103 results about "Semantic tree" patented technology

The invention provides an XACML strategy rule detecting method, belonging to the field of authorized strategy analysis in information safety. According to the XACML strategy rule, the method has a rule status definition, a rule status correlation definition and a conflict type analysis; on the basis, a strategy index based on a semantic tree is established, a concrete XACML strategy rule detection is carried out and the rule conflict and the rule redundancy are analyzed; the detection method comprises two types: a conflict detection method based on a property level operation correlation and a detection method for other typed conflicts based on the status correlation. In the redundancy analysis, the analysis determining method of the rule redundancy is given respectively in the algorithms of allowing priority, refusing priority and the first-time application dispelling. By adopting the detection method, the strategy manager can precisely locate the rules causing the conflict and the reasons for the conflict; in the redundancy analysis, according to the analysis result, the strategy structure can be optimized and the redundancy rules which has no influence on accessing the determining result can be deleted, therefore, the strategy determining efficiency is improved.

The invention provides an image marking method based on a characteristic scene, which comprises the steps of: segmenting a marked image used for learning by adopting an image segmenting algorithm, and obtaining vision description of an image region; 2, carrying out automatic semantic scene clustering on the marked image used for learning; 3, generating a characteristic scene space for each scene semantic category; 4, establishing corresponding semantic tree for each characteristic scene space; and 5, projecting an image to be marked in each characteristic scene space, determining the semantic category of the image to be marked for the fitting degree of a mixing model by adopting the projected vision characteristic and obtaining the final marking of the image through the semantic tree for the image for determining the semantic content. The image marking method fully utilizes the marked character information of a learning image, is used for carrying out automatic semantic scene clustering on the marked image used for learning, and ensures that more complete vision description is obtained under the special scene, thereby improving the reliability of automatic semantic marking through the image vision characteristic.

The invention discloses a multi-feature adaptive fusion-based image retrieval method. The method comprises the following steps of: selecting image features, namely extracting more than two image features of each image in an image library; establishing a semantic tree of each image feature of each image in the image library; performing normalization processing on all image features of the images which is input by a user and is to be retrieved; performing fusion on the scores of the retrieval results of all image features; in screened images, respectively weighting and adding the scores of the retrieval results of all image features of each image to obtain final scores of the retrieval results; and outputting the images according to an order of the final scores of the retrieval results from high to low, wherein the score weights of the retrieval results of each image feature are not fixed. Due to the adoption of the multi-feature fusion method, the retrieval accuracy is greatly improved; and due to the adoption of a dynamic weight, a traditional fixed weight is changed, and the effect of image retrieval is further improved.

The invention discloses a short text similarity calculation method based on semantics. The short text similarity calculation method comprises the following steps of: preprocessing corpus data, establishing word Embedding, constructing a word semantic tree, calculating semantic similarity between words in a short text, and calculating the semantic similarity between the short texts. On the basis of deep learning word Embedding, a hierarchical clustering method is combined to create the word semantic tree and calculate the similarity between words in the short text, on the basis, various characteristics of the short text are combined to calculate the semantic similarity between the short texts, and the defect in the prior art that the word semantic tree can not describe a semantic relationship between a fresh word and a known word is effectively solved.

The invention discloses a hierarchical semantic tree construction method and system for language understanding. The method mainly comprises the steps as follows: segmenting terms of a statement and loading a semantic knowledge base; recognizing all nodes of the statement according to an LV rule, and recognizing the level of the nodes according to semantic knowledge and term positions and collocations; generating a special node by punctuation at the end of the statement, and taking the special node as a root node of a semantic tree; merging the nodes according to generated node information, recognizing semantic side chunks of the statement, and taking a level-0 semantic side as a child node to be hung on the root node; circularly traversing all child nodes of the statement till no low-level semantic side exists, and taking the child nodes as leaf nodes to be hung on the child node. According to the hierarchical semantic tree construction method and system, under the condition that no syntactic resource exists, the semantic structure tree is obtained through semantic information and the term positions and collocations only, so that a computer can enter a deep semantic layer of a natural language, various processing of the natural language can be finished on the basis of understanding, the first step of semantic understanding of the natural language is realized, and the hierarchical semantic tree construction method and system can be applied to information retrieval, automatic abstraction, machine translation, text categorization, information filtration and the like.

The present invention discloses a natural language semantic understanding method and system. The method includes: obtaining text to be parsed; performing word segmentation and part-of-speech tagging on the text to be parsed; performing syntactic analysis on the text after word segmentation based on context-related information, and obtaining the Describe the natural word-dependent syntactic tree of each sentence in the text to be processed; construct a semantic tree according to the natural word-dependent syntactic tree and the pre-built ontology knowledge base; use the semantic tree to obtain semantic understanding results. The invention can improve the correctness and flexibility of natural language semantic understanding.

A phonetic data processing system processes phonetic stream data to produce a set of semantic data, using a context-free rich semantic grammar database (RSG DB) that includes a grammar tree, comprised of sub-trees, representing words and phrases. A phonetic searcher accepts the phonetic estimates and searches the RSG DB to produce a best word list, which is processed by a semantic parser, using the RSG DB, to produce a semantic tree instance, including all valid interpretations of the phonetic stream. An application accesses a semantic tree evaluator to interpret the semantic tree instance according to a context to produce a final linguistic interpretation of the phonetic stream, which is returned to the application.

The invention discloses a remote-sensing artificial ground object identifying method based on a semantic tree model of an object. The remote-sensing artificial ground object identifying method comprises the steps of: establishing a remote-sensing ground object representative image set; splitting images in the remote-sensing ground object representative image set by adopting a multi-scale method, and obtaining an object tree of each image; modeling for each node of each object tree by adopting an LDA (linear discriminant analysis) method, and computing implied semantic features contained in the tree node objects; obtaining the object tree sets of all the images in the representative set to learn each pair of object trees in a matching way, and extracting the common maximum sub-trees from the object trees; combining all the common maximum sub-trees together by adopting a step-by-step adding method, and forming an object semantic tree of the category of the described ground object; and identifying the artificial ground object according to the object semantic tree and obtaining the area in which the ground object is positioned. The remote-sensing artificial ground object identifying method disclosed by the invention can be used for mostly effectively processing the artificial ground objects in the condition of high-resolution remote-sensing images; the identification result is accurate, the robustness is good, the applicability is high, and manual work is reduced.

Embodiments of the present invention provide a method, system and computer program product for telephonic fraud prevention. In an embodiment of the invention, a method of telephonic fraud prevention includes speech recognizing in real-time, audio of a telephone call from a caller to a called party. Once the real-time audio has been speech recognized into text, the text may be parsed into words and the words compared to a hierarchical semantic tree of terms. On the condition that a match is detected between one of the words and a node of the tree, a level of the tree is identified at which the match is detected and the level is correlated to a degree of risk of the telephone call. Finally, an alert is displayed to the called party reflecting the degree of risk.

The invention discloses an image classification method based on a tree structure and system using the method. The method includes the first step of providing a sample set with label information and building a semantic tree structure according to semantic correlation of the label information; the second step of obtaining a set of supervised codebooks and classifier models through model training according to the sample set and the semantic tree structure; the third step of generating multiple middle layer feature representations of an image to be tested through the supervised codebooks obtained from the model training, and predicting a classification label of the image to be tested by means of the classifier models according to the middle layer feature representations. The image classification method solves the classification problem that existing codebook (feature) learning can not effectively respond to massive classification.

The invention discloses a CAD semantic model search method based on a design intent. The method comprises the steps of A, establishing a three-dimensional CAD model database and carrying out three-dimensional annotation of the design intent through utilization of a PMI module of UG according to modeling, analyzing and manufacturing features of each model; B, carrying out classification on the annotation information of three-dimensional models according to modeling information, analyzing information and manufacturing information, and establishing a design intent semantic tree of each model; C, establishing a field-based body semantic model tree according to a three-dimensional semantic tree database; D, establishing a search index according to the body semantic tree; E, comparing similarity of a target search word set and semantic tree nodes and returning the same or similar nodes and sub-nodes thereof; and F, calculating corresponding model semantic similarity according to the returned nodes, returning the three-dimensional models with high semantic similarity and feeding back the three-dimensional models to a user. According to the method, the semantic gap problem of the content-based search method is solved, the similarity calculation is carried out by matching target search words and semantic annotation words, and the recall ratio of search is improved.

The invention discloses a cross-modal retrieval method for querying a video from a complex text based on semantic tree enhancement. For complex text query statements, words of complex text query statements are converted into leaf node representations, the relationship between child nodes is mined, the two child nodes with the highest dependency are combined, a semantic tree structure of the querystatements is constructed in a recursion mode, and query representations based on semantic tree enhancement are obtained. For coding of candidate videos, video preliminary features are obtained through a CNN, time dependence and semantic correlation between the videos are captured through a GRU and a self-attention mechanism module, and robust video feature representation is obtained. The complextext query representation and the video feature representation are mapped into a public space, and a matching relationship between the complex text query representation and the video feature representation is is automatically learned, thereby realizing cross-modal retrieval from complex text query to video. Information components in the complex text query statements can be explained, the user intention can be better understood, and the retrieval performance is improved to a great extent.

The invention discloses a language entity relationship analysis method and relates to the field of natural language processing. Complete solution integral computing is carried out on input language strings by the method so as to select the optimal semantic tree. The invention further provides a machine translation device and a machine translation method based on the language entity relationship analysis method. The translation device comprises a semantic library module, a language entity relationship analyzer and a target language generator. The invention provides a novel language processing module. In a program, a complete language logic framework is established through the grasp of all natural language logics and the full utilization of combination explosion, the core problem of combination explosion in language is basically solved, and the accuracy and the translation speed can be obviously improved. The system does not have the massive production rules of a system of rules or the massive alignment corpora and the corresponding deep processing resources of a statistic system, thereby having remarkable advantages in engineering. A reliable basis can also be provided to various natural language applications.

The invention belongs to the field of optical character recognition, and particularly relates to a mathematical formula recognition method, device and equipment. The method comprises the following steps: acquiring a mathematical formula picture to be identified, and preprocessing the mathematical formula picture; distinguishing a plurality of rows of mathematical formula pictures and a single rowof mathematical formula pictures from the mathematical formula pictures to be identified by adopting a LeNet classifier; cutting the multiple rows of mathematical formula pictures into multiple single-row mathematical formula pictures in a projection mode; segmenting all the single-row mathematical formula pictures into single mathematical character pictures; identifying the type of each mathematical character picture by adopting a neural network; utilizing an improved baseline identification method to identify the relative position between the single mathematical characters; and forming a semantic tree of the mathematical formula picture to be identified, analyzing the semantic tree into a latex language, and outputting the latex language. The method has the advantages of being high in recognition rate of recognition formula characters and complete in structure recognition.

The invention mainly relates to the field of full-text search, discloses a built semantic tree and provides a semantic tree based indexing method and system. According to the method, a statement is subjected to incremental hash-coding processing according to a sequence of characters in the statement, specific semantic information coding is formed, pre-semantic feature information, characters and semantic features are stored, and the semantic tree is built; semantic based indexing basis is established according to the semantic tree, a semantic tree and document association table and document storage, and a semantic tree based full-text search engine is provided. The semantic tree based indexing method and system have the advantages of no dependence on word segmentation service, small storage space, high query speed and the like, and are suitable for full-text index of character information and semantic comprehension and processing based on the semantic tree.

The invention discloses a method and a device for identifying a semantic structure of network information. The semantic structure comprises a plurality of semantic comments of the network page information content related to the semantics, properties of the commented information, and relations among the semantic comments. The method comprises the following steps: storing into a semantic structure tree in the system by defining the semantic structure of a sample page; generating a semantic tree identification command and a semantic tree validity identification command; and storing a semantic structure description file, a semantic tree identification command file and a semantic tree validity identification file in an external storage after the semantic tree identification command and the semantic tree validity identification command are verified. The semantic structure of the network page information, which is defined and identified by the method and the device of the invention, can be used by various systems, such as an information extraction system, a full-text and semantic search system, a commercial information mining system, an information syndication system, a network knowledgebase system and the like.

The invention discloses a GML analytic method based on GDOM and persistence thereof, including the steps of GDOM object model design, GDOM semantic analytic interface design, persistence processing method and GDOM data analytic flow. The method of the invention, directing at the disadvantages that GML oriented text analytic interface is not enough and is lack of standard and efficiency is low, designs a document object model with enough GML object expression and semantic manipulation interface (GDOM). Aiming at improving GML analytic efficiency, GDOM object oriented persistence storing method is designed, and structure element data for storing GDOM semantic tree structure information and content element data for storing GDOM semantic tree node content information are defined. On the basis, GDOM persistence file is generated based on SAX method, and GDOM persistence file analyzed based on DOM method. The invention provides solution for efficiently and flexibly processing GML or other semi-structured spatial data resource.

The invention discloses a semantic tree based asynchronous dynamic push-down network reachability analysis method and belongs to the technical field of software safety and reliability. The semantic-tree based asynchronous dynamic push-down network reachability analysis method is characterized in that leading a semantic tree to a dynamic push-down network; establishing a semantic tree of a simulated middle model and enabling the reachability of the model to be decidable through a context limit method to calculate a reachable pattern set inside limited context execution for k times; calculating whether an intersection of the reachable pattern set and a target pattern set is empty or not to judge whether the reachable pattern set is reachable or not, accordingly judging whether design errors or bugs exist in an abstract model of a program and guaranteeing the model being correct and reliable.

The invention relates to a time correlation interactive fusion-based online community post influence sorting method. The method comprises the following steps of: determining time correlation-based influence sorting; carrying out semantic modeling on text contents of posts according to a text semantic model, so as to construct a semantic context similarity-based semantic tree; and fusing text semantic meanings of the posts with structure information of a network community according to a uniform interactive fusion algorithm, and sorting the influences of the posts. Through fusing time correlation information into a sorting scheme, a time correlation influence sorting manner is formed, a uniform fusion framework which combines the semantic meanings and the network community structure is realized on such basis, and the network structure is fused with the text contents, so that the problem of discovering the potential influence sources in the network community is solved, and displayed time information and semantic context information of network community posts can be sufficiently utilized.

The embodiment of the invention discloses a semantic processing method and device, electronic equipment and a medium, and relates to the technical field of knowledge maps. According to the specific implementation scheme, a target semantic element rule matched with a to-be-analyzed text is determined, and the to-be-analyzed text is analyzed by adopting the target semantic element rule to obtain a semantic element analysis result; a target structured rule associated with the target semantic element rule is adopted, and a semantic tree is generated according to a semantic element analysis result;and based on the semantic tree, semantic understanding is performed on the to-be-analyzed text. According to the embodiment of the invention, the analysis efficiency and accuracy of complex problemsin the to-be-analyzed text are effectively improved.

The invention discloses a sketch recognition method, which comprises the following steps of S1, obtaining pictures to be processed; S2, segmenting the collected picture into parts with semantic information to obtain a part diagram of the sketch; S3, obtaining the label of the component through identifying the component diagram by using the depth learning network model; S4, associating the semanticinformation of the component with the semantic information of the object to which the component belongs; S5, outputting the label of the object to which the part belongs obtained through the semantictree. The application of the method in commodity retrieval is characterizd by comprising the following steps of 1) obtaining picture information; 2) using a retrieval system to utilize the sketch recognition method to obtain the label of the article that the user wants to find according to the picture; 3) recommending the corresponding commodity for the user according to the identified label. Themethod and the application of the invention improve the correct rate of the identification of the complete sketch, save the time for the user to select the commodity, and enhance the user experience.

The invention discloses a method for automatically generating a submission demand abstract based on a strategy gradient algorithm. The method comprises the steps of extracting submission information and source code annotation in a submission demand relationship and a text semantic tree structure corresponding to the submission information and the source code annotation; encoding into a hidden state through a bidirectional recurrent neural network encoder; mapping into a vector sequence with a fixed length; and carrying out soft control between a word selected from a vocabulary table and a wordcopied from a source sequence through the generation probability of the vocabulary by using a pointer generator to obtain final vocabulary distribution. A strategy gradient algorithm with a base lineis combined with N times of Monte Carlo search; the method comprises the following steps: calculating an average reward containing a sequence of an action through N times of Monte Carlo search, finding out an action sequence with the maximum average reward, taking the action as an action to be selected, performing the action according to the action to obtain a complete sequence, updating a strategy gradient by utilizing a difference value between the sequence searched by Monte Carlo search and a baseline sequence, and finally generating a submission demand abstract.

The invention provides a semantic comprehension method, device and equipment and a storage medium, and the method comprises the steps of obtaining a target text; according to the target text and a knowledge semantic tree template constructed in advance for the field to which the target text belongs, generating a knowledge semantic tree capable of reflecting the semantics of the target text as thetarget knowledge semantic tree, wherein the knowledge semantic tree template comprises a plurality of entities capable of embodying semantics in the field to which the target text belongs, entity types corresponding to the plurality of entities respectively, and relationships among the plurality of entities, wherein the target knowledge semantic tree comprises a plurality of target entities capable of reflecting target text semantics, entity types corresponding to the plurality of target entities respectively and relationships among the plurality of target entities; and determining a standardtext corresponding to the target text from the standard text set according to the target knowledge semantic tree. The semantic comprehension method provided by the invention can correctly understand the real semantics of the content expressed by the target text.

An autonomous agent creates a first semantic tree from a question and second semantic tree from a candidate answer. The agent identifies, between the first semantic tree and the second semantic tree, common subtrees and calculates a semantic alignment score from a sum of sizes of each of the common subtrees. The agent forms a first syntactic tree for the question and a second syntactic tree for the candidate answer. The agent identifies a number of common syntactic nodes between the first syntactic tree and the second syntactic tree. The agent calculates a syntactic alignment score based on the number of common syntactic nodes. Responsive to determining that a sum of the semantic alignment score and the syntactic alignment score is greater than a threshold, the agent outputs the candidate answer to a device.

The invention relates to the technical field of software security vulnerability detection, in particular to a function-level software vulnerability detection method, which comprises the following steps of: A) importing a training code; B) obtaining an abstract semantic tree of the training code to form an initial feature vector; C) unifying the function name and the variable name; D) obtaining original features; E) obtaining a characteristic expression; F) training a neural network model; And G) obtaining the feature expression of the to-be-detected software code, and inputting the to-be-detected feature expression into the neural network model trained in the step F to obtain a vulnerability detection result. The substantial effects of the invention are as follows: the scheme uses a seriesof simple methods to cooperate with Bi-; The LSTM neural network is used for processing codes, advanced abstract semantic features of functions can be directly extracted, manpower and material resources are saved, and cross-project vulnerability detection can be implemented through the extracted advanced abstract semantic features.

A mobility pattern mining device includes: a data collecting unit configured to collect a user's historical data; a stay point obtaining unit configured to obtain stay points of the user from the historical data; an extracting unit configured to obtain a semantic tree for a certain topic and extract topic related stay points from the stay points of the user by using the semantic tree for the certain topic; a determining unit configured to determine a candidate mobility pattern of the user based on the topic related stay points; and a selecting unit configured to select a frequent mobility pattern which best matches the candidate mobility pattern of the user from a frequent mobility pattern database related to the certain topic, wherein the database is set in advance based on historical data for a plurality of users to obtain mobility patterns about topics for users.

The invention provides a persona access method, which comprises the following steps that: S1: according to a plurality of target tags sent from a business side and a logic relationship among a plurality of target tags, generating a semantic tree, and generating a query code according to the semantic tree; S2: sending the query code to a data side for the data side to carry out query on user portrait data stored in the data side on the basis of the query code, and obtaining target data, wherein the target data is the user portrait data which conforms to the logic relationship among the plurality of target tags; and S3: receiving the target data returned from the data side, and sending the target data to the business side. By use of the persona access method, the semantic tree is applied togenerate the query code, the automatic access of a business party is realized, requirement communication cost between the business party and a persona party is lowered, the data query pressure of thepersona party is released, and persona access efficiency is improved.

The invention provides a content retrieval method, device and equipment and a storage medium. The method comprises the following steps of receiving query requests, wherein the query request comprisesa query statement inputted by a user; preprocessing query statements, obtaining a word attribute list corresponding to the query request, wherein the word attribute list comprises at least one query keyword in the query statement and an attribute corresponding to each query keyword; according to the word attribute list, constructing a semantic tree, wherein the nodes in the semantic tree are composed of query keywords in the word attribute list; according to the semantic tree, generating the query language, obtaining the content corresponding to the query request through query according to thequery language, so that the function docking with different search systems is achieved, the search query of complex query statements with unclear structures is completed, then the accurate reply content is provided, and the user experience is improved.