110results about How to "Save computing power" patented technology

The invention discloses an intelligent operation and maintenance management method and system based on an artificial intelligence data center, and relates to the technical field of data processing, and the operation and maintenance management system comprises a data collection module, a data classification storage module, a data prediction module, a data processing module and a data evaluation module. The data acquisition module is used for acquiring different hardware equipment data and software data in the operation and maintenance management system in real time. The data classification storage module is used for classifying and storing the data in the operation and maintenance management system, and then the importance of different data is determined by utilizing grades; and then the data prediction module analyzes the classified data, so that the operation and maintenance management system can predict different classification data conveniently, after fault data occurs in the operation and maintenance management system, judgment is performed between the fault data and the classification, and the position of the fault data in the operation and maintenance management system is effectively and quickly positioned.

The invention belongs to the technical field of large models of deep learning, and provides a large-model low-rank adaptive layer weight matrix fine tuning method in order to reduce calculation complexity in a low-rank weight matrix multiplication process in a low-rank adaptive method and optimize calculation power and memory requirements required by a training model. The two low-rank weight matrixes are copied, spliced and then added, or the two low-rank weight matrixes are divided into the sub-matrixes and then the sub-matrixes are added one by one, so that compared with a mode of multiplying the two low-rank weight matrixes, the calculation complexity of matrix low-rank decomposition can be reduced, meanwhile, the rank of the low-rank weight matrixes can be improved, and the calculation efficiency of matrix low-rank decomposition is improved. When different downstream tasks are finely adjusted, the corresponding weight parameters are independently trained and switched, so that the training efficiency of different fine adjustment weights is improved, and the weight memory requirement is reduced.

The invention discloses an unloading control method, device and system, and relates to the field of control. Based on material weight information of mineral powder loaded by a vehicle loaded with materials, the unloading time is calculated in advance, after it is determined that the vehicle is parked in a parking space of a corresponding unloading hole groove and unloading is started, the pre-calculation time is waited, and the unloading time is shortened; the vehicle residual material state is determined through image detection, and the vehicle is controlled so that the vehicle can conduct sudden entering and sudden braking of the target number of times matched with the vehicle residual material state, so that refined control over residual material discharging can be achieved, the situation that sudden entering and sudden braking control is conducted repeatedly is avoided to a certain degree, and the vehicle residual material discharging efficiency is improved. The residual material state detection is started after the pre-calculation duration, and compared with the scheme of real-time detection in the discharging process, the platform calculation power is saved; in addition, in the unloading process through the unloading device, participation of a driver and factory ground crew is not needed, and manpower resources can be saved.

The invention discloses a two-stage sparse method based on a small sample rapid sparse large-scale language model, and the method comprises the following steps: S1, mask initialization: based on a plurality of importance indexes for measuring parameters, employing a plurality of mask initialization methods to initialize a mask of a language model; s2, reordering the masks: reordering the masks based on the small sample calibration set and the straight-through estimator; s3, mask adjustment: based on the small sample calibration set and the reordered mask matrix in the step S2, taking an original model as a teacher model, taking a sparse model as a student model, realizing a block-level self-distillation process of the large language model in a time dimension before and after sparsification, and obtaining the sparse model; the method consumes less computing power, uses a smaller data set, occupies less GPU memory while realizing considerable performance, does not influence the reasoning speed of the sparse model, and has remarkable practical value and application prospect.

The invention provides a quality evaluation method and system for image correction and a rail transit detection device, and the method comprises the steps: carrying out the grading segmentation of a standard whole vehicle image with a single vehicle as a unit, and obtaining a standard key part region image; performing hierarchical segmentation on a target whole vehicle image to be evaluated by taking a single vehicle as a unit to obtain a target key component region image; performing feature extraction and feature segmentation on the standard key component region image to obtain a standard feature matrix; performing feature extraction and feature segmentation on the target key component region image to obtain a target feature matrix; and aligning the standard feature matrix with the target feature matrix, determining a feature change rate matrix, and evaluating the image correction quality based on the feature change rate matrix. According to the method, the whole vehicle image is segmented by taking a single vehicle as a unit, so that the computing power is saved, and the used memory is optimized. And the problem of quality evaluation after line scanning image correction is solved in a targeted manner.

The invention provides an industrial production safety intelligent management platform and management method. The platform comprises a real-time monitoring module, a risk assessment module, an operation permission and process management module, a data analysis and decision module, an emergency plan module, a fault maintenance module, an early warning module and a platform display module. And the risk assessment module comprises a first-level risk module, a second-level risk module and a third-level risk module of which the risk degrees are sequentially reduced. The real-time monitoring module transmits collected data to the risk assessment module, the fault maintenance module and the data analysis and decision module. And the operation permission and process management module is used for storing the monitoring data corresponding to the operation equipment of the real-time monitoring module, comparing the monitoring data with preset normal operation judgment conditions, and performing online application and approval on the operation of the real-time monitoring module. According to the method, closing operation is rapidly adopted for operation accidents, the step of analyzing emergency plans is saved, and the processing efficiency of emergently solving abnormities or accidents is improved.

The invention relates to a vehicle driving area detection method, electronic equipment and a storage medium. The method comprises the following steps: acquiring image data and point cloud data in a driving area acquired by a target vehicle; lane line detection is carried out on the driving area based on the image data, and obstacle detection is carried out on the driving area based on the point cloud data; and when it is detected that a lane line exists in the driving area, obtaining a detection result of whether an obstacle exists in a target lane corresponding to the lane line. According to the embodiment of the invention, the image data and the point cloud data are combined, lane line detection is carried out by utilizing the image data, and obstacle detection is carried out by utilizing the point cloud data, so that whether an obstacle exists in the target lane or not can be quickly and accurately judged, the computing power can be saved to a great extent, and a better recognition result can be obtained.

The invention discloses a flood situation detection method and device based on big data hyper-fusion and a medium. The method comprises the steps of generating a corresponding ponding area list and a monitoring area list; performing spatial association on the ponding area list, the camera list and the water level gauge sensor list so as to determine the camera and the water level gauge sensor which have a spatial association relationship with the ponding area; for each ponding area, calculating the water depth of the ponding area corresponding to the ponding area according to the water depth data collected by the camera and the water level gauge sensor which have the spatial association relationship with the ponding area, and predicting the predicted ponding depth of the ponding area in the future according to the water depth of the ponding area; dividing camera monitoring grading lists of different grades according to the first camera list, the second camera list and the fourth camera list; and feeding back the gathered flood situation information and the map capturing frequency to a control center, so that the control center carries out rescue scheduling according to the flood situation information, and carries out dynamic scheduling on cameras in the ponding area and the monitoring area.

The invention relates to the field of distributed archive management, in particular to a distributed budget archive collaborative management system based on big data, which is provided with an archive acquisition module, a feature analysis module, a label setting module and an archive optimization module. A label setting module triggers and determines a data representation difference representation value from a data standard form feature and sets a label for an archive file, then an archive optimization module is adopted to carry out targeted classification processing on the archive file according to the label of the archive file subsequently, and for the archive file with the difference representation label, it is considered that the difference of the archive file is high, and the classification efficiency is high. According to the method, a complete information extraction reconstruction mode is adopted, archive files are optimized, non-differential expression labels can be suggested to be processed due to the fact that the standard types of the archive files are high, and therefore when massive archive files are faced, targeted processing can be carried out, the computing power is saved, and the consistency of the archive files is improved.

The present invention discloses a workflow-based method for automated analysis and model optimization of hyperspectral data, and the steps are as follows: S1, processing the acquired hyperspectral image of the target sample, extracting and saving the spectral data of the characteristic area, and constructing a one-dimensional hyperspectral data set of all target samples; S2, constructing a DeepSpNet model based on a one-dimensional convolutional neural network; S3, setting the training parameters of the DeepSpNet model, and establishing a hyperparameter combination; S4, dividing the one-dimensional hyperspectral data set into a training set and a test set in proportion, training the DeepSpNet model with the training set, evaluating the accuracy, precision, and recall of the DeepSpNet model through the test set, and automatically screening the best hyperparameter combination; S5, saving the DeepSpNet model with the best hyperparameter combination for target prediction. The present invention can accurately capture the defect characteristics inside the sample and effectively improve the depth detection capability.

Embodiments of the present application relate to the technical field of human-computer interaction, and disclose a method and device for determining an interactive gesture and an electronic device. The method comprises the following steps: first, target component detection is performed; then, gesture detection and recognition are performed in a local area (around a boundary box) near the target component. In addition, for N gesture detection boxes (multiple users) in a current video frame, M target gesture detection boxes are selected therefrom to perform hand component positioning and gesture recognition processing, which can reduce detection time consumption and improve real-time performance. On this basis, the interactive gesture is determined according to the gesture detection result of the current video frame and the gesture detection results of a plurality of historical video frames, that is, gesture recognition is selectively performed on the user in each frame in a plurality of continuous video frames to determine the interactive gesture, which can reduce the computing power, reduce the time consumption, improve the real-time performance, and improve the accuracy and stability of the interactive gesture. That is, in the multi-user human-computer interaction scene, the interactive gesture can be accurately and timely determined.

The invention relates to an artificial intelligence technology, and provides a to-be-financed invoice verification method, apparatus and device, and a medium, which perform table restoration on contract information based on a large language model, and perform subsequent processing after the contract information is restored into a table, so that the reasoning effect of the large language model can be improved. The target cue word is generated according to each piece of commodity information in the target invoice to be financed and the contract data table, and the target cue word is input to the large language model for reasoning, so that the large language model can be utilized to perform automatic matching on the invoice to be financed and the contract information, manual intervention is not needed, the matching efficiency is improved, and the error rate is low; according to the method, the reasoning result is post-processed to remove invalid information, so that the valid information is utilized to verify the to-be-financing invoice, and the calculation power is saved, so that the verification efficiency is improved.

The application discloses a routing association relationship updating method, a routing communication method and related devices. The method determines the shortest path of each node in the autonomous network when updating the path, and determines the problem node according to the comparison result between the shortest path of each node and the historical path. Finally, according to the routing prefix in the problem node association prefix set, the target next hop block associated with the routing prefix is selected from the pre-stored next hop block. Then, the next hop block associated with the first prefix is updated according to the target next hop block and the shortest path of the problem node. The next hop block of the application is an index representing the forwarding address of the message. The update of the next hop block associated with the routing prefix is the update of the forwarding address of the message. The flow does not need to re-decide the next hop address of each routing prefix based on the shortest path of all nodes when updating the path, which saves the computing power and improves the network performance.

The present invention discloses a real-time hybrid test control compensation method, comprising: obtaining the displacement response of the actuator through white noise excitation; fitting the white noise with the displacement response to obtain a transfer model; designing a compensation filter based on the transfer model, and optimizing the parameters of the compensation filter, and completing the hybrid test control compensation based on the optimized compensation filter model. The purpose of the present invention is to reduce the loading error in the hybrid test and increase the test accuracy. At the same time, the stability and reliability of the hybrid test are also guaranteed.

The present invention discloses a method for video deinterlacing and super-resolution based on a cyclic Unet network. The method of the present invention is a multi-frame input and multi-frame output adaptive video deinterlacing based on a cyclic Unet neural network. Each time, the current two adjacent frames of data and the two-field deinterlacing prediction data predicted in the previous time are input, and the above data are input into the Unet neural network, and the two-field deinterlacing data predicted in the current time and the deinterlacing data restored in combination with the input data are output. If the input is standard definition data and the output requires high-definition data, the deinterlacing data is input into the SRnet (super-resolution restoration network) to output high-definition deinterlacing data. If no data conversion is required, the deinterlacing data is directly output. The cyclic Unet neural network of the present invention has a powerful video deinterlacing restoration capability, and can adaptively process interlaced data of different scenes without scene judgment to obtain an ideal deinterlacing effect.

The application provides a multi-inverter hybrid system transient stability boundary delineation method based on reverse integration, and belongs to the field of electrical engineering. The delineation method combines a circuit model of a grid-constructed inverter, a grid-following inverter and an infinite grid hybrid system and a virtual synchronous machine mathematical model of the grid-constructed inverter, derives a second-order differential-algebraic equation set of the hybrid system, further obtains system steady-state equilibrium points by solving the equation set and classifies, and reversely integrates from the type I unstable equilibrium point to obtain a transient stability boundary of the hybrid system. The application is simple and intuitive, has a solid theoretical basis, can quickly and accurately identify the transient stability boundary of the grid-connected inverter system, and has important significance for analyzing the transient stability of the multi-grid-connected inverter hybrid system.

This invention provides a face action recognition method, comprising: acquiring the face key point recognition results of a local face parsing service for a sequence of images to be recognized, wherein the sequence of images to be recognized is obtained by a face image acquisition service based on face action recognition instructions; determining the organ key point sequence corresponding to each target facial organ based on the face key point recognition results, wherein the target facial organs are determined according to the face action recognition instructions; determining the action recognition results corresponding to each target facial organ based on the organ key point sequence; and determining the face action recognition results of the front-end browser based on the action recognition results. Face action recognition can be directly performed in the front-end browser based on the organ key point sequence, reducing server-side computing power. Furthermore, using the organ key point sequence for face action recognition eliminates the need to directly capture temporal dependencies in the sequence of images to be recognized, reducing the parameter requirements of the local face parsing service, thereby reducing development and deployment costs.

The present invention discloses a vehicle driving trajectory prediction method for an automatic driving system, which includes the steps of 1, determining the position and boundary of surrounding static obstacles; 2, predicting the trajectory of the dynamic obstacles of interest by a long short-term memory network method; 3, planning a collision-free local path by a dynamic programming optimization method; 4, calculating a suitable preview distance according to the current positioning and speed of the vehicle itself, and determining the corresponding preview point on the local path; 5, calculating the wheel deflection angle required to reach the preview point according to the difference between the vehicle heading and the heading of the preview point; 6, calculating the vehicle's own position in the next step according to the vehicle kinematics; 7, determining whether the index value of the preview point exceeds the index value of the local path end point, and if so, outputting the final result as a collision-free predicted trajectory; otherwise, returning to step 4. The technical effect of the present invention is that an automatic driving vehicle can accurately predict the driving trajectory on a road without lane lines, reduce computing power, and avoid collision accidents.

The invention relates to the technical field of information, in particular to a log storage system construction method and system based on multidimensional logic relation interaction.The method comprises the steps that a log storage instruction is received, an original log set is collected based on the log storage instruction, analysis operation is executed on the original log set, and a multidimensional data set is obtained; calculating a user weight according to the multi-dimensional data and the priority user sequence, calculating a time weight according to the transaction time and the priority time sequence in the multi-dimensional data, obtaining a headquarters position, calculating a position weight according to an initiation position and the headquarters position in the multi-dimensional data, and obtaining a headquarters position; and calculating the log priority according to the user weight, the time weight, the position weight and the transaction amount value, performing classification compression operation on the backlog set to obtain a log compression package, and constructing a log graph database by using the common log set to complete the construction of the log storage system. According to the method, the log storage space can be saved, and the log retrieval efficiency is improved.

The present application provides a camera online calibration method, device and vehicle, and relates to the field of camera calibration technology. When the target camera meets the online calibration conditions, the method obtains the current configuration information and historical calibration information of the target camera, and when it is determined based on the current configuration information and the historical calibration information that the target camera meets the continuous calibration conditions, the target camera is continuously calibrated based on the historical calibration information. Thus, when the target camera fails to exit the online calibration due to factors such as the road environment and the driving mode during the last online calibration process, the historical calibration information generated when the last online calibration exited can still be used during the current online calibration process for continuous calibration, that is, there is no need to perform the online calibration of the target camera from the beginning during the current online calibration process, which greatly improves the probability of successful online calibration of the target camera and reduces the computing power during the online calibration of the target camera.

The embodiment of the invention discloses a space array UV LED light source and an AI time domain control photoetching method, and relates to the technical field of photoetching. The method comprises the following steps: acquiring a mask file, and decomposing the mask file to obtain a plurality of basic patterns; based on a preset basic pattern algorithm database, a plurality of UV LED lamp bead control algorithms corresponding to the basic patterns of the mask plate file are obtained respectively, and an initial space array UV LED light source control algorithm is formed; based on a preset neural network, the initial space array UV LED light source control algorithm is optimized in a mechanical learning mode, and an artificial intelligence light source-mask joint optimization algorithm is obtained; and controlling the space array UV LED light source to penetrate through the mask plate to expose a wafer based on the artificial intelligence light source-mask joint optimization algorithm. Compared with a traditional photoetching method, the method has the technical effects of small calculation amount and high product yield.

The invention discloses a large-range collaborative navigation method for an extraterrestrial patroller, and relates to the field of computer vision, visual navigation and map splicing. The method comprises the following steps: performing significance analysis based on spectral residual for a right monocular camera, focusing on sight capture of a typical feature region, establishing a visual odometer model of inertial IMU pre-integration, and performing back-end optimization driven by a factor graph; establishing a plurality of extraterrestrial patroller similar region search models based on an improved bag-of-words model, introducing a similarity relative scoring function based on a norm form, setting a relative threshold value of a similarity suppression function, and obtaining an image overlapping region; according to the method, the calculation capability of an airborne computer is considered, a sparse feature point map and patroller pose splicing model is established, complete splicing of overlapped area maps is completed through splicing of small sparse feature point maps, and the splicing precision and the splicing efficiency are improved.

The invention discloses a multi-energy carbon flow emission monitoring method and device suitable for an industrial park, and the method comprises the steps: building a source-network-load full-link multi-energy carbon flow model from the two links of energy transmission and energy conversion in combination with the carbon emission characteristics of each link of an energy network; providing a basic flow of multi-energy carbon flow calculation of the industrial park in combination with respective characteristics of various energy sources; on the basis of the multi-energy carbon flow model and the basic flow of industrial park multi-energy carbon flow calculation, energy carbon flow information of all inflow nodes of a current node is inquired in combination with a decentralized iteration thought until the energy carbon flow information of the node is calculated, and global energy carbon flow information is output when preset iteration times are reached; and on the basis of global energy carbon flow information, the multi-energy carbon flow of the industrial park is monitored in combination with the characteristics of the global energy carbon flow information. The device comprises a processor and a memory. According to the invention, accurate and credible real-time carbon emission calculation and monitoring of the industrial park energy system are realized, and the atmospheric environment is improved.

The invention relates to the technical field of image recognition, in particular to a dish recognition system based on visual inspection, a dish image storage module stores a plurality of dish images, a dish classification module calculates dish recognition tendency parameters and divides the categories of the dish images, and a recognition unit selects recognition strategies according to the categories of the dish images. Matching with a dish library according to the chromatic value of each food material in the dish image and the outline of the food material, identifying a dish corresponding to the dish image, or screening a dish possible set in the dish library according to the shape and size of each food material in the dish image and the chromatic value of each food material, and obtaining the food material contained in the dish possible set, the food materials contained in the dish possible set are matched with the food materials contained in the dish images, the dishes corresponding to the dish images are recognized, the display unit is used for displaying the dishes corresponding to the dish images, the dish images are classified, different recognition strategies are adopted for all kinds of dish images, and therefore the recognition efficiency is improved while the reliability is guaranteed.

The present invention discloses a hydropower unit health status evaluation system based on multi-source information fusion, which relates to the technical field of hydropower unit health status evaluation. A stage analysis unit is used to determine whether the same type of equipment will be in any of the basic period, the two-term period and the final period under different service times, and then the content of the enabled monitoring object is analyzed according to the different time periods; the monitoring object analyzes several maintenance data, observes the number of occurrences of each monitoring data under abnormal conditions, and determines which monitoring objects are in high frequency according to the number of occurrences, so as to determine to monitor different data at different stages; thereby, the present application can observe a small amount of data under different conditions to determine whether an abnormality occurs. The present application is simple and effective, does not need to monitor all data, and can save computing power in some cases.

The application discloses a wavelength modulation-direct absorption dual-mode wide-range gas concentration detection method with temperature self-adaptive threshold, and belongs to the technical field of tunable diode laser absorption spectrum gas detection. The existing pure mode switching scheme generally uses a fixed concentration threshold, and temperature change will cause the switching point to deviate from the optimal error balance point, aiming at the problem, the application calibrates the critical peak absorbance as a unified reference under the reference temperature, and also calculates the line intensity under different temperatures to generate a corresponding lookup table; during work, the current line intensity is obtained by real-time temperature lookup table, and the concentration switching threshold is dynamically updated, the wavelength modulation mode is used in the initial detection stage, when the concentration continuously exceeds the threshold, the direct absorption mode is switched to, and when the concentration is lower than the hysteresis threshold, it is switched back, the application uses dynamic threshold updating to make the switching point correspond to the optimal error balance point of the two methods at all times, and the sensitivity at low concentration and the linearity at high concentration are considered.

This application provides a license plate recognition method, apparatus, electronic device, and storage medium. The method includes: sliding a sliding window of preset length and width along the long side of a preset sliding area in a first image, acquiring multiple sliding window results generated during the sliding process; determining the cutting position of the image to be processed based on the multiple sliding window results and the cutting position; determining whether the license plate to be recognized is a double-layer license plate based on the cutting position; if the license plate to be recognized is a double-layer license plate, cutting and stitching the image to be processed according to the cutting position to obtain a second image; and inputting the second image into a license plate recognition model to obtain a first recognition result. In this technical solution, the electronic device only needs to store a single-layer license plate recognition model to simultaneously recognize both single-layer and double-layer license plates, improving memory utilization and reducing the computing power used.

The invention discloses a visual bending clamp image anti-shake method and system, which relates to the technical field of image communication and comprises an image acquisition module, an image processing module, a data transmission module, a display module and the like. An electronic anti-shake technology is adopted, a high-performance image acquisition module is integrated in the limited clamp body space of the visual bending clamp, the performance of a camera is fully played, and the effects that the response delay time is smaller than 20 ms, 25 frames of images are stably output per second, and each frame of image has 512 * 512 pixels are achieved; the working state of the camera is divided into a mobile working state and a static working state, image anti-shake calculation is carried out only in the static working state, scene requirements are accurately met, the computing power is saved, and image display is more scientific and efficient; a complex feature point matching algorithm is abandoned, the infrared light source is ingeniously introduced, the distance between the camera and the shot part is calculated in real time through the infrared light source, anti-shake calculation is accurately achieved, and meanwhile the tissue developing effect is improved in the static working state.

The application discloses a kind of based on image space random distribution lossless secret image steganography and extraction method, specifically is: using space technology in carrier image pixel low 4 place write secret information, the pixel value of secret image is using random sample to break up pixel order before embedding carrier image, for the embedding position of secret image in carrier image, using key generation random uniform distribution pixel position;Image extraction method, 16 bits character is extracted from the end of key, decode as the width and height value of secret image, through key generation secret image pixel position random sample and secret information embedding position in carrier image, extract secret information from embedding position, and restore each pixel of secret image, generate the secret image after restoration.The beneficial effects of the present application are: the present application can be used for covert information and the like Hidden transmission, with lossless extraction, embedding capacity is larger, information security is good, not easy to detect, the characteristics such as small consumption of computing power.

The invention relates to the field of cement sheath detection, in particular to a method for evaluating the gas packing capacity of a cement sheath, which comprises the following steps of: testing the gas breakthrough pressure of the cement sheath with different heights and cementation characterization parameters by simulating the service temperature, pressure and gas well bore conditions of the cement sheath on site; and a cement sheath packing capacity expression is established through a multivariate linear fitting method according to an experimental result, so that the cement sheath packing capacities of different well sections are accurately evaluated, and the evaluation efficiency of the gas packing capacity of the cement sheath is improved.