306 results about "Stochastic field" patented technology

A composite language model may include a composite word predictor. The composite word predictor may include a first language model and a second language model that are combined according to a directed Markov random field. The composite word predictor can predict a next word based upon a first set of contexts and a second set of contexts. The first language model may include a first word predictor that is dependent upon the first set of contexts. The second language model may include a second word predictor that is dependent upon the second set of contexts. Composite model parameters can be determined by multiple iterations of a convergent N-best list approximate Expectation-Maximization algorithm and a follow-up Expectation-Maximization algorithm applied in sequence, wherein the convergent N-best list approximate Expectation-Maximization algorithm and the follow-up Expectation-Maximization algorithm extracts the first set of contexts and the second set of contexts from a training corpus.

The invention provides an image semantic division method based on a depth full convolution network and a condition random field. The image semantic division method comprises the following steps: establishing a depth full convolution semantic division network model; carrying out structured prediction based on a pixel label of a full connection condition random field, and carrying out model training, parameter learning and image semantic division. According to the image semantic division method provided by the invention, expansion convolution and a spatial pyramid pooling module are introduced into the depth full convolution network, and a label predication pattern output by the depth full convolution network is further revised by utilizing the condition random field; the expansion convolution is used for enlarging a receptive field and ensures that the resolution ratio of a feature pattern is not changed; the spatial pyramid pooling module is used for extracting contextual features of different scale regions from a convolution local feature pattern, and a mutual relation between different objects and connection between the objects and features of regions with different scales are provided for the label predication; the full connection condition random field is used for further optimizing the pixel label according to feature similarity of pixel strength and positions, so that a semantic division pattern with a high resolution ratio, an accurate boundary and good space continuity is generated.

The invention discloses a named entities recognition method based on bidirectional LSTM and CRF. The named entities recognition method based on the bidirectional LSTM and CRF is improved and optimizedbased on the traditional named entities recognition algorithm in the prior art. The named entities recognition method based on the bidirectional LSTM and CRF comprises the following steps: (1) preprocessing a text, extracting phrase information and character information of the text; (2) coding the text character information by means of the bidirectional LSTM neural network to convert the text character information into character vectors; (3) using the glove model to code the text phrase information into word vectors; (4) combining the character vectors and the word vectors into a context information vector and putting the context information vector into the bidirectional LSTM neural network; and (5) decoding the output of the bidirectional LSTM with a linear chain condition random field to obtain a text annotation entity. The invention uses a deep neural network to extract text features and decodes the textual features with the condition random field, therefore, the text feature information can be effectively extracted and good effects can be achieved in the entity recognition tasks of different languages.

A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.

A system for extracting information from text, the system including parsing functionality operative to parse a text using a grammar, the parsing functionality including named entity recognition functionality operative to recognize named entities and recognition probabilities associated therewith and relationship extraction functionality operative to utilize the named entities and the probabilities to determine relationships between the named entities, and storage functionality operative to store outputs of the parsing functionality in a database.

The invention discloses a deep learning-based weakly supervised salient object detection method and system. The method comprises the steps of generating salient images of all training images by utilizing an unsupervised saliency detection method; by taking the salient images and corresponding image-level type labels as noisy supervision information of initial iteration, training a multi-task fullconvolutional neural network, and after the training process is converged, generating a new type activation image and a salient object prediction image; adjusting the type activation image and the salient object prediction image by utilizing a conditional random field model; updating saliency labeling information for next iteration by utilizing a label updating policy; performing the training process by multi-time iteration until a stop condition is met; and performing general training on a data set comprising unknown types of images to obtain a final model. According to the detection method and system, noise information is automatically eliminated in an optimization process, and a good prediction effect can be achieved by only using image-level labeling information, so that a complex andlong-time pixel-level manual labeling process is avoided.

The invention discloses a geographical science domain named entity recognition method, which is used for recognizing geographical science core term entities and geographical location entities. The method mainly comprises three steps of (1) establishing a geographical science domain dictionary, and using a new word discovery algorithm to identify new words in the geographical science domain in an unsupervised way; (2) training and testing based on a conditional random field (CRF) model and a multichannel convolutional neural network (MCCNN) model; (3) carrying out error correcting and fusion on entities recognized by the models by using a rule-based method. According to the geographical science domain named entity recognition method, the new words of the domain are identified as the dictionary in an unsupervised way by using the new word discovery algorithm, so that the work distinguishing effect is improved. The semantic vectors of the words are learnt from large-scale unmarked data in an unsupervised way, and basic characteristics of the words are synthesized and are taken as the input characteristics of the MCCNN model, so that manual selection and construction of the characteristics are avoided. The predicting results of the two models are fused by means of a custom rule, so that the problem of error marking in a recognition process can be corrected.

The invention relates to an industry comment data fine grain sentiment analysis method. The industry comment data fine grain sentiment analysis method is applied to Internet data analysis and comprises obtaining comment data of e-commerce industry goods and preprocessing the comment data; establishing initial industry sentiment word libraries and computing distribution of words under different sentiment polarities through 1-gram and 2-gram; performing Chinese word segmentation on the comment data; based on the sentiment word libraries established through the 1-gram and the 2-gram, utilizing combined sentiment models to perform word modeling to obtain the probability distribution of the words which belong to different topics under different sentiment distributions; utilizing context information to re-determine the sentiment alignment of sentiment words in sentences; performing named entity identification and extracting comment characteristics through conditional random fields to compute the sentiment alignment of comment words of the comment characteristics. The industry comment data fine grain sentiment analysis method computes the sentiment of the comment words through the two dimensions of topic and sentiment to achieve fine grain sentiment analysis on the industry comment data, thereby achieving high precision and interpretability of analysis results.

An Active Random Field is presented, in which a Markov Random Field (MRF) or a Conditional Random Field (CRF) is trained together with a fast inference algorithm using pairs of input and desired output and a benchmark error measure.

The invention discloses a text mining method based on online medical question and answer information. The text mining method comprises the following steps of: extracting disease question and answer information from an obtained original webpage by adopting a network data extracting mode based on DOM and a webpage template; carrying out medical named entity identification in the extracted disease question and answer information by virtue of characteristics of a conditional random field model; and mining a medical entity relationship by virtue of the medical named entity identification. The method can be used for effectively obtaining a potential association relationship among various entities. The method is suitable for mining work of all disease classes, and has certain expandability.

The invention discloses a Chinese domain term recognition method based on mutual information and a conditional random field model. The Chinese domain term recognition method includes the following steps: (1) gathering domain text corpus and marking all the punctuations, spaces, numbers, ASSCII (American Standard Code for Information Interchange) characters and characters except Chinese characters in the corpus; (2) setting character strings and computing the mutual information values of the character strings, (3) computing the left comentropy and the right comentropy of every character string, (4) defining character string evaluation function, setting evaluation function threshold, computing the evaluation function values of every character string, determining that every character string is a word, comparing in sequence the evaluation function value of the former character with the evaluation function value of the latter character in the character string and segmenting character meaning character strings one by one, (5) utilizing conditional random fields to train a conditional random field model and recognizing domain terms with the conditional random field model. When the Chinese domain term recognition method is used to recognize terms, the data sparsity of legitimate terms is overcome, the amount of calculation of conditional random fields is reduced, and the accuracy of the Chinese domain term recognition is improved.

The present invention discloses an improved full-convolutional neural network-based power transmission line insulator state recognition method. The method includes the following steps that: S1, the picture of a power transmission line insulator is collected through an unmanned aerial vehicle; S2, classification regression and position regression are performed on the image through a target detection network Faster R-CNN so as to intercept a separate insulator picture; S3, semantic segmentation is performed on the insulator picture through using a full-convolutional neural network; S4, fine segmentation is performed through a full-connection condition random field; S5, noise points in the image are filtered by using a morphological operation method; and S6, the insulator is classified through a deep learning classification network, and the status of the insulator is determined. According to the method of the invention, training and parameter adjustment and optimization are performed on labeled insulator pictures; the status of the power transmission line insulator can be effectively identified; the subjective influence of manual setting of thresholds and the randomness of manual extraction of features in traditional insulator status recognition can be avoided; the efficiency of line inspection can be significantly improved; and the difficulty of the line inspection can be decreased.

The invention provides an image salient target detection method combined with deep learning. The method is based on an improved RFCN deep convolution neural network of cross-level feature fusion, anda network model comprises two parts of basic feature extraction and cross-level feature fusion. The method comprises: firstly, using an improved deep convolution network model to extract features of an input image, and using a cross-level fusion framework for feature fusion, to generate a high-level semantic feature preliminary saliency map; then, fusing the preliminary saliency map with image bottom-layer features to perform saliency propagation and obtain structure information; finally, using a conditional random field (CRF) to optimize a saliency propagation result to obtain a final saliency map. In a PR curve graph obtain by the method, F value and MAE effect are better than those obtained by other nine algorithms. The method can improve integrity of salient target detection, and has characteristics of less background noise and high algorithm robustness.

The invention discloses a multi-view texture mapping method. The method can be used for carrying out high-realistic texture mapping on a three-dimensional model by an image sequence shot in multiple angles. The method comprises the steps of firstly converting multi-view texture mapping into a Markov random field problem, and obtaining an optimal texture image corresponding relation of each patch by an energy optimization method; then simplifying mapped texture data, and restoring invalid textures in part of invisible regions; finally eliminating the color difference of spliced boundaries of textures by a gradient merge method, and obtaining a seamless texture mapping effect. Compared with the conventional method, the method disclosed by the invention has obvious advantages in the two aspects of mapping of complicated sheltered textures and merging of large texture data in the model; high-quality texture mapping is still generated in a complicated scene; examples in a series of complicated scenes show the effectiveness and the robustness of the method.

Enhancement of contours in images that are noisy or otherwise corrupted is important in medical imaging, scanning for weapons detection, and many other fields. Here, the Curve Indicator Random Field (CIRF) is used as a model of uncorrupted images of contours for constructing linear, quadratic and cubic Volterra filters involving a number of adjustable parameters.

The invention discloses an efficient CNN-CRF network-based retina image segmentation method. According to the method, aiming at an image space information constraint problem, a full convolutional neural network and a conditional random field are combined; and aiming at a retina image blood vessel segmentation problem, a whole image is designed and an end-to-end deep learning and segmentation model is trained. Through predicting image pixels through the full convolutional neural network and segmenting semantic meanings of the conditional random field, a retina blood vessel image segmentation result is finally obtained. Compared with a pixel-by-pixel segmentation method, the method is capable of segmenting a complete image through a forward operation, so that the processing effect of the method is higher than that of the current technological level; and the method can be widely applied to the retina diagnosis fields of diabetes, hypertension and glaucoma, and provide powerful theoretical and technological support for the pathological diagnosis of retina images.

The present invention is an automated image analysis framework for cervical cancerous lesion detection. The present invention uses domain-specific diagnostic features in a probabilistic manner using conditional random fields. In addition, the present invention discloses a novel window-based performance assessment scheme for two-dimensional image analysis, which addresses the intrinsic problem of image misalignment. As a domain-specific anatomical feature, image regions corresponding to different tissue types are extracted from cervical images taken before and after the application of acetic acid during a clinical exam. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the conditional random field model. The output provides information about both the tissue severity and the location of cancerous tissue in an image.

An image segmentation method based on a hierarchical higher order conditional random field model is provided, comprising: firstly, extracting a multi-class texture feature for a target image, and constructing a one-variable potential function and a pairing potential function of a pixel level; then, acquiring super pixel fragments of different granularities by using a unsupervised segmentation algorithm; designing a one-variable potential function and a pairing potential function of a super pixel level corresponding to each granularity layer; constructing a hierarchical higher order conditional random field model; learning a parameter of the hierarchical higher order conditional random field model in a supervision manner by using a manual marked sample; and finally, acquiring a final segmentation marking result for a to-be-tested image by means of model reasoning. The hierarchical higher order conditional random field model used in the present invention fuses multi-feature texture information and multi-layer super pixel segmentation information of an image, and can effectively improve boundary segmentation accuracy of a multi-target object in the image.

The invention relates to a legal document named entity identification method and apparatus, and a computer device. The method comprises the steps of obtaining a legal document to be identified; inputting the legal document to be identified into the deep neural network model for identification to obtain an identification result; wherein the deep neural network model is obtained by training a language model through a plurality of legal document data with labels, a bidirectional recurrent neural network and a conditional random place; wherein the language model is obtained by training a Google Bert model through a plurality of corpora. According to the invention, the deep neural network model is adopted to carry out entity identification; extracting a character vector from a Chinese charactersequence of the legal document to be identified by adopting a language model obtained by training a Google Bert model; and inputting the character vectors into a bidirectional recurrent neural network, inputting the output codes of the bidirectional recurrent neural network into a linear chain conditional random field, and obtaining a recognition result, so that the network for realizing named entity recognition is simple in structure, low in training cost and high in prediction capability.

The present invention belongs to the computer-assisted medical field, and especially relates to a brain tumor automatic segmentation method through fusion of a full convolutional neural network and a conditional random field. The objective of the invention is to solve the problem that the depth learning technology cannot ensure the continuity of a segmentation result on the appearance and the space when the brain tumor segmentation is performed in the prior art. In order to solve the problem mentioned above, the method comprises the following steps: the step 1, employing a non-uniform offset correction and luminance regularization method to process the magnetic resonance image of the brain tumor image to generate a second magnetic resonance image; and the step 2, employing the neural network fusing the full convolutional neural network and the conditional random field to perform brain tumor segmentation of the second magnetic resonance image and output the brain tumor segmentation result. The brain tumor automatic segmentation method through fusion of the full convolutional neural network and the conditional random field can perform end-to-end brain tumor segmentation slice to slice and has higher operation efficiency.

The invention relates to a method and an object detection device for analysing objects in the environment and/or scenes in the environment. The object detection device includes a data processing and/or evaluation device. In the data processing and/or evaluation device, image data (x^t) is evaluated on the basis of a Conditional Random Field (CRF) model and the CRF model provides additional object nodes (o^t_n) which take into account information from an object detector.

The invention relates to a convolutional neural network road scene classification and road segmentation method. A dual-task joint structure model based on the convolutional neural network is established.and composed of an encoder and two decoders. Feature information sharing is achieved through end-to-end training.Classification of various road scenes such as urban roads, rural roads and highwaysis completed, road drivable areas in the scenes are segmented, and the dual goals of road scene classification and road area segmentation are achieved. Based on a convolutional neural network, scene classification and road extraction in road scene perception are combined. Real-time output is obtained through an end-to-end training mode, the functions of an intelligent driving assistance system areimproved, and an effective and reliable driving assistance function is provided. A mode of combining a full convolutional network and a conditional random field is adopted for a part extracted from adrivable area in the model, a high-resolution image optimization output result can be generated, and a relatively accurate segmentation effect is achieved.

The present invention is a method of generating a model of a random field which has directionally varying continuity. First, a tentative model for the random field is specified. Second, connected strings of nodes within the model are identified. Third, a spectral simulation on each of the strings of nodes is performed to determine updated values for the random field. Finally, the tentative model is updated with the data values from the spectral simulations.

The invention discloses a plain text oriented enterprise entity classification method. The plain text oriented enterprise entity classification method comprises the steps of S1, carrying out type labeling for the enterprise entities in collected plain text data and regarding the enterprise entities being subjected to type labeling as a training set of an enterprise entity identification module; carrying out type labeling for the enterprise entities in the collected plain text data according to business nature and regarding the enterprise entities being subjected to the type labeling as a training sample set of an enterprise entity classification module; and S2, carrying out enterprise entity identification model training through a condition random field model to obtain an enterprise entity identification model; S3, carrying out semantic vectorization construction for the text data of an original training set; S4, training by regarding the data of the training set after being subjected to type labeling and semantic vectorization as training parameters to obtain an enterprise entity classification model; and S5, classifying the enterprise entity in a to-be-predicted text by utilizing the enterprise entity classification model. According to the plain text oriented enterprise entity classification method, as the obtained semantic vector serves as the feature of the entity, dependence on artificial features and external data is reduced, and the universality and robustness are guaranteed.

The embodiment of the invention provides a semantic fuzzy matching method. The method comprises the following steps of: extracting characteristics of the text identified by voice to obtain the characteristic data; carrying out named entity identification on the characteristic data by a conditional random field (CRF) to find the key semantic categories of sentences; and accurately matching the key semantic categories, performing fuzzy matching when the accurate match is failed, calculating the similarity of the key semantic categories and the key words in the dictionary, selecting the key words with largest similarity to replace the key semantic categories, and marking the categories. By the method of the embodiment, the CRF is used for marking the sequence, the key semantic categories in the inquire statement are initially marked and located; the fuzzy matching range is shortened; the similarity is calculated according to the domain dictionary; the dictionary entries with the largest similarity are used for replacing the wrong key semantic categories in the user query; the calculation amount is reduced; and the identifying speed is improved.

The invention relates to the technical field of text processing, in particular to a keyword extraction method, apparatus and device and a storage medium. The method includes: obtaining corpus text tobe extracted; inputting the to-be-extracted corpus text into a text labeling model for character type labeling processing to obtain a label corresponding to each character in the to-be-extracted corpus text, wherein the text labeling model is determined by performing supervised training based on a preset neural network model by using a training corpus text with a sample label, and the preset neural network model comprises a semantic representation model, a full connection layer connected with the semantic representation model, a conditional random field connected with the full connection layerand an output layer connected with the conditional random field; obtaining a character corresponding to a preset label in the corpus text to be extracted; and determining a keyword of the corpus textto be extracted according to the character corresponding to the preset label. According to the method, the accuracy and recall rate of keyword extraction can be improved.

The invention provides an abnormal behavior description method based on characteristics of a block mass and a track. The abnormal behavior description method comprises the following steps of utilizing a characteristic extraction method to extract color characteristics, textural characteristics and position characteristics of a scene, utilizing a K-means algorithm to cluster the characteristics to generate the block mass, and utilizing a conditional random fields (CRF) to conduct description on the block mass; and utilizing a mixed gaussian model to conduct sport target detection, extracting track characteristics of a target, combining the block mass description and the track characteristics to form a combined characteristic vector quantity, using a hidden markov model (HMM) to conduct modeling on the combined characteristic vector quantity, utilizing the built HMM to describe abnormal behaviors of the target in the scene, and enabling an abstract attached diagram to serve as a functional block diagram of the abnormal behavior description method . The abnormal behavior description method based on the characteristics of the block mass and the track not only considers influences of the scene on the abnormal behaviors, but also achieves long-time tracking and describing on the target.