring is sleeved on the outer side of the slide rod; compared with the prior art, the present invention has the following beneficial effects: by designing the positioning mechanism, the product is fixed, the spacing can be adjusted, and coding of products of other specifications is convenient; and when adjusting, only the position of one side needs to be adjusted, thereby reducing the operation steps and improving the work efficiency; and when coding the next product, the position of the first clamping block and the second clamping block does not need to be readjusted.

The utility model discloses a coding machine for packaging food auxiliary materials, which comprises a mounting frame arranged above a machine base, material conveying rollers are arranged on the inner side of the mounting frame, a conveying belt is arranged between the two material conveying rollers, and a stand column is arranged on one side of the conveying belt; the transverse plate is arranged on one side of the stand column, a first sliding groove is formed in the side wall of the stand column, a first sliding block is arranged in the first sliding groove, a movable plate is arranged below the transverse plate, a second sliding groove is formed in the lower end of the transverse plate, and a second sliding block is arranged in the second sliding groove; a laser code printing mechanism is arranged below the moving plate, a third sliding groove is formed in the lower end of the moving plate, a third sliding block is arranged in the third sliding groove, the laser code printing mechanism can move transversely or longitudinally, different patterns are printed according to code printing requirements, and food packaging and conveying are seen through the moving conveying belt; and the food packaging coding efficiency is improved on the premise of ensuring the coding precision.

The present invention discloses an image encoding and decoding method with multi-resolution output, the method comprising: S1: extracting multi-scale features of an image and constructing a multi-scale feature library; S2: based on the multi-scale feature library, training an extreme learning machine model and a support vector machine model to predict the target existence probability and the target size; S3: when the predicted target existence probability is greater than the target existence probability threshold, selecting a multi-scale feature matching the predicted target size in the multi-scale feature library, encoding, and obtaining the encoding feature; S4: performing multi-scale expansion convolution on the encoding feature to obtain a decoded image; S5: based on the decoded image, identifying the target, and correcting the encoding and decoding system based on the identification result. The present invention selects multi-scale features of appropriate resolution for encoding according to the target size category, and corrects the encoding and decoding system according to the decoded image identification result, which is conducive to adapting to scene requirements and improving encoding and decoding efficiency and quality.

The invention discloses a material filling and packaging line, which belongs to the field of packaging equipment and comprises a bottle supply device, a cap supply device, a conveying device, an empty bottle mark photographing and adjusting device, a material filling device, a bottle cap mounting device, a bottle cap detection device, a finished product discharging device and a qualified product supporting device. The empty bottle mark photographing and adjusting device is used for transferring the empty bottles of the bottle supply device to the conveying device to photograph empty bottle marks and adjust the bottle body marks to face the same direction. According to the material filling packaging line, the empty bottle mark photographing and adjusting device is additionally arranged, the consistency of the postures of the bottles is guaranteed, the implementation of subsequent technologies needing to code the bottles and other technologies needing to keep the consistency of the postures of the bottles is facilitated, and the attractiveness of product packaging is also improved; in addition, the bottle cap detection device is additionally arranged, products with unqualified bottle cap installation can be removed in time, the yield of the products is increased, and the product quality is ensured. According to the material filling and packaging line, the bottle support supplementing device is additionally arranged in the qualified finished product support loading device, neglected loading of products is avoided, the supplemented material storage conveying line is arranged in the bottle support supplementing device to achieve supplementing work of the bottle supports, and therefore it is guaranteed that neglected loading of the bottle supports is avoided.

The invention provides an emotional support dialogue strategy management method fusing user feedback, and relates to the technical field of natural language processing, and the method comprises the steps: obtaining input dialogue information; inputting the dialogue information into a pre-trained knowledge enhancement encoder, and outputting context representation of enhanced knowledge; based on the context representation, selecting to generate a reply strategy for pacifying the user; generating a candidate reply consistent with the reply strategy based on the reply strategy and the context representation; and predicting feedback of the user to the candidate replies, and iteratively generating an optimal reply strategy based on the feedback. According to the method, the adaptive reply strategy can be effectively and accurately predicted, and the reply consistent with the reply strategy can be generated.

This utility model provides a low-noise mahjong machine, belonging to the technical field of mahjong machine technology; it includes a mahjong table, with a shuffling assembly rotatably connected to the bottom of the inner cavity of the mahjong table, a base fixedly connected to the bottom of the mahjong table, a No. 1 motor fixedly connected to one end of the inner side of the base, and a drive gear fixedly connected to the output end of the No. 1 motor. The drive gear meshes with the bottom end of the shuffling assembly. Inner grooves are formed around the inside of the mahjong table, and a cleaning assembly is rotatably connected to the inner side of each inner groove. This utility model, by setting up the cleaning assembly, allows a bidirectional screw to drive the inner screw sleeves on both sides, and pushes the surrounding push plates inward through a transmission rod. This allows the push plates to push the mahjong tiles above the table into the mahjong table, eliminating the need for manual pushing and improving the automation performance of the mahjong machine. Furthermore, the side grooves on the outer sides of adjacent push plates prevent collisions between the four push plates, facilitating the operation of the cleaning assembly.

The embodiment of the invention discloses an image perception pre-processing coding method, system and device and a storage medium. According to the technical scheme provided by the embodiment of the invention, the to-be-coded video image is acquired, the to-be-coded video image is input into the pre-trained pre-processing network model, and the pre-processing network model calculates the loss function based on the regression loss, the structural similarity loss and the discrete cosine transform loss in the training process; iteratively adjusting model parameters of the pre-processing network model based on a loss function until the pre-processing network model converges, and determining discrete cosine transform loss based on frequency domain information of a predicted image of the pre-processing network model; and outputting a pre-processing image of the to-be-coded video image based on the pre-processing network model so as to carry out video image coding based on the pre-processing image. By adopting the technical means, the image quality fidelity of the video image can be ensured while the coding efficiency is ensured, the pre-processing effect of the video image is improved, and the video coding and display effects are further optimized.