68results about How to "Guaranteed Search Accuracy" patented technology

The invention discloses a cloud environment task scheduling method based on an improved ant colony algorithm. On the basis of the conventional ant colony algorithm, a rest-life-pheromone (RLP) concept is introduced; by comparing the RLPs of ant brothers in the searching process, repeated search can be effectively eliminated, and searching accuracy is improved; and by adoption of a method for computing the quantity of the ant brothers, the quantity of ants can be dynamically changed under the specific conditions of loads and tasks of cloud environment, so a system is not overloaded, and the searching accuracy is ensured. Compared with the prior art, the cloud environment task scheduling method based on the improved ant colony algorithm has the advantages that requirements of a user on task execution time can be met to the greatest extent, and the allocation efficiency and execution efficiency of the tasks are improved.

The invention discloses an image retrieval method based on visual phrases in the technical field of computer information processing. The method comprises the following steps of: firstly, extracting salient areas of a standard image and an image to be retrieved, respectively, and extracting characteristic describers from the salient areas; secondly, clustering the characteristic describers in a standard image library by means of a random kd tree; thirdly, representing the characteristic describers of the standard image and the image to be retrieved using visual phrases, respectively, and creating a two-dimensional inverted index according to the visual phases of the standard image; and finally, performing similarity search and space geometrical relationship measurement on the characteristic describers of the image to be retrieved represented by the visual phrases in the two-dimensional inverted index, thus giving a final retrieval result. The method disclosed by the invention reduces the calculation quantity of the retrieval process and improves the instantaneity of retrieval while guaranteeing the accuracy rate of retrieval.

The invention belongs to the technical field of image exposure, and relates to an automatic exposure control method. The automatic exposure control method comprises the steps of S1, carrying out imagecollected by using binocular vision and an active structural light source projection method, and obtaining the last image collected each time; S2, obtaining the average brightness of the image by using a dynamic partitioning and dynamic weight coefficient adjusting method; S3, judging whether the average brightness of the image is within a target brightness range or not, if so, not carrying out exposure compensation and terminating the automatic exposure control, otherwise, entering the step S4; and S4, obtaining the difference between the average brightness of the image and the target brightness, selecting the corresponding step size for exposure compensation according to the difference and returning back to the step S1. The automatic exposure control method soles the problems of great noise signal, insufficient or excessive exposure of a target area due to excessive contrast between the target object and the background, excessively long adjustment time and excessively great difference between the image brightness and the target brightness in the prior art.

The invention discloses a quick movement estimation method which comprises the following steps: taking the median prediction point of an existing block, the central point of a block at same position with the existing block in a reference frame and the motion vector toward point of the block at the same position with the existing block in the reference frame as candidate search points; selecting an initial search point in the candidate search points; determining the position of a search window in accordance with the selected initial search point, and determining the size of the search window in accordance with the type of the existing block; and determining the matching block/or the motion vector of the existing block in the search window. In the method, the multiple candidate search points are preset, and the advantages of a quick movement estimation algorithm are used for reference; and by setting the different search windows and search step sizes corresponding to the existing blocks with the different types, search accuracy is ensured, the total number of the points required to be searched can be effectively reduced at the same time, thus the method is more beneficial to realizing based on hardware.

The invention discloses a fault diagnosis method for a PWM inverter of a motor drive system. The fault diagnosis method is characterized in that an inverter fault diagnosis model based on both wavelet packet decomposition and an RBF neural network is designed, wavelet packet transformation is utilized to extract a feature vector of a fault signal of the inverter, and the feature vector is taken as the input quantity of the RBF neutral network; a wolf pack-simulated annealing algorithm is adopted to optimize structural parameters of the RBF neutral network; and 22 groups of learning samples and 6 groups of test samples are utilized to train and examine the RBF neutral network. Simulation experiment analysis shows that when the fault diagnosis method is used for an open-circuit fault of the PWM inverter of a three-phase motor drive system, the fault position of an inverter TGBT power tube can be accurately positioned, fault diagnosis is quick, accurate and efficient, and the fault diagnosis method contributes to improving the running reliability of the motor drive system.

The invention provides a ship short-circuit fault diagnosis method based on improved GA-PSO-BP which comprises the following steps: S1, acquiring a three-phase voltage signal when a ship power system is short-circuited, and establishing a training data set and a test data set; S2, establishing a three-layer BP neural network model; S3, establishing a particle swarm representing the BP neural network model; s4, endowing the BP neural network model with the particle position, inputting the training data set into the BP neural network to carry out ship short-circuit fault diagnosis, obtaining a diagnosis result, calculating an error value of the diagnosis result, when the error value is greater than or equal to gmax and the number of iterations does not reach gmax, adding 1 to the number of iterations, entering S5, otherwise, ending iteration, and entering S7; s5, updating the particle speed and the particle position; s6, performing cross mutation on particle positions, and updating the particles into particles of the next generation; repeating the steps S4-S6; s7, using the global optimal value of the particle swarm as an optimal particle to endow the BP neural network model; and S8, inputting the test data set into the BP neural network model, and diagnosing the ship short-circuit fault.

The invention discloses an adaptive genetic algorithm-based interplanetary orbit control optimization method. The method comprises the following steps: establishing a B plane of a target planet; calculating a velocity increment of orbit control and a B plane position residual error; and optimizing a midcourse correction opportunity by using an adaptive genetic algorithm. Fuel consumption of midcourse correction and a target planet position error are used as optimization objectives. The genetic algorithm is used for carrying out optimization on the opportunity of the midcourse correction in the interplanetary transfer orbit; the traditional genetic algorithm is improved, the adaptive crossover probability and mutation probability are used, and the algorithm convergence rate is accelerated. Compared with the traditional numerical searching method, the adaptive genetic algorithm enables the optimizing precision to be ensured and calculation time to be saved. With the method, the considerable fuel consumption can be reduced for the interplanetary exploration task and the efficiency of the interplanetary cruise track control strategy selection can also be effectively improved.

The invention relates to a data search method and system based on table function and a computer storage medium. The data search method based on table function comprises the following steps: classifying external information based on a preset rule; performing feature expression on the external information according to a classification result; preprocessing a result of the feature expression; generating a target mapping relation table of the search resources based on the preprocessing result; and outputting a result of the search problem through the target mapping relation table. On the basis of guaranteeing the search accuracy, the purposes of improving the search efficiency, enabling the search result to be fed back in real time and meeting the actual operation requirement are achieved.

The invention provides a data processing method based on a cloud server. The data processing method comprises a step of data initialization, to be specific, combining data distributed at different network spaces, completing default items in data and cleaning dirt data; selecting data, to be specific, converting different formats of data from initialized data into a uniform format; a step of data pretreatment, to be specific, checking the uniform format of data, removing redundant data with noise data, and supplementing default data, and meanwhile, marking the data through encoding; a step of data excavation, which mainly includes steps of determining an excavation goal, selecting an algorithm, and processing the data by the excavation algorithm, and educing and storing the excavated data after adding a logo. The speed rate in data searching is improved, and the searching precision is greatly improved.

The invention discloses a dynamic zooming search window-based motion estimation method and a dynamic zooming search window-based motion estimation system. The method comprises the following steps of: performing zero motion pre-termination judgment on a video sequence; predicting initial search points; performing initial positioning by searching on a large scale by adopting an extended hexagon search method; performing secondary search in a determined range on a small scale by adopting a diamond search method; and further performing precise positioning in the determined range by adopting a cross search pattern (CSP) method to obtain a motion vector. The system is characterized by consisting of a video data input module and a central processing unit module, wherein the video data input module is formed by connecting an acquisition charge coupled device (CCD) camera with an analogue-to-digital (A/D) converter in series; the central processing unit module comprises an image preprocessing module, a first buffer, a second buffer, a search window data memory, a comparator, a control subprogram control module, an operation subprogram control module and a clock control module. The method and the system improve the search efficiency of a motion estimation algorithm.

The invention provides a motion estimation method, a motion estimation device, a computer readable storage medium and electronic equipment, and relates to the technical field of image and video processing. The motion estimation method comprises the following steps: determining an error between a to-be-matched block and a candidate block, the to-be-matched block being an image block in a current frame image, and the candidate block being an image block in a reference frame image; selecting at least two candidate blocks with the smallest error with the to-be-matched block from the candidate blocks; determining a search range in the reference frame image according to the positions of the at least two candidate blocks; and searching a global optimal block of the to-be-matched block in the search range, and obtaining an optimal motion vector of the to-be-matched block through the global optimal block. According to the invention, motion estimation can be carried out in different scenes, andthe accuracy and efficiency are high.

The invention discloses a data search method and device. The method comprises the steps of obtaining natural language input information; determining search intention data corresponding to the naturallanguage input information according to the natural language input information; according to the search intention data and a pre-established matching model, determining a search intention type corresponding to the natural language input information, pre-establishing a matching model according to natural language historical input information, wherein the search intention type comprises a list listtype, an attribute value type or an object information type; and searching the data according to the natural language input information and the corresponding search intention type. The search efficiency can be improved while the search accuracy is guaranteed, manpower and material resources are saved, and the user satisfaction is improved.

The invention provides a litigation cost prediction method, a litigation cost prediction device, and terminal equipment. The invention is suitable for the technical field of data processing. The method comprises the steps of obtaining case information, evidence information and personal information of a to-be-processed case input by a user; analyzing the case information to obtain case keywords andcase types; searching a first historical similar case based on the case keyword, the case type and the personal information; screening the first historical similar cases to obtain corresponding second historical similar cases; and processing the case information and the evidence information of the to-be-processed case based on the case information, the evidence information, the judgment result, the litigation duration and the cost data of the second historical similar case to obtain a reference judgment result, a reference litigation duration and reference cost data of the to-be-processed case. According to the embodiment of the invention, the analysis and accurate prediction of the case litigation duration cost and result are realized.

The invention discloses an image retrieval method and device, computer equipment and a storage medium, and relates to the field of artificial intelligence. The image retrieval method comprises the steps of acquiring a to-be-retrieved image; extracting scale invariant feature transformation feature points of the to-be-retrieved image; traversing the scale-invariant feature transformation feature points of the to-be-retrieved image, and acquiring a target feature center by calculations, substituting the index number of the target feature center for each scale invariant feature transformation feature point closest to the feature center over time; and searching in a Hash inverted index table according to the index number of the target feature center to obtain a target historical image. By adopting the image retrieval method, the same or similar images can be quickly retrieved from mass images.

The method comprises: selecting the searching template based on quadrature distributive model; using the quadrature distributive feature of motion vector to fast position to neighboring area of the optimum point; making motion search on multi searching points corresponding to each level of searching template; finding the motion searching point with least error from the result of motion search; according to the position of the motion search point with least error in the first level search template, determining the searching template used by the next motion search.

The invention relates to a short-term power load prediction method based on SFO-TSVR. The method comprises the following steps: obtaining historical load data, meteorological data and corresponding date type data to serve as original sample data; dividing the original sample data into a training set and a test set; setting an input data sequence, and constructing a TSVR model; based on the training set, training the TSVR model by adopting an SFO algorithm; and based on the test set, verifying the trained TSVR model, and if the verification is passed, inputting related data of an actual to-be-predicted day into the trained TSVR model according to the set input data sequence to obtain a power load prediction value of the actual to-be-predicted day, otherwise, returning to carry out model training again. Compared with the prior art, the method can efficiently and accurately obtain a short-term load prediction result.

The invention provides a file processing method based on Internet. The file processing method comprises steps of initiating a file, in which merging files in different network space and supplementing default items in files and cleaning dirty files, selecting files, converting the files initially processed into a uniformed format, pre-processing the files, in which the format-uniformed files are checked and noise files and redundant files are eliminated, default files are supplemented and the files are encoded and labeled, and excavating the file, concretely comprising the following steps of determining an excavating target, selecting algorithm, processing the file based on the excavating algorithm and attaching the label to the excavated file and storing the file. File searching speed can be improved and searching precision can be guaranteed by the use of the file processing method based on Internet.

The invention provides a video copy detection method and device, a storage medium and an electronic device. The method comprises the following steps: extracting a first target key frame of a query video; extracting a first video feature of the first target key frame; acquiring a second video feature of a second target key frame of the reference video; and when it is determined that the query video is matched with the reference video according to the first video feature and the second video feature, extracting similar video clips in the query video and the reference video. The problems of low video copy detection efficiency and poor video copy detection accuracy in a video copy detection method in the related technology are solved, and the effects of improving the video copy detection efficiency and improving the video copy detection accuracy are further achieved.

The invention discloses a data acquisition method, which comprises the following steps of acquiring an acquired data identifier by a server, and retrieving in a memory cache according to the data identifier; if the corresponding material data is not retrieved in the memory cache, obtaining the material data corresponding to the data identifier from a database; and processing the material data to obtain display data. The material data is hierarchically stored to hierarchically process the acquisition of the data, so that the data acquisition efficiency is improved, and the risk that the database is broken down is also reduced. The invention further discloses a data retrieval method and a request response method.

The invention discloses a medical image retrieval system based on computer processing in the technical field of image retrieval. The medical image retrieval system comprises an acquisition image subsystem; the acquisition image subsystem is in electrical output connection with a central processing unit; the central processing unit is electrically and bidirectionally connected with a retrieval subsystem; the central processing unit is in electrical output connection with a display subsystem; and the display subsystem is electrically and bidirectionally connected with a feedback subsystem. According to the medical image retrieval system disclosed by the invention, information in an input image is directly read by the acquisition image subsystem so as to ensure accuracy of retrieval, benefit to accuracy of analysis on pathology and reduce individual subjectivity and uncertainty; by the central processing unit, retrieval of the image is ordered, and rapid retrieval efficiency and accuracy are ensured; and by the retrieval subsystem, information to be retrieved can be rapidly, accurately and respectively retrieved from a computer database, the internet and an index database, and accuracy of the information and a wide retrieval range are ensured.