50 results about "Online dictionary" patented technology

Methods, systems and computer programs for automatic, highly accurate machine comprehension of a plurality of segments of free form unstructured text in a natural language. The system answers a plurality of complex, free-form questions asked in a natural language, based on the totality of input text. The system further uses a multi-dimensional data model to measure the total effects of actions / verbs acting on various unique nouns present in the input text. The system may convert the questions into another multi-dimensional data model and may then compare the two data models in program memory to derive the answers to the posed questions. The system may then automatically detect unknown words and optionally look them up in digital information sources, such as online dictionaries and encyclopedias, to fill in the gaps in knowledge to answer the questions with expert-like reliability.

The invention relates to the technical field of image processing, and particularly relates to a sparse-representation-based multi-mode magnetic resonance image segmentation method and a device. A sparse-representation-based classification SRC (sparse representation based classification) algorithm is adopted by the segmentation method. An image is accurately segmented via establishing an image segmentation model on the basis of an MAP-MRF framework by the segmentation method. A Markov random field is utilized, and influence of adjacent pixels in surrounding space of the pixels is fully considered so that accuracy of image segmentation is increased. Meanwhile, an online dictionary learning method and an image segmentation optimization method are adopted so that operation speed is enhanced.

The invention discloses an indoor human body behavior recognition method. The method comprises the following steps that: human body three-dimensional skeleton information is obtained based on Kinect equipment; three-dimensional skeleton features in each video set are extracted; the three-dimensional skeleton features are trained, and the features are described, and the training of the three-dimensional skeleton features further includes the following steps that: online dictionary learning is performed on the features, and then, sparse principal component analysis is performed on the features, and finally, a multi-task large margin nearest neighbor algorithm and a linear support vector machine are utilized to classify the features, so that a training feature set can be obtained; three-dimensional skeleton features of test videos are extracted; and the multi-task large margin nearest neighbor algorithm and the linear support vector machine are utilized to classify the features, so that feature descriptions can be obtained, and optimum judgment is performed on the training feature set and the test features with a scoring mechanism. The indoor human body behavior recognition method of the invention has a bright application prospect in intelligent video surveillance, patient monitoring systems, human-computer interaction, virtual reality, smart home, intelligent security and prevention and athlete assistant training, and has high feasibility and great social economic benefits.

The invention relates to a non local joint sparse representation based hyperspectral image super-resolution reconstruction method. The method comprises: firstly, performing dictionary training on a low-spatial-resolution hyperspectral image with an online dictionary training method to obtain a corresponding spectral dictionary; secondly, performing joint sparse representation on similar pixel vectors by virtue of a full-color image of a same scene, and reconstructing a high-resolution image; and finally, processing the reconstructed high-resolution image by utilizing an iterative reverse projection technology to obtain a high-resolution hyperspectral image with smaller reconstruction error and higher visual quality. According to the method, the similar pixel vectors are subjected to non local joint sparse representation by utilizing the non local self-similarity property of the image, so that the visual quality of the reconstructed image is improved and structural features of edges, textures and the like of the image are reconstructed more effectively in an empty region while image spectral information is kept complete; and multiple wavebands of the hyperspectral image are subjected to sparse representation and reconstruction at the same time, so that the hyperspectral image with relatively high definition and identification degree can be reconstructed.

The invention discloses a self-adaption online dictionary learning super-resolution method. The method firstly selects one group of high-resolution training image set and one group of low-resolution training image set,then establishes a relationship on the high-resolution training image set and the low-resolution training image set, and provides more prior information for image reconstructing through high-resolution / low-resolution dictionary to obtain a better reconstructing effect under the condition of high amplification factor, at the same time, the method uses SP (Self Propelled) sparse coding algorithm, overcomes the defect of low reconstructing accuracy due to traditional greedy algorithm and keeps a lower computation complexity. The method has the advantages of overcoming the defects of complex computation and low training speed in the current mainstream dictionary learning algorithms such as MOD (Multimedia On Demand) and K-SVD(k-singular value decomposition) and shortening image reconstructing time in general. Compared with the prior art based on learning image super-resolution, the method of the invention has a higher reconstructing accuracy and a shorter algorithm time.

A system and method predictively generates words based on a user input, according to a frequency of lookup of each of the generated words. The system and method also allows for a user to add predictively generated words to a word list that assists in the facilitation of word and vocabulary comprehension for a user. Words in the online dictionary are grouped in word families where a user can navigate between different forms of a root word.

The invention provides a super- resolution image reconstruction system based on a self-adaptation submodel dictionary choice. The super-resolution image reconstruction system based on the self-adaptation submodel dictionary choice comprises an input module, a high and low frequency training set construction module, a candidate base vector gathering and building module, a submodel dictionary choice module, a test image preprocessing module, a super-resolution image reconstruction module and an output module, wherein the high and low frequency training set construction module comprises a band allocation submodel and a primitive block extraction submodel; the candidate base vector gathering and organizing module comprises an online dictionary learning submodel and a DCT dictionary construction submodel; the test image preprocessing module comprises a low frequency smoothing submodel and a primitive block extraction submodel. The super-resolution image reconstruction system based on the self-adaptation submodel dictionary choosing is applied to different dictionary sizes and decimation factors, the super-resolution image reconstruction system based on the self-adaptation submodel dictionary choosing can significantly improve the subjective and objective quality of a reconstitution image, the high effective dictionary design process is guaranteed, and a novel visual angle is provided for the existing image compression standard at the same time.

The invention discloses a bearing fault diagnosis method based on feature enhancement, which can effectively and rapidly extract bearing fault vibration signal shock characteristics while the signal data amount is reduced. Firstly, the bearing fault vibration signals are decomposed by variational mode decomposition (VMD), a kurtosis value and a component with the maximum cross-correlation functionwith the original signal are selected as the optimal components which have better block sparse characteristics. On the basis of the traditional online dictionary learning constraint model, l2, 1 normconstraints of a sparse coefficient are added. Under a new constraint model, sparse representation and dictionary learning are carried out alternatively, inter-block sparse characteristics of the newconstraint can be matched with block sparse characteristics of vibration signals in a sparse representation process, the redundant component in the signals is further removed, l2, 1 norm constraintsare added during the dictionary learning process at the same time, and an experimental result shows that dictionary atoms acquired from the dictionary learning process with new constraints added are more robust against noise interference. The dictionary obtained based on learning and the sparse coefficient are subjected to signal reconstruction, the signal shock characteristics with the redundantcomponents enhanced such as noise in the signals can be removed, and the fault information of the signals is further extracted to complete fault diagnosis.

The invention discloses a multi-angle indoor human action recognition method based on a 3D skeleton. The multi-angle indoor human action recognition method comprises the following steps that 1) videos of human motions at three angles of a front angle, a squint angle and a side angle are acquired; and the videos include training videos and test videos; 2) human skeleton 3D features in the videos are extracted through body feeling equipment; and the three-dimensional skeleton features include global motion features and arm and leg local motion features; 3) model training is performed; feature description is performed through the human skeleton 3D features in the training videos so that a training feature set is obtained; and the concrete process is listed as follows: online dictionary learning of the three-dimensional skeleton features is performed; and then dimension reduction is performed through sparse principal component analysis so that a feature set data set is formed; and 4) the feature set of the samples of the test videos is inputted, and recognition is performed through a linear support vector machine (LSVM). Classified recognition of the multi-angle motions is realized by the method so that the limitation of a single-angle recognition algorithm can be overcome and thus the method has more research value and actual application value.

The invention discloses a vibration signal compressing and sampling method, and belongs to the technical field of processing for mechanical vibration signals. The vibration signal compressing and sampling method can effectively solve the problem of an adaptive ability and an online learning ability. The vibration signal compressing and sampling method comprises the steps of first carrying out Nyquist sampling on continuous vibration signals Xc so as to acquire a prior signal Xp of the vibration signals; constructing a sparse transformation matrix Ds of the prior signal Xp by using an online dictionary learning algorithm; then carrying out sparse transformation on the continuous vibration signals Xc so as to acquire a sparse vector Xs, transmitting the sparse vector Xs to a perception matrix so as to carry out perception sampling to acquire a compressed signal Y; and finally, transmitting the compressed vibration signal Y to a reconstruction recovery terminal, carrying out signal reconstruction, and acquiring a vibration signal Xc with a transverse line thereon. The method disclosed by the invention is mainly applied to long-distance transmission of vibration signals.

This invention describes an electronic dictionary that is built and maintained by the user community. It is a single source to translate any word from any language into any other language. The dictionary resides with an online server. User with online connection specifies his / her native language and looks up any correct word, misspelled word, acronym, or phrase of any foreign language. The definitions and related information are also supplied by the user community. A user can also place advertisement. He / she can associate the advertisement with the entries in the dictionary. While the dictionary content is user maintained, the administrator has the full control.

The invention provides a gradable video coding system based on multi-scale online dictionary learning. A multi-scale training set establishing module based on layered sparsity is used for obtaining layered sparsity structures, in different scales, of an image through wavelet transformation. By means of a Gaussian differential filter set, direction energy is extracted so that primitive areas in the image can be obtained, and a multi-scale training set is generated by cutting out image blocks of the primitive areas. By means of an online dictionary learning module, it is ensured that dictionary atoms are iterated and optimized under low complexity according to the stochastic gradient descent method so that a sub-dictionary base corresponding to the multi-scale training set can be generated. For low-frequency video frames, a cross-scale video frame reconstruction module learns lost high-frequency information on different levels through the constructed sub-dictionary base; the aim of grading video quality is achieved through different-grade wavelet inverse transformation reconstruction. By means of the gradable video coding system, complexity of a super-resolution algorithm based on learning is lowered, the reconstruction quality gain is obtained at different transmission rates compared with H.264, and high expandability is achieved.

Methods, systems and computer programs for automatic, highly accurate machine comprehension of a plurality of segments of free form unstructured text in a natural language. The system answers a plurality of complex, free-form questions asked in a natural language, based on the totality of input text. The system further uses a multi-dimensional data model to measure the total effects of actions / verbs acting on various unique nouns present in the input text. The system may convert the questions into another multi-dimensional data model and may then compare the two data models in program memory to derive the answers to the posed questions. The system may then automatically detect unknown words and optionally look them up in digital information sources, such as online dictionaries and encyclopedias, to fill in the gaps in knowledge to answer the questions with expert-like reliability.

The present invention relates to a sparse representation-based single-image rain elimination method. The method includes the following steps that: the low-frequency part and high-frequency part of an original image are obtained; non-overlapping partitioning is performed on the high-frequency part; online dictionary learning is carried out, so that a corresponding dictionary DHF composed of a plurality of sub-blocks is obtained; each of the sub-blocks of the DHF are divided into two categories by using an affinity propagation clustering method, wherein one category represents the geometric component information of the high-frequency part, and the other category represents the rain component information in the high-frequency part; the color distribution and edge direction of each sub-block are extracted, and each of the sub-blocks of the formed rain dictionary of the high-frequency part are classified again; a rain component in the high-frequency part is restored; the geometric component of the high-frequency part is obtained; and a rain-eliminated image can be obtained. The method of the invention has a better rain elimination effect.

The invention discloses an image fusion method based on guiding filter and online dictionary learning. The method comprises the following steps: S1. Obtaining all source images respectively and decomposing the source images based on guiding filter, decomposing each source image to obtain low frequency and high frequency components; S2, the low-frequency components of the decomposed source images are fused in an integrated manner, The fused low frequency components are obtained, and the high frequency components of the decomposed source images are fused by using the fusion method based on sparse representation, and the fused high frequency components are obtained. When the fusion method based on sparse representation is used, the online robust dictionary learning method is used to obtain the dictionary. S3. The obtained fused low-frequency component and the fused high-frequency component are combined to obtain a final fused image. The invention has the advantages of simple realization method, good real-time performance and effect of multi-image fusion, high fusion efficiency, easy realization and the like.

Method and apparatus for automatically predicting lexical sememes using a lexical dictionary, comprising inputting a word, retrieving the word's semantic definition and sememes corresponding to the word from an online dictionary, setting each of the retrieved sememes as a candidate sememe, inputting the word's semantic definition and candidate sememe, and estimating the probability that the candidate sememe can be inferred from the word's semantic definition.

The invention discloses a real-time translation method and apparatus. The method comprises the following steps: step 1, obtaining a text input by a user and a corresponding pinyin string in real time; step 2, segmenting the pinyin string according to all possibilities by taking pinyin of a single Chinese character as a unit, taking candidate Chinese characters corresponding to the pinyin as nodes, forming a grid structure by connecting lines of the candidate Chinese characters, scoring a Chinese character string composed of any segmentation path in the grid by using a language model to obtain candidate results, and selecting an optimal Chinese character string from the candidate results; and step 3, calling a translation algorithm to translate the optimal Chinese character string, and outputting a translation result. Through the real-time translation method and apparatus, the technical problem that the user needs to occasionally perform switching between the text and an online dictionary during real-time translation of the input text is solved.

A system and method predictively generates words based on a user input, according to a frequency of lookup of each of the generated words. The system and method also allows for a user to add predictively generated words to a word list that assists in the facilitation of word and vocabulary comprehension for a user. Words in the online dictionary are grouped in word families where a user can navigate between different forms of a root word.

The invention discloses a remote sensing image dictionary learning classification method based on the utilization of the spatial relationship. The method comprises the following steps: firstly regarding a p-neighborhood set of each pixel as a training unit, and carrying out the spatial relationship information extraction and expression of each training unit; then introducing local neighbor space relationship information to construct a dictionary learning model based on local neighbor region joint representation, and training by using features extracted from each training unit by means of an online dictionary updating mechanism to obtain an optimal dictionary set; and finally, performing sparse coding on the p-neighborhood set associated with each pixel based on the optimal dictionary obtained by training, and training a linear support vector machine model to classify unlabeled pixels based on the obtained sparse discrimination coefficient features and labeling information. According tothe invention, joint sparse representation is carried out on local neighbor area pixels of the remote sensing image, so that the constructed dictionary learning model can fully perceive potential spatial relationship information in the image to achieve the purpose of accurately identifying a ground object target.

The invention provides a personal document searching method based on synonyms. The personal document searching method comprises the following steps of: carrying out word segmentation on document names with concentrated data by a conventional tokenizer, carrying out synonym matching by using an online dictionary website after word segmentation, and gathering synonym and near-synonym information of words returned by the online dictionary website by using a webpage gathering technology and storing the synonym and near-synonym information of the words in a database; and then inquiring in combination of the corresponding synonyms based on input keywords by using a character string matching method. According to the personal document searching method, personal desktop files and the synonyms are combined; the solution is put forward specific to the query problem of the files in personnel data management; the personal document searching method has the characteristics of being concise and practical and easy in realization; and simultaneously, according to the personal document searching method, the file searching time of users can be greatly reduced, the users can inquire the personal desktop files conveniently, and the recall rate and the accuracy rate of the files are improved.

The invention discloses a method for identifying counterfeit goods data based on an online dictionary learning data matching model, the technical proposal of the invention is that the hardware equipment is installed and debugged at first, networking and learning from images of counterfeit data matching models are performed, the data matching model of online dictionary learning is established, theversion of the goods to be inspected, Batch, packing and time patterns are placed beneath the scanning device; collection of image information and similarity matching are carried out through online dictionary learning data matching model, so that that final similarity is obtained, a threshold is set, and the final similarity is compared with the threshold. As the final similarity is greater than the threshold value, it is judged that the identify goods are authentic, when the final similarity is less than the threshold value, it is judged that the goods are counterfeit, and the information ofthe genuine goods and the counterfeit goods is saved for self-adjustment and self-proofreading, which effectively improves the accuracy of the identification judgment, saves the running time of the whole algorithm, and greatly improves the efficiency and success rate of the identification.

The invention discloses a pushing method for updates of an online dictionary. In the system and the method, by the technical means that a dictionary server provides client side subscription or contrary subscription of vocabulary information items corresponding to the queried vocabularies when the client side queries the vocabularies through the online dictionary, and pushes the updates of the vocabulary information items of the corresponding queried vocabularies to the client side, the technical effect of reducing a cross comparison process for consulting the updated vocabulary information items by the client side can be realized.

The invention discloses a spatial big data dictionary learning method based on particle swarm optimization. The spatial big data dictionary learning method includes step 1, preprocessing spatial big data; step 2, learning an online dictionary learning (ODL) dictionary, and utilizing an ODL algorithm to process remotely sensed data which are currently read in and after being separated to acquire a priori dictionary; step 3, building a particle swarm optimization model; step 4, performing PSO through a particle swarm optimization algorithm to acquire a new dictionary after being optimized; step 5, adopting an algorithm stabilizing mechanism to introduce an intermediate variable in the ODL algorithm, and transmitting updating information of a sparse coefficient matrix generated by the new dictionary after PSO; step 8, judging whether data exist in a spatial large-size data set or not. The spatial big data dictionary learning method has the advantages that large-size remotely sensed data are processed effectively, accuracy in spatial big-data expression is improved under the circumstance that calculating load is not increased as much as possible, and noise contained in remotely sensed data in the process of rebuilding can be inhibited well.

The invention relates to a method and a device for voice activity detection. The method comprises the steps of extracting the signal characteristics of clean voice signals and the signal characteristics of noise mixed voice signals, carrying out dictionary training according to the signal characteristics of the clean voice signals to obtain a voice dictionary, dynamically updating predetermined noise training data according to the signal characteristics of the noise mixed voice signals, extracting the signal characteristics of the updated noise training data and carrying out online dictionary training to obtain a noise dictionary; performing sparse representation on the signal frames of a noise mixed voice signal input according to the voice dictionary and the noise dictionary, extracting a sparse coefficient in the sparse representation, and detecting the signal frames of the input noise mixed voice signal according to the sparse coefficient. The method and the device are capable of accurately recognizing the voice part and the non-voice part of a voice signal in a noise environment, and the performance of the voice activity detection in the varying noise environment is improved.

The invention discloses a method of marking diseases in ancient murals on the basis of global dictionary features. The method includes the steps of by applying a dictionary training method to an original mural image, according to a pre-marked true value image, subjecting a disease area and a no-disease image to online dictionary learning to train a disease dictionary and a non-disease dictionary; super-pixelating the target image by means of a super-pixel method; creating Bayesian models to mark each super-pixel block. Images can be more quickly and effectively segmented by means of super-pixelating and sparse coding; the identical Bayesian models are used to segment diseases in the ancient mural images, and the sparse coding based on super-pixels helps increase algorithm operating speed by 103 times, approximating real-time segmenting.

The invention provides an online dictionary learning probability optimal power flow method under a source-charge interaction electric power market. Trainings are performed in a lot of Monte-Carlo simulation sampling samples, a result with the highest occurrence frequency is obtained, so massive repeated calculation of the direct current optimal power flows is effectively avoided. By use of a dictionary learning theory which is widely applied to the signal processing technology, a dictionary is formed according to the theory based on an acquired basic signal group and plenty of signals are characterized by linear combinations of bytes in the dictionary. The objective of the invention is to pay attention to the fact how to acquire conditional probability distribution of system state quantities (such as line power flows, generator dispatching decisions, node boundary electricity price, and blocking states) in the future moment when prediction sequence samples of system parameter random variables such as new energy power generation and node load injection power are known. Compared with a traditional Monte-Carlo simulation-based probability optimal power flow method, online calculationrequirements can be met.

The invention relates to a system for enlarging local electronic dictionary by inquiring online dictionary which comprises: online dictionary inquiry interface for receiving website information and generating acquiring commands; data processing module for linking the website and making the webpage display in the inquiry interface to get webpage content and one more inquiry data; enlarging database for storing the webpage content and inquired data; displaying inquired data in the online dictionary inquiring interface.

The invention discloses a structured functional knowledge completion method for implicit conflict detection. The method comprises the following steps: firstly, obtaining paraphrases in an online dictionary according to a given group of implicit attribute words; for each implicit attribute word Ii belongs to I, obtaining a part-of-speech label of a paraphrasing sentence in the online dictionary through a lexical parser, and taking all nouns as candidate attribute words Ci of Ii; dividing all words cij belonging to Ci in the candidate attribute words into two classes, one class being attributesof implicit attribute words, the other class being non-attribute words, obtaining an accurate classification result through an iterative classification algorithm by utilizing an inter-word relationship in WordNet, and finally complementing missing attributes in the structured functional knowledge. The extracted structured functional knowledge can be used for implicit conflict judgment in the smarthome system, the automation degree of the implicit conflict detection system is improved, and the detection accuracy is greatly improved.

The invention relates to an online dictionary learning super-resolution reconstruction method based on sparse representation. The online dictionary learning super-resolution reconstruction method comprises the three parts of prior information, dictionary learning and sparse reconstruction. The dictionary training part adopts online dictionary learning, so that not only is external image library information effectively utilized, but also the image information is added to update the dictionary. Besides, on the basis of sparse prior, a local autoregression model and non-local self-similarity areadded at the same time to serve as prior information, a non-local regularized super-resolution reconstruction model is established, and various structural features of the image are reconstructed. In the sparse reconstruction stage, a sparse coefficient is determined by using multi-scale self-similarity sparse representation, a non-local constraint item is constructed according to a corresponding relation between different scale similar blocks, and additional information of a multi-scale self-similarity structure is introduced into a reconstruction process in an image reconstruction model; Themethod not only can reduce the dependence of the test image on the training image set, but also can overcome the local distortion or fuzziness of the image block in the reconstruction process, therebyfurther improving the quality of the reconstructed image.