104 results about "Importance Weight" patented technology

The present invention is directed to a system and a method for generating a temporally ranked set of search results in response to a query. Each result in the set of search results can be ranked temporally or based on the reputation associated with authors of each result and the reputation associated with the repository where each result is located. Temporal ranking takes into account a present importance weight and a future importance weight are assigned to each result. The present importance of each result uses creation date, publication date, in-link dates and search frequency, and the future importance uses an aging factor based on the elapsed time from publication for each search result and a rate at which each search result decreases in importance. Temporal ranking can be applied as a modification of existing and common search engine algorithms include PageRank and HITS.

An improved system and method for identifying context-dependent term importance of queries is provided. A query term importance model is learned using supervised learning of context-dependent term importance for queries and is then applied for advertisement prediction using term importance weights of query terms as query features. For instance, a query term importance model for query rewriting may predict rewritten queries that match a query with term importance weights assigned as query features. Or a query term importance model for advertisement prediction may predict relevant advertisements for a query with term importance weights assigned as query features. In an embodiment, a sponsored advertisement selection engine selects sponsored advertisements scored by a query term importance engine that applies a query term importance model using term importance weights as query features and inverse document frequency weights as advertisement features to assign a relevance score.

An improved system and method for identifying context-dependent term importance of queries is provided. A query term importance model is learned using supervised learning of context-dependent term importance for queries and is then applied for advertisement prediction using term importance weights of query terms as query features. For instance, a query term importance model for query rewriting may predict rewritten queries that match a query with term importance weights assigned as query features. Or a query term importance model for advertisement prediction may predict relevant advertisements for a query with term importance weights assigned as query features. In an embodiment, a sponsored advertisement selection engine selects sponsored advertisements scored by a query term importance engine that applies a query term importance model using term importance weights as query features and inverse document frequency weights as advertisement features to assign a relevance score.

The embodiment of the invention provides a text matching method and device applied to electronic equipment. The method comprises the steps that search terms input by a user are received and subjected to participle treatment, at least one participle is obtained; according to a pre-trained classification model and at least one of the term property, semantic attribute, independent search term probability and click rate of each term, the importance weight of each participle is determined; according to the text to be matched and a text set where the text to be matched is located, the term frequency and inverse document frequency of each participle are determined; according to the importance weight, term frequency and inverse document frequency of each participle, the matching degree of the search terms and the text to be matched is calculated. According to the text matching method and device, the importance degree of each participle can be more accurately measured by means of the important weight and inverse document frequency of each term, and therefore the text matching accuracy can be improved when text matching is carried out according to the importance degree of each participle.

The invention discloses a bayesian fitering-based general data assimilation method. The method comprises the steps of: inputting an initial value set into an analysis model in a prediction step so as to obtain a prediction set value; calculating prediction error covariance matrix by using set kalman filtering in an updating step, and updating each prediction set according to the observation value and kalman gain matrix; or, calculating importance weight of each set sample by adopting particle filtering through set prediction value, calculating the number of effective particles by utilizing normalization importance, resampling the set according to the weight to obtain updated analysis value and analysis set; or, calculating prediction error covariance matrix by adopting unscented kalman filtering, and updating each prediction set according to the observation value and kalman gain matrix; conducting next prediction and assimilation by taking the updated analysis set as the initial values of the analysis model, and repeating the prediction step and the updating step. The method can enable Earth remote-sensing observation information and land surface process model information to be effectively integrated, thus forming a land surface process information prediction system with small errors.

The invention provides a method for extracting a keyword from a text. The method comprises the following steps: dividing the text into words to obtain the words corresponding to the text; labeling word characteristics of the words; adding statistical information to the words; indexing the words; inputting label information, the statistical information and indexing information of the words into a deep learning extraction model so as to obtain importance weights of the words; according to the importance weights, selecting at least one corresponding word as the keyword of the text. In correspondence to the method, the invention further provides a device for extracting the keyword from the text.

The invention discloses a power communication network security situation awareness and prediction method based on IRT hierarchical analysis and LSTM (Long Short Term Memory). The method is used for solving awareness and prediction on the security situation in the existing power communication network. The method comprises the implementation processes of: firstly, extracting characteristics influencing network security situation evaluation from network connection condition data acquired in the power communication network, furthermore, calculating a network security situation value based on a hierarchical IRT model, and then, establishing a network security situation prediction model based on LSTM, so that prediction on the security situation of the power communication network is realized. Byadoption of the method disclosed by the invention, the accuracy of the importance weight in a security situation evaluation process can be effectively improved; for the time sequence properties of anetwork security situation, the security situation of the power communication network can be predicted better; and furthermore, the network security condition can be reflected and predicted more accurately and effectively through the established model evaluation and prediction method.

The invention relates to a drug entity relationship extraction method and system based on an attention mechanism neural network. The method comprises the following steps: (1) analyzing the text content of a pharmaceutical document, using sentences as basic units for sentence segmentation, and performing vectorization representation on each word in the sentences; (2) inputting a vectorized representation result into a recurrent neural network, extracting association characteristics of words in the sentences according to a front-back bidirectional word sequence through the recurrent neural network, and identifying all medicine entities; (3) obtaining inter-word importance weights in the sentences through an attention mechanism neural network, and combining the inter-word importance weights with the output in the step (2); And (4) inputting a result obtained in the step (3) into a convolutional neural network, and predicting a category relation between every two medicated entity words through the convolutional neural network. According to the classification method for increasing the attention mechanism concerned entity class information weight, the influence caused by wrong dependencyanalysis results in long sentences can be reduced, and the accuracy of extracting the pharmacochemical entity relationship is improved.

The invention discloses a text processing method and device and a storage medium. The method comprises the steps of obtaining a plurality of original short sentences of an original text and a plurality of original words of each original short sentence, and obtaining a plurality of target short sentences of a target text and a plurality of target words of each target short sentence; determining anoriginal short sentence vector of each original short sentence according to the original word vector of each original word and the corresponding importance weight, and determining a target short sentence vector of each target short sentence according to the target word vector of each target word and the corresponding importance weight; obtaining the similarity between the original text and the target text according to a first target matrix determined by each original short sentence vector and the corresponding importance weight and a second target matrix determined by each target short sentence vector and the corresponding importance weight; and when the similarity is greater than a target threshold, determining that the target text is matched with the original text, and outputting the target text, so that the technical problem that the text matching accuracy is lower in the prior art is solved.

A frequency hopping signal receiving system comprising: a receiver for extracting discrete-time samples from the signal; a memory connected to the receiver for storing the extracted discrete-time samples from the signal; at least one processor operatively connected to the memory for: determining a state-space vector that captures relevant information to describe the dynamics of the signal; selecting a parameter to represent the probability of hopping associated with the signal; generating particle filters to estimate unknown parameters in the state-space vector based upon the extracted discrete-time samples by generating random particles that approximate the filtering distribution having importance weights; specifying the importance function in closed-form in a convenient mixture representation, which enables drawing particles and updating the importance weights; constructing an estimator to generate hop particles based upon observing at least one sample hop and then evaluating the estimator using a conditional expected value; using a spectrogram to generate particles in conjunction with an importance function; and estimating the hop frequency, hop time, and amplitude parameters, and a method thereof.

The invention discloses a method for acquiring document set abstracts and a device for improving the acquiring effect of the document set abstracts. The method extracts each sentence included in each document in the document set for forming a sentence set, the importance weighted value of each sentence in the sentence set is determined on the basis of the text similarity between documents in the document set and between the sentences in the sentence set, and the document set abstracts are formed by selecting the sentences in the specified number according to the determined importance weighted values in accordance with the selection sequence from higher importance weighted values to lower importance weighted values.

The invention discloses an electromobile energy supply cost analysis method based on a hierarchy analysis method, which comprises the following steps of: 1) constructing a hierarchical structure model by taking electromobile energy supply cost as a target layer, an evaluation index as a criterion layer, sub indexes of the evaluation index in the criterion layer as a sub criterion layer and an optional battery energy supply mode as a scheme layer, 2) quantitatively evaluating importance of the sub indexes under the criterion layer for a general target of the target layer according to a 1-9 scaling method and constructing a comparison judgment matrix, 3) calculating a weight vector of the matrix, 4) carrying out consistence check on the judgment matrix, modifying importance weights of the criterion layer and the sub criterion layer for the general target if the consistence check does not meet requirements till the consistence check meets the requirements, 5) outputting a synthetic weight of schemes of the scheme layer, and 6) carrying out decision analysis. The analysis method has reference and application values for the decision analysis of constructing a charging station and an electrical changing station.

The invention claims an adaptive Monte-Carnot positioning method incorporating two-dimensional code information. The method comprises the steps of: S1, establishing a motion model by using absolute position information provided by the two-dimensional code and a control amount u<t> of an odometer; S2, performing particle sampling according to the established motion model, and estimating an initialpose of a robot; S3, using a two-dimensional laser sensor for ranging to establish an observation model; S4, determining the importance weight of each particle and updating the weight; S5, adaptivelyadjusting the number of particles required for the next iteration according to the distribution of the particles in a state space; and S6, determining the position of the robot in the environment according to the distribution of the particles. The adaptive Monte-Carnot positioning method incorporating the two-dimensional code information can accurately position the robot in the environment and reduce the calculation amount.

The invention discloses a method for comprehensively evaluating an ecosystem service of an artificial wetland. The method comprises the following steps of: A, establishing a target, evaluation criteria and an evaluation index of each criterion; B, establishing a scoring questionnaire of a step analysis judgment matrix for the comprehensive evaluation of the ecosystem service of the artificial wetland to form a criterion layer and an index layer; C, calculating a relative importance weight of the criterion layer relative to a target layer and a relative importance weight of the index layer relative to the criterion layer; D, calculating importance weights of a lowest layer and a highest layer and inspecting a calculation result; E, tracking and monitoring the characteristic of each index of the index layer and evaluating an original numerical value of each index; and F, multiplying the importance weight of general ranking in the step D by the fuzzy membership of the index obtained by the step E to obtain the comprehensive evaluation index situation of the ecosystem service of the artificial wetland. The method can conveniently, deeply and fully analyze all values of the ecosystem service of the artificial wetland. Guidance and basis are provided for design, optimization, construction, operation and management.

The present invention provides an automatic hierarchical atlas collaging method based on image importance. The method comprises four steps: step 1: segmenting an image by using a Meanshift algorithm, extracting a salient area in the image in a rectangle manner, and if there are a plurality of salient areas, merging the salient areas into one; step 2: calculating to obtain a different degree of an image foreground and background through color complexity and pixel gradient complexity of the image foreground and background, then calculating an average value of different degrees between the image and other images in an atlas, to obtain a representing degree of the image, and finally averaging the different degree of the foreground and background and the different degrees between images, to obtain importance of each image; step 3: storing a hierarchical relationship of the atlas by using an XML file, and using the above obtained importance of the image as a weight of a node and storing a rectangle outline circumscribing the salient area; and step 4: using a Voronoi tree to visualize a hierarchy of the atlas, representing a subset of the atlas or an importance weight of the image by using a canvas area, and automatically collaging the salient area of each image according to the rectangle outline of the salient area of the node and an image zooming technology.

The invention provides an artificial fish-swarm based particle filtering method in which the artificial fish-swarm algorithm is introduced into particle filtering. The basic thinking of the method is as follows: the clustering and foraging behaviors of the artificial fish-swarm algorithm are introduced while the target function, namely the measurement function, is selected and the importance weight is adjusted to guide the prior particles to continuously move toward a high likelihood domain, thus improving particle distribution, increasing the diversity of the particles and improving the filtering precision of the algorithm; besides, in the artificial fish-swarm algorithm, when a domain for optimization is larger or is in an area which is flat in change, a part of artificial fishes randomly move aimlessly, thus affecting the optimization efficiency; and the invention further provides an adaptive step method to improve the randomness of artificial fish view selection, thus not only lightening the computational burden of the algorithm but also ensuring the algorithm convergence.

The invention discloses a method for carrying out adaptive computing on importance weights of low-level features of an image, which is used for ensuring the visual integrity of a sensitive target in the process of image compression. In the invention, according to an image, the optimal compression parameters are adaptively computed, wherein the image comprises four low-level features such as color, gradient, brightness and center distance; in the process of computing the importance weight of color, an image to be processed is subjected to color histogram statistics, and a weight function is established for computing the weight of color according to frequencies; in the process of computing the importance weight of gradient, the image is divided into blocks, the gradient of pixels in each block is computed, then the orientation of the obtained gradient is subjected to histogram statistics, and an inter-block orientation change rule is computed so as to determine the importance weight of gradient; in the process of computing the importance weight of brightness, the image to be processed is divided into two parts, the brightness value of each part is computed, and the part with a larger value is taken as the main reference basis for weight computing; and in the process of computing the importance weight of position, a fixed value is assigned, and finally, corresponding weight parameters of each low-level feature are obtained.

The invention discloses an automatic text abstract generation method based on dynamic word vectors, and aims to provide an automatic text abstract generation method with higher accuracy and fluency. According to the technical scheme, the method comprises the steps of firstly preprocessing a text through a text preprocessing module, wherein the preprocessing comprises word segmentation operation, high-frequency word filtering and part-of-speech tagging, and forming an initial word vector from the processed text; inputting the initial word vector into an ELMo model module to generate a preliminary dynamic word vector; meanwhile, inputting the text into a Doc2Vec sentence vector module to obtain a sentence vector of each sentence; inputting the sentence vector into a self-attention mechanismmodule to calculate an importance weight relative to the abstract result so as to generate a weighted sentence vector; and taking the weighted sentence vector as an environment feature vector of eachword, adding the environment feature vector and the initial dynamic word vector to obtain a final dynamic word vector, and inputting the dynamic word vector into a Transformer neural network model togenerate a high-quality text abstract.

The invention relates to an intelligent photovoltaic array fault diagnosis method based on an optimal rotating forest. Firstly, the data of photovoltaic electrical characteristics under various operating conditions are collected and mapped to obtain the overall fault characteristics. Secondly, the ReliefF feature selection algorithm is used to rank the importance weights of the fault features, andthe most important fault features are obtained. Then, the input variables of the base classifier are obtained by using the improved rotating forest algorithm. Furthermore, the limit learning machinereplaces the decision tree in the original rotating forest algorithm to overcome the over-fitting problem and obtain the optimal model parameters by traversal method. Furthermore, the optimal trainingmodel of rotating forest fault diagnosis is obtained by combining the improved rotating forest algorithm with the limit learning algorithm to train each sample in the training set. Finally, the training model is used to detect and classify the fault of PV arrays. The method of the invention has high classification accuracy and is an effective alternative scheme for photovoltaic fault diagnosis.

A method and an apparatus for word quality mining and evaluating are disclosed. The method includes: calculating a Document Frequency (DF) of a word in mass categorized data; evaluating the word in multiple single-aspects according to the DF of the word; and evaluating the word in multiple aspects according to the multiple single aspect evaluations to obtain an importance weight of the word. According to the solution of the present invention, the importance of the word in the mass categorized data may be evaluated, and words with high quality may be obtained through an integrated evaluation.

The embodiments of the invention provide a multi-modal fusion method and device for psychological stress detection. The multi-modal fusion method is based on an attention-enhanced feature matrix of physiological data->text, physiological data->pictures, text->physiological data, text->pictures, pictures->physiological data and pictures->text, based on a feedforward fully-connected neural network,a fusion feature matrix of the text, the pictures and the physiological data is obtained; then based on importance weights of the text, the pictures, and the physiological data and the fusion featurematrix of the text, the pictures and the physiological data, a fusion representation matrix of three modes is obtained; and finally, based on the fusion representation matrix of the three modes and the feedforward fully-connected network, a pressure classification vector reflecting the psychological stress problem is obtained. By merging text picture data and physiological related data, not only the deficiencies caused by the subjectivity of text and picture data are compensated, but also certain inherent problems of physiological related data are solved.

The invention applies to the multimedia information field, and provides a coding optimization method of a medium grain scalable video, a coding optimization device of the medium gain scalable video, and an information terminal. The method comprises the following steps: defining an importance weight vector of a sheet; calculating the mass percentage of each sheet based on a mass enhancing layer; establishing a relation curve of the code rate and the mass percentage according to the mass percentage of the sheet in the mass enhancing layer and the bit number actually required for coding the sheet; and structuring a rate-distortion model of the medium grain scalable sheet; estimating the video stream code rate according to the structured rate-distortion model of the medium grain scalable sheet and rate-distortion models of preset I, P and B frames; and obtaining an optimal solution controlled by the code rate within the target medium grain scalable code rate interval by a greedy algorithm according to the estimated video stream code rate. In the invention, a medium grain scalable video coding scheme is optimized by the greedy algorithm, therefore, the problems due to the limited bandwidth and the video quality can be effectively solved, and the image coding quality can be improved.