348 results about "Similarity model" patented technology

A novel bandwidth extension technique allows information to be encoded and decoded using a fractal self similarity model or an accurate spectral replacement model, or both. Also a multi-band temporal amplitude coding technique, useful as an enhancement to any coding/decoding technique, helps with accurate reconstruction of the temporal envelope and employs a utility filterbank. A perceptual coder using a comodulation masking release model, operating typically with more conventional perceptual coders, makes the perceptual model more accurate and hence increases the efficiency of the overall perceptual coder.

A method for matching documents based on spatial layout of regions based on a shape similarity model for detecting similarity between general 2D objects. The method uses the shape similarity model to determine if two documents are similar by logical region generation in which logical regions are automatically derived from information in the documents to be matched, region correspondence, in which a correspondence is established between the regions on the documents, pose computation in which the individual transforms relating corresponding regions are recovered, and pose verification in which the extent of spatial similarity is measured by projecting one document onto the other using the computed pose parameters.

The invention provides a target tracking algorithm based on the self-adaptive particle filter and sparse representation. According to the target tracking algorithm based on the self-adaptive particle filter and the sparse representation, the improved self-adaptive particle filter technique is adopted to serve as a tracking algorithm framework, a block sparse representation model is used for establishing an observation similarity model of a target, partitioning of the target is achieved by means of the self-adaptive partitioning technique, a structural sparse column diagram of a current target state is constructed to calculate the observation similarity of the current target state, blocking is detected by means of a blocking detection mechanism, a target / background dictionary template and a target template column diagram are updated to capture the change of the appearance of the target and the change of the environment during tracking, L1 optimization in the sparse representation is achieved by means of the variable-direction multiplicator method, and then the execution speed of the target tracking algorithm is increased. The target tracking algorithm based on the self-adaptive particle filter and the sparse representation has the advantage that the robustness to the conditions of the posture change of the tracking target, the change of the environment and lighting and blocking is strong.

The invention discloses a social-label-based method for optimizing a personalized recommendation system. In the method, social label similarity and score similarity are adopted and applied to calculation of a user-and-project oriented K-nearest neighbor model, and then a user and a project of a K-nearest neighbor are used for calculating a prediction score of the project by the user at the same time. Because the label similarity and the score similarity are adopted in the method at the same time, so that the K-nearest neighbor calculation of the user and the project is more accurate, the recommendation accuracy is obviously higher than that obtained by singly adopting the score similarity, and a cold-start problem based on a label similarity model can be solved. Therefore, a data sparsityproblem can be solved by using a user-and-project oriented recommendation model, and the recommendation accuracy is also obviously higher than that of a conventional user-oriented recommendation model and a project-oriented recommendation model.

The invention discloses a method and system for recommending information. The method includes the steps that when a recommending request sent by a client is received, a relevant recommending list is generated according to current information browsed by a user and an information similarity model; a non-personalized recommending list is generated according to a statistic model of behavior data; a personalized recommending list is generated according to the information similarity model, the statistic model of the behavior data and a user interest model; a comprehensive recommending list is generated according to the generated relevant recommending list, the generated personalized recommending list and the non-personalized recommending list; the generated comprehensive recommending list is returned to the client as the recommending result. With the method and system, a result meeting the interest of the user and the information scene currently browsed by the user can be recommended to the user, and the method and system can meet user requirements better by adjusting the recommending result according to a recommending strategy.

The invention discloses an author influence propagation ability prediction method based on an interest similarity model. The author influence propagation ability prediction method includes the following steps that 1, academic relation information of author literature is extracted and excavated from literature basic information of a literature database and includes author-paper writing relation and literature-literature citation relation; 2, according to the author-paper writing relation and the literature-literature citation relation, an author citation relation network and an author cooperative relation network are set up; 3, based on co-citation relation, interest similarity among authors is calculated, wherein the co-citation relation means that if two pieces of literature citrates one piece of literature, the two pieces of literature have the co-citation relation; 4, the author citation relation network and the author cooperative relation network are used for excavating author influence propagation path; interest similarity is used as path weight, and influence propagation ability is obtained through weighted calculation.

The invention provides a large mechanical equipment structure dynamic similarity test method, comprising the steps as follows: (1) a basic similarity theorem is adopted, all physical quantities are listed, geometrical quantity, density and elastic modulus are determined as basic physical quantities, and the similarity theorem is written into a dimensionless equation expressed by the basic physical quantity; (2) according to concerned basic physical principle, the similarity ratio of all physical quantities adopts similar relation expression, and the similar relation expression is modified according to a structure elastic vibration similarity equation; (3) similar model material is selected, density similarity ratio and elastic modulus similarity ratio are determined, geometrical quantity similarity ratio is determined, and the similar model design is then completed; (4) a structure dynamic test of the similar model is carried out so as to obtain the dynamic characteristic number which is substituted into the similarity relation expression so as to work out the dynamic characteristic data of the original model which is also the natural vibration frequency. The large mechanical equipment structure dynamic similarity test method realizes the conversion of ultra-large structure dynamic natural frequency with small model, effectively reduces the scales of dynamic test objects, simplifies the test instruments, and reduces the test cost.

An embodiment of the present invention provides a similarity model test apparatus for simulating tunnel construction, comprising a testing stand, a hydraulic loading apparatus, a data test and acquisition apparatus, and a similarity model; wherein the hydraulic loading apparatus is arranged outside the testing stand; the similarity model is arranged inside the testing stand; one part of the data test and acquisition apparatus is arranged inside the testing stand, the other part of the data test and acquisition apparatus is arranged outside the testing stand. The similarity model test apparatus in the embodiment of the present invention not only can achieve simulation of an excavation process of the tunnel, a tunnel pre-support state and influence on the tunnel by extraneous dynamic load, but also can complete data acquisition and analysis through a built-in monitoring system, so as to evaluate and optimize deflection of tunnel excavation, control capability of support means, and influence degree on the tunnel construction by the extraneous dynamic load.

The invention relates to a terminal area prevailing traffic flow recognizing method based on track spectral clusters. The method includes the steps of firstly, analyzing a given airport pavement to obtain flight path data, and conducting dividing to obtain feature track points and normal track points; secondly, setting up a space rectangular coordinate system; thirdly, putting forward an occupation degree concept according to the distance between a track and the center of a space grid, and enabling the occupation degree concept to be used for representing the occupation degree of the track in the space grid; fourthly, setting up an inter-track overall similarity model on the basis of a track partial similarity model; fifthly, constructing an Laplacian similarity matrix, and then analyzing the clusters through the spectral cluster algorithm; sixthly, conducting prevailing traffic flow recognition on the clusters obtained in the fifth step through the nuclear density estimation method; seventhly, displaying the recognition result in a displaying and interaction module. The terminal area prevailing traffic flow recognizing method has the advantages that a prevailing traffic flow track and an abnormal track can be simultaneously obtained through the spectral cluster algorithm, therefore, related personnel are assisted in scientifically and reasonably planning a terminal area and improving airport entering and leaving air lines, and the capacity of the terminal area is improved.

The invention relates to the field of traffic data processing and the field of intelligent transportation, and discloses a traffic road condition forecasting method and device based on historical data and date attribute data. The method and the device are used for solving the problems that in the prior art, traffic road condition forecasting depends on real-time data, forecasting input is complex, and a traffic road condition change rule is hard to embody on the date attribute data. The technical scheme provided by the invention is that the method comprises the steps of through mining a relation of the date attribute data and the road condition, on the basis of the road historical road condition data and the date attribute data, building a reliable and effective road condition forecasting model, i.e. completing road traffic road condition changing process similarity assessment modeling at different dates based on the date attribute date through researching historical multi-day date attribute data and the road condition data; and on the basis of the obtained traffic road condition changing process similarity model, date attribute data corresponding to a date to be forecasted, and a date attribute and road condition data corresponding to the historical date, carrying out road condition forecasting of the date to be forecasted.

The invention discloses a model test device for simulating the instability failure of rock and soil slopes under complex conditions, and belongs to the technical fields of geotechnical engineering andmining engineering. The model test device comprises a wind and rain simulation system, an earthquake simulation system, a similar model test system and a monitoring system. Through the adoption of the device, similar model test of rock and soil slope bodies such as waste dumps and tailings dams can be carried out efficiently, and the stability and failure modes of the slope bodies under rainfall,earthquake and the coupling action thereof can be researched and analyzed.

The invention discloses an image super-resolution reconstruction processing method. On the basis of adaptive sparse representation reconstruction research, a series of corresponding sub-dictionaries are obtained through image block subset learning, and then an optimal sub-dictionary is adaptively selected for each reconstructed image block, so that more accurate sparse representation modeling can be carried out and the algorithm effect and efficiency can be improved. In order to improve the capability of a sparse representation model, a nonlocal self-similarity prior item is introduced, a nonlocal self-similarity model is improved by utilizing a bilateral filtering thought, and spatial position distance constraints among pixels are introduced, so that image edge information is better kept. Moreover, distance measurement of nonlocal self-similarity is improved, so that the calculation amount is reduced. An experiment proves that the noise influence can be effectively suppressed and image edge details can be kept, and the method has a certain superiority in the aspects of peak signal-to-noise ratios and visual effects.

The invention discloses a human face confirming method based on similarity measurement. The method comprises the following steps that features of N pairs of human face images are extracted, each pair of human face features are subjected to PCA transform, and a feature vector of human face sample pairs is obtained; within-class weighed subspace is obtained through a weighted covariance matrix and subjected to weighted subspace projection, and feature vectors of the human face pairs obtained after projection are obtained; in combination of the knowledge of priori measurement, a priori similarity matrix and a priori distance matrix are obtained; a lagrangian multiplier method and a paired method are used for solving a target function of similarity measurement learning, and a measurement matrix is obtained; the similarity of human face pairs is calculated in combination with a similarity model, and therefore an optimal threshold value is obtained and used for human face confirmation. The problems that under the constraint-free condition, due to interference of expressions, postures, illumination, backgrounds and other factors, the difference of different human face images of the same person is large, and extracted human face feature vectors are greatly different are solved, and therefore the human face confirmation accuracy is improved.

The invention provides a Storm-based real-time recommendation method and a system therefor. The real-time recommendation method comprises the steps of: A, performing offline similarity calculation on video data and behavior data of users separately to obtain a similarity model of video, and performing statistical analysis on the behavior data to obtain the statistical data of user behavior; B, performing user modeling according to the video data in the Storm end to generate interest vectors and combining the interest vectors and the similarity model to obtain individualized recommendation results based on the user behavior; C, integrating the statistical data, the similarity model and the individualized recommendation results to obtain a recommendation list. The method combines similarity and interest, thereby improving the accuracy of individualized analysis of user preferences and guaranteeing the recommendation quality.

The invention discloses a subject similarity based case retrieving method, and belongs to the technical field of data retrieving. The method is characterized in that the document layout and the keywords are treated as the constraint conditions, and the automatic extraction algorithm is utilized to extract three sections, namely, the case facts of the document, the dispute focus and the judgment result; the subject terms of each document section are correspondingly extracted through a subject mode based on the field word list, thus obtaining the subject word blocks and non-subject word blocks of each document section; a feature inverse index is created according to the property words in the subject word blocks and the non-subject word blocks of each document section; the feature inverse index is mapped into a feature vector; the similarity of searching statements and documents in a document data set is calculated through a subject similarity model; the similarity of searching statements and documents in the document data set are sequenced, and the sequencing result is output, thus finishing document retrieving. According to the method, the document is described in a two-dimension manner, namely, the judicial feature words and the judicial subject, and the similar-case retrieving efficiency and accuracy can be improved.

The invention discloses a training method for similarity model parameters, a search processing method and corresponding apparatuses. The method for the similarity model parameters comprises the steps of constructing a training data set; performing training by utilizing the training data set to obtain the similarity model parameters; obtaining statement description input by a user and obtaining all word entries from a pre-created word entry database; obtaining a word vector matrix corresponding to the statement description and a word vector of each word entry in the word entry database; determining the similarity between the statement description and each word entry in the word entry database according to the similarity model parameters and the word vector matrix corresponding to the statement description; and presenting a search result of the statement description to the user according to the similarity between the statement description and each word entry in the word entry database. According to the training method, the search processing method and the corresponding apparatuses, the word entry described by the user can be reversely searched for according to the description input by the user, so that the search experience and efficiency of the user are improved.

An overheating fault simulating method for GIS (gas insulated switchgear) bus joint includes steps of building a mathematical temperature-rising model according to a physical heating process of the GIS bus joint; performing similarity analysis according to the mathematical temperature-rising model, determining an accurate coupling field similarity relation; simplifying the mathematical temperature-rising model, determining an approximate coupling field similarity relation; determining a simulation test scheme of overheating faults of the GIS bus joint and a physical GIS bus joint similarity model under various contact conditions; implementing an overheating fault simulation test on the basis of the physical similarity model of the GIS bus joint according to the simulation test scheme, and acquiring simulation test data. By simulating the overheating faults of the GIS bus joint with the similarity model of the GIS bus joint, overheating fault mechanisms and reliability features are indirectly researched, the defects that protomodel simulation test is high in cost, equipment manufacturing period is long and reliability during test is poor are overcome, and implementing of temperature monitoring and routing inspection of the GIS bus joint are facilitated.

The embodiment of the invention provides a text matching method based on a text similarity model. The method comprises the following steps of: receiving text information and determining a feature vector of the text information, wherein, the feature vector at least comprises a text string, a text phonetic alphabet and a word vector; Feature vectors are input into the text similarity model; Obtaining the feature similarity of the output of the text similarity model; At least one preset statement reach a preset feature threshold is determined as match text of that text information according to the feature similarity. The embodiment of the invention also provides a text matching system based on a text similarity model and a training method and system of the text similarity model. The embodiment of the invention determines the feature similarity between the user input statement and each preset statement in the text similarity model by using the text similarity model considering a pluralityof dimension feature vectors, and further determines the matching text with relatively high precision.

The invention relates to the field of intelligent decision making and discloses a consultation request processing method and device, a computer equipment and a storage medium, to reduce question and answer interaction between an operator and a user, reduce the situation of low efficiency caused by human participation and effectively improve consultation feedback efficiency. The method comprises the following steps: obtaining a consultation request triggered by a user through an application, wherein the consultation request comprisingto-be-answered consultation text information; determining whether the to-be-answered consultation text information being questioning text information or not through a preset text classification model; if being determined that the to-be-answered text informationbeing question text information, to extract a to-be-answered question from the to-be-answered text information; determining the similarity between the to-be-answered question and the historical questioning question according to a preset similarity model; determining target answering content according to the similarity between the to-be-answered question and the historical questioning question; and performing consultation feedback on an answer corresponding to the consultation request.

Embodiments of the present invention relate to a song recommendation method and apparatus. The method comprises: obtaining a historical preference score of each song heard by a target user within a preset number of days; according to the historical preference score of each song heard by the target user within a preset number of days and a song similarity model, determining a first score of each song in a music library, and recommending the song to the target user based on the ranking of the first score of each song in the music library; obtaining a second score of each song in the music library, wherein the second score is a score of a song obtained based on music-playing behaviors of a plurality of users and a user voting algorithm; determining interest tags of the target user according to historical song-searching behavior data of the target user; and recommending the song to the target user based on the ranking of the second score of each song under the interest tags. Thus, according to the method and apparatus provided by the embodiments of the present invention, the accuracy of recommending songs to the user is high, and the personalized needs of the user can be satisfied.

Embodiments of the invention provide a target user directing method and apparatus. The method comprises the steps of determining the similarity between alternative users and seed users by utilizing a similar model; by utilizing a conversion prediction model, predicting probabilities of executing predetermined conversion operations on to-be-released information by the alternative users; and according to the similarity and the probabilities, selecting out a target user of the to-be-released information from the alternative users.

The invention discloses a method for recombining an incomplete JPEG file fragmentation, comprising the following steps: extracting and determining JPEG file fragmentation data on a memory medium; acquiring JPEG file header information and decoding the JPEG file fragmentation according to the JPEG file header information based on the type of the JPEG file to obtain multiple JPEG file fragmentation data blocks to be analyzed; acquiring the similarity of two data blocks according to a similarity model and connecting the adjacent data blocks according to the similarity to form a JPEG file; and judging whether the data block belongs to the current JPEG file according to the MCU difference of each data block, if not, deleting, and otherwise, maintaining, wherein the maintained multiple data blocks connected together form a complete JEPG file. By using the method, the file fragmentation can be accurately recombined into a complete JPEG file.