30 results about "Labeling Problem" patented technology

The invention relates to the field of bioinformatics and data mining, in particular to a hierarchical multi-label classification method for protein function prediction, and aims at solving the data set imbalance problem, multi-label problem and hierarchical constraint problem when the conventional classification methods are used for predicting protein functions. The method comprises the following steps of: 1, a training stage: training a data set of each node in a class label hierarchical structure by adopting an SVM classifier in the training stage so as to obtain a group of basic classifiers; and 2, a prediction stage: firstly obtaining preliminary results of unknown samples by using the group of basic classifiers obtained in the training stage in the prediction stage, and processing the results by adopting a TPR algorithm with a weight so as to obtain a final result which satisfies a hierarchical constraint condition and realize the prediction of the protein functions. The hierarchical multi-label classification method for protein function prediction is applied to the field of bioinformatics and data mining.

The invention provides a remote supervision relation extraction method combined with background knowledge. The method comprises the following steps: for each packet in a training data set, obtaining avector representation of each sentence in the packet through a sentence encoder; constructing a sentence-level attention mechanism by utilizing entity representation in the knowledge base, distributing attention weight for each sentence, and obtaining a unique semantic vector of each packet based on the attention weight of each sentence; carrying out relation retrieval on the semantic vectors ofthe packets by utilizing the relation vectors in the knowledge base; and training the whole relation extractor according to the unified objective function. By applying the method and the device, the error labeling problem in remote supervision can be relieved, and the relationship prediction accuracy is improved.

The invention relates to a method and a system for extracting entity relations from texts, a storage medium and an electronic device. The method comprises the following steps: acquiring entity triplerelation set, entity and entity attribute set, and concept set; Training a triple relation set of a sentence of a text set and two entities identified in the sentence; Obtaining a sentence comprisinga training text set, two entities identified in the sentence, concepts corresponding to the two entities and a relation set of the two entities respectively, inputting sentence vectors into an entityrelation extraction model and training; Each sentence contains two entities, concepts corresponding to the two entities, and a set of relationships between the two entities. The entity relationship extraction method of the invention extracts the relationship between entities by using the semantic context information in the text, and solves the error labeling problem existing in the remote monitoring process.

The invention discloses a Google user map text labeling method based on an SVG. The method includes the steps that an SVG object with a path text is added to a self-defining overlaying layer of a Google map, and when the overlaying layer is drawn, a current map projection is acquired through a getProjection method; a labeled path represented by longitudes and latitudes is converted into a pixel path under the current projection; the length of the pixel path is calculated and compared with the length of a labeled text, if the pixel path is too short, the SVG object is not displayed; the starting point position of the labeled text on the pixel path is determined so that it can be guaranteed that the text is located in the middle of the path; the space, actually occupied by the labeled text, of the pixel path is determined according to the length of the text; the minimum coordinate value of the labeled text on the pixel path is determined through comparison and serves as a top left corner coordinate of the SVG object; the pixel path of the labeled text relative to the SVG top left corner is calculated; the text pixel path expressed by coordinate strings is converted into a path of path elements in the SVG, and d attributes of the path are replaced. The text labeling problem is solved, and a new way is found for Google user map text labeling.

The invention discloses a desktop conference system and a control method thereof. The desktop conference system comprises a conference desk. A conference terminal is arranged on each seat of the conference desk. Each conference terminal comprises a terminal processor and a touch display screen, a recording module and a USB interface module which are connected with the terminal processor, wherein the conference terminal is connected with a central control unit, the central control unit is provided with a central processor, and the central processor is connected with a storage. An electronic speech draft of a keynote speaker, a speech recording file of the keynote speaker, labeling positions made by other conferees in the electronic speech draft, the corresponding labeling problem content, corresponding question asking and recording files, question asking and recording files and answering content of a corresponding main conference terminal, statement recording files and statement contentof other conferees are saved together to generate the meeting summary.

The invention relates to a Chinese named entity recognition method based on reading understanding, and belongs to the technical field of natural language processing. The method comprises the steps ofperforming word segmentation processing on document-level corpora to obtain a document-level sequence; obtaining a triple consisting of a retrieval tag problem, a document-level sequence entity and adocument-level sequence; taking the retrieval tag problem and the document-level sequence in the triple as input, and generating hidden output fused into document-level context information through a BERT coding layer; passing hidden output fused with the document-level context information through a convolutional neural network, obtaining semantic features of a long-distance context, capturing semantic information of the whole document context, and compressing the semantic information into feature mapping; and predicting all entities in the document through the prediction layer by utilizing semantic information of the context of the whole document, predicting start indexes and end indexes of the entities, and splicing the start indexes and the end indexes to generate named entities. According to the invention, entity identification in the document can be carried out, and the identification effect is good.

The invention relates to a labeling method of a single-side point cloud model, in particular to a method of dividing a point cloud model into scenes, constructing a lattice-division model based on anoctree, roughly labeling each lattice-division model, and fine labeling each lattice-division model. The invention relates to a labeling method of a single-side point cloud model, which uses an improved region growth algorithm to label the point cloud model, can clearly divide the mesh boundary, and simultaneously solves the ambiguous labeling problem in the existing pixel level labeling method.

A method of labeling pixels in an image is described where the pixel label is selected from a set of three or more labels. The pixel labeling problem is reduced to a sequence of binary optimizations by representing the label value for each pixel as a binary word and then optimizing the value of each bit within the word, starting with the most significant bit. Data which has been learned from one or more training images is used in the optimization to provide information about the less significant bits within the word.

The invention relates to the field of artificial intelligence, in particular to a text labeling method and device, electronic equipment and a storage medium, wherein the method comprises the steps: obtaining a to-be-labeled text and an actual language of the to-be-labeled text; obtaining a trained text labeling model corresponding to the actual language and the target language; carrying out semantic space conversion processing on the actual semantic features of the to-be-labeled text through the trained text labeling model, and acquiring target semantic features of the to-be-labeled text in a target language; performing clustering processing on the target semantic features through a trained text labeling model to obtain a clustering result of the to-be-labeled text; performing classification processing on the clustering result through a trained text labeling model to obtain text type information of the to-be-labeled text; and according to the text type information, performing text type labeling on the to-be-labeled text. According to the method and the device, the text type of any language text can be automatically labeled on the basis of the text in the target language with a large number of labeled samples, so that the cross-language text labeling problem is solved.

The invention discloses a semi-supervised industrial product flaw detection method and system based on positive sample learning. The method comprises the following steps: training an image restoration network and a flaw segmentation prediction network through positive sample images; and inputting an image containing a flaw to be detected into the image restoration network to obtain a restored certified product image, calculating an absolute value of a difference value between the two images, splicing the three images to obtain a detection tensor, generating a segmentation mask binary image according to the detection tensor through the segmentation prediction network, and obtaining a flaw region. According to the method, a semi-supervised deep learning method is used, defect position data of a pixel level does not need to be labeled in advance, the labeling problem in defect segmentation is solved, and full-automatic training learning, defect segmentation and defect classification can be realized only by using part of certified product images in production. And pixels at various types of abnormal flaw positions can be segmented.

The invention discloses an unstructured test question data labeling method and device and a storage medium. The method comprises the steps: extracting multiple pieces of unlabeled data from a test question data set according to a self-service sampling method to be preprocessed; inputting the plurality of pieces of pre-processed unlabeled data into a deep learning network, and inputting labeled data into the deep learning network for correction; respectively inputting an output result of the deep learning network into at least two different types of base classifiers for ensemble learning, wherein each base classifier comprises a plurality of weak learners and a strong learner of the same type; and constructing a transition probability matrix for the output data in all the base classifiers,solving the transition probability matrix, and generating a labeling result. According to the method, the labeling accuracy is improved, the labeling problem of test questions, test papers and other unstructured data is effectively solved, on the basis, the automatic storage problem of unstructured texts can be solved, and a large amount of manual labor can be saved.

The invention provides a bimodal iterative denoising anomaly detection method and terminal based on a video weak mark, and the method comprises the steps: enabling the weak mark to serve as the noiseof an accurate label, and respectively carrying out the label denoising from an image control and a feature space; learning characteristics of normal and abnormal videos from an image space by using an auto-encoder; learning features of the video clip at different times by using a graph convolution model; and alternately updating the classifier and the de-noiser by utilizing iteration. According to the method, the weak marking problem of the video is fully considered, the difficulty of marking the data is overcome by utilizing a denoising model method, and the method has very strong robustness, can well solve the problem of marking of the video and has universal applicability in the research field that the data are difficult to collect in abnormal detection.

The invention discloses a short video automatic labeling method based on feature and multi-label enhanced representation, which comprises the following steps: reconstructing an original feature matrixby using a dictionary mapping matrix, a product of public low-rank representation and a sparse error matrix to form a multi-view low-rank representation item; clustering an overall data set to obtainall data sets and potential label correlation information in different clusters to form global and local label correlation learning items; taking the common low-rank representation as a prediction label, subtracting the prediction label from a real label to obtain a labeling error, and minimizing the labeling error to form a minimized labeling error term; and weighting the multi-view low-rank representation item, the global and local label correlation learning item and the minimized labeling error item to obtain a total target function, optimizing the total target function by using an alternating direction multiplier method, introducing a Lagrange multiplier, and sequentially iteratively updating each matrix variable until the value of the target function converges to obtain a final labeling result. According to the method, the accuracy in the short video multi-label labeling problem is improved.

The invention discloses a remote supervision relation extraction method and system based on relation hierarchy interaction, and the method comprises the steps: fusing three types of inputs: word embedding, relative position embedding and head and tail entity embedding through an information processing mechanism, and obtaining word embedding representation; coding the word embedding representation through neural network coding, and obtaining sentence representation; establishing a relationship hierarchical interaction structure, and obtaining a relationship-enhanced sentence representation; eliminating mistakenly labeled sentence instances, and obtaining sentence packet representation; and constructing a classifier through a multi-layer perceptron and a softmax activation function, obtaining a probability score of the sentence packet for a relation category, and performing relation extraction according to the probability score. According to the method, for the error tag problem and the long-tail distribution problem of the remote supervision relationship, the hierarchical structure of the relationship in a knowledge base is utilized to model the interaction relationship between the relationship hierarchies, more valuable clues are provided for a relationship extraction classification task, and the performance of a relationship extraction model is improved.

The invention discloses a video scene detection labeling method and system, and the method comprises the steps: obtaining the modal features of a video, an audio and a text through a pre-training model according to a modal information source embedded by the input video, the audio and the text, carrying out the alignment and fusion of the obtained modal features of the video, the audio and the text, and forming a window basic cross-modal representation, according to the multi-temporal attention and the difference between the adjacent windows, the basic cross-modal representation of the windows is evolved into self-adaptive context sensing representation, the scene is detected according to the obtained self-adaptive context sensing representation, and the attributes of the windows are determined through a window attribute classifier; obtaining an accurate position of a scene boundary in the window through a position offset regression device; and based on the obtained scene boundaries, specifying a plurality of labels for each scene to realize scene labeling, attributing scene detection into window attribute classification and position offset regression, and solving the multi-label labeling problem through integrated learning of two-stage classifiers. The problems of error propagation and huge calculation cost are solved through a unified network of cross-modal clues; scene detection is attributed to window attribute classification and position offset regression, and the multi-label labeling problem is solved through ensemble learning of two-stage classifiers.

The invention discloses a multi-label character relationship automatic labeling method based on event remote supervision, which includes the following steps: collecting events that affect the character relationship; making a corresponding event labeling template; building an event template knowledge base; and performing data preprocessing; The preprocessed sentences use the event labeling template to mark events; carry out character relationship labeling; character relationship labeling results; calculate the credibility between "event" and "sentence"; calculate the sentence score; set a threshold, the Sentences with a sentence score below the threshold are discarded; the final character relationship annotation is obtained. The present invention matches the event template knowledge base to obtain the events that affect the relationship between characters, and then automatically deduces the multi-label relationship of characters according to multiple events, which can solve the multi-label problem of character relationship, can significantly improve the accuracy of multi-label character relationship labeling, and has more advantages. Excellent mobility.

The invention discloses an inspiration material intelligent question answering system and method, and the system comprises a knowledge base module which stores a plurality of different types of inspiration materials, and pastes a corresponding label on each material; an question library module which comprises a plurality of standard questions, and a mapping relation is established between each standard question and the corresponding inspiration material; an input module which is used for acquiring input information; a selection module; the selection module is used for selecting a creation period and extracting different styles of inspiration materials according to the creation period. A retrieval module; and the retrieval module retrieves the inspiration materials in the knowledge base module according to the input information and the creation period and is used for acquiring the required inspiration materials. According to the method and the system, the knowledge graph for the inspiration materials is constructed, related materials in the knowledge graph are retrieved according to problems of designers, and the innovation efficiency of the designers can be improved through retrieval based on the knowledge graph.

The disclosure provides an approach for image segmentation from an uncalibrated camera array. In one aspect, a segmentation application computes a pseudo depth map for each frame of a video sequence recorded with a camera array based on dense correspondences between cameras in the array. The segmentation application then fuses such pseudo depth maps computed for satellite cameras of the camera array to obtain a pseudo depth map at a central camera. Further, the segmentation application interpolates virtual green screen positions for an entire frame based on user input which provides control points and pseudo depth thresholds at the control points. The segmentation application then computes an initial segmentation based on a thresholding using the virtual green screen positions, and refines the initial segmentation by solving a binary labeling problem in a Markov random field to better align the segmentation with image edges and provide temporal coherency for the segmentation.

The embodiment of the invention provides a trademark labeling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a plurality of preset trademark data sets, carrying out the training of a first labeling model, carrying out the pre-labeling of newly-added trademark data, and obtaining a saturation labeling result, and training the first labeling model according to a saturation labeling result to obtain a second labeling model, and finally labeling the to-be-detected image based on the second labeling model. Therefore, the labeling problem caused by inconsistent cognition of the trademarks is avoided, the cognition of the trademarks is more uniform and normative, the cognition and recognition range of the second labeling model for each trademark is expanded, the category and style covered by trademark detection are improved, and the trademark labeling range is expanded; the recall rate of the second identification model can be improved; the second recognition model is wider in cognition and recognition range and high in reusability, can be flexibly transplanted to other trademark labeling scenes, and is high in universality.

The invention relates to a resource allocation method and device for a labeling problem and a readable storage medium. The resource allocation method for the annotation problem comprises the steps ofobtaining a plurality of annotation problems; and generating and outputting an allocation result according to the expected reports respectively obtained by inputting the resources into the annotationproblems. And in the data labeling scene, inputting limited resources into the task to obtain the maximum report. And generating and outputting an allocation result according to the expected reports obtained by inputting the resources into the annotation problems respectively. Reward maximization is taken as a unique distribution reference, so that the condition that resources are tended to be input into tasks with equal probabilities when the resources are limited in a data labeling scene in the prior art is changed, and the resource distribution for the labeling problem is truly realized.

The invention discloses a deep learning-based marking method for patient problem parts, comprising the following steps: collecting a three-dimensional depth image, analyzing the three-dimensional depth image, and establishing a sample database; marking the three-dimensional depth image in the database; constructing and describing the patient's problem Dimensional features of the site; training a binary classification model; using the problem site detection model to mark the problem site of the patient in real time, which solves the technical problem of the risk of incorrectly identifying the surgical site in the prior art.

The invention discloses a Google user map text labeling method based on an SVG. The method includes the steps that an SVG object with a path text is added to a self-defining overlaying layer of a Google map, and when the overlaying layer is drawn, a current map projection is acquired through a getProjection method; a labeled path represented by longitudes and latitudes is converted into a pixel path under the current projection; the length of the pixel path is calculated and compared with the length of a labeled text, if the pixel path is too short, the SVG object is not displayed; the starting point position of the labeled text on the pixel path is determined so that it can be guaranteed that the text is located in the middle of the path; the space, actually occupied by the labeled text, of the pixel path is determined according to the length of the text; the minimum coordinate value of the labeled text on the pixel path is determined through comparison and serves as a top left corner coordinate of the SVG object; the pixel path of the labeled text relative to the SVG top left corner is calculated; the text pixel path expressed by coordinate strings is converted into a path of path elements in the SVG, and d attributes of the path are replaced. The text labeling problem is solved, and a new way is found for Google user map text labeling.

The invention discloses a data stream monitoring method and device, a storage medium and equipment, which can be applied to the field of Internet of Things, and the method comprises the following steps: after receiving a query request sent by a user, analyzing the query request to obtain a problem data text; obtaining a state label of the problem data text from a pre-constructed data table, wherein the state label comprises a system number of the problem system and a change type of the problem data; the change type is used for indicating a change operation executed by the problem system on the problem data; acquiring a transmission path of the problem data from a pre-constructed data table relation graph; and displaying the state label and the transmission path to a user through a preset interface. According to the method, based on the state label of the problem data text and the transmission path of the problem data, a user can be effectively helped to locate the source of the problem data, namely search the system number of the problem system, the user does not need to traverse project systems one by one to search the source of the problem data, and the search time of the problem data is effectively shortened.

The present invention provides an efficient hardware guided filtering method for use in solving a multi-label problem. The method includes the following steps: inputting an input guidance of a multi-label image; defining an efficient hardware guided filtering (HGF) model; calculating a vector by a customized matrix inversion operation; inputting guidance through a mapping program for adding up result of each channel to form a polynomial guidance, and introducing nonlinearity into the linear model; and obtaining a filtering result in an efficient hardware mode by element-wise calculation and box filtering.

The invention discloses a multi-label character relationship automatic labeling method based on event remote supervision. The method comprises the following steps: collecting events influencing character relationships; making a corresponding event labeling template; constructing an event template knowledge base; carrying out data preprocessing; performing event labeling on the preprocessed sentences by utilizing an event labeling template; carrying out character relationship labeling; performing character relationship labeling to obtain a result; calculating the credibility between the 'event 'and the 'sentence'; calculating sentence scores; setting a threshold value, and discarding the sentences with the sentence scores lower than the threshold value; and obtaining a final character relationship label. According to the method, the events influencing the character relationship are obtained through event template knowledge base matching, then the character multi-label relationship is automatically reasoned according to the multiple events, the character relationship multi-label problem can be solved, the accuracy of multi-label character relationship labeling can be remarkably improved, and more excellent mobility is achieved.