47 results about "Implicit relationship" patented technology

Systems and methods of a knowledge management networking are disclosed here. In one aspect, embodiments of the present disclosure include a method, which may be implemented on a system, of hosting a web-space having a plurality of objects, the plurality of objects to include one or more of, representations of a set of users, a set of web-items, and a set of nets; wherein a net of the set of nets is a subset of the web-space comprising a sub-plurality of the plurality of objects. One embodiment can include, tracking an explicit relationship between a first set of at least two objects of the set of objects; the explicit relationship to be pre-determined by a user of the set of users, identifying an implicit relationship between a second set of at least two objects of the set of objects; the implicit relationship to be identified based on a semantic relationship between the at least two objects, and determining a default set of privacy rules governing access between the at least two objects based on one or more of the identified explicit relationship and the implicit relationship.

The invention discloses a visual question and answer fusion enhancement method based on multi-modal fusion. The method comprises the following steps of 1, constructing a time sequence model by utilizing a GRU structure, obtaining feature representation learning of a problem, and utilizing output which is extracted from Faster R-CNN and is based on an attention model from bottom to top as the feature representation; 2, performing multi-modal reasoning based on an attention model Transformer, and introducing the attention model for performing multi-modal fusion on a picture-problem-answer tripleset, and establishing an inference relation; and 3, providing different reasoning processes and result outputs for different implicit relationships, and performing label distribution regression learning according to the result outputs to determine answers. According to the method, answers are obtained based on specific pictures and questions and directly applied to applications serving the blind,the blind or visually impaired people can be helped to better perceive the surrounding environment, the method is also applied to a picture retrieval system, and the accuracy and diversity of pictureretrieval are improved.

An autonomic computing system and method determine policy definitions (404) and a set of available actions (410); monitor resources distributed within the system; determine if the system is at a desired end state; and modify resource states by sending instructions for the resources to perform available actions. The policy definitions (404) specify: start order between resources, prioritization between resources, conditional activation of policies, desired end state of resources, and location limitation of resources. The system and method receive status information from available resources, and monitor and modify the system until it reaches the desired end state. The policy definitions (404) can be determined by specifying a user-defined system end state and resource relationships. The policy definitions (404) can further harvest implicit relationships between resources, via self-discovery, and underlying relationships among resources.

A method (system and computer program product) performs facet classification synthesis to relate concepts represented by concept definitions defined in accordance with a faceted data set comprising facets, facet attributes, and facet attributes hierarchies. Dimensional concept relationships are expressed between the concept definitions. Two concept definitions are determined to be related in a particular dimensional concept relationship by examining whether at least one of explicit relationships and implicit relationships exist in the faceted data se between the respective facet attributes of the two concept definitions.

The invention discloses a visual dialogue generation method based on a context perceptual map neural network. The visual dialogue generation method comprises the following steps of 1, preprocessing the text input in a visual dialogue and constructing a word list; 2, extracting the features of a dialogue image and the features of a dialogue text; 3, obtaining a context feature vector of the historical dialogue; 4, constructing a context perceptual map; 5, iteratively updating the context perceptual map; 6, carrying out attention processing on the nodes of the context perceptual map based on a current problem; 7, performing multi-modal semantic fusion and decoding to generate an answer feature sequence; 8, generating the parameter optimization of a network model based on the visual dialogueof the context perceptual map neural network; 9, generating a prediction answer. According to the method, the context perceptual map neural network is constructed on the visual dialogue, and the implicit relationship between different objects in the image can be reasoned by using the text semantic information with finer granularity, so that the reasonability and accuracy of the answers generated by an intelligent agent for question prediction are improved.

The invention relates to a semantic web based method for acquiring an implicit relationship among steel iron making process knowledge. The method is used for accurately expressing the implicit relationship among the steel iron making process knowledge. The method comprises the following steps of 1) performing triple expression on the steel iron making process knowledge to establish an initialized model of a concept and the relationship of the steel iron making process knowledge; 2) converting the initialized model to construct an ontology base; 3) performing semantic mapping on production standard data and the ontology base to construct a semantic web model; 4) performing formalized expression on a constraint condition of the concept and the relationship in the steel iron making process knowledge by adopting a semantic web rule language (SWRL) to establish a knowledge reasoning-oriented rule base; and 5) according to the semantic web model and the rule base, obtaining implicit associated information of the steel iron making process knowledge. Compared with the prior art, the method has the advantages of reusability, easiness for maintenance, flexibility for expression, fullness for discovery, strong data correlation and the like.

The invention discloses a high-rockfill-dam transient-rheological-parameter inversion method based on the response surface method.The method includes the steps that a rockfill-dam three-dimensional finite element model is built in combination with dam body material sections and construction grading conditions, the sensitivity of the transient parameters and the rheological parameters of rockfill of the material sections is analyzed, and the transient parameters with the high sensitivity and the rheological parameters with the high sensitivity are selected as to-be-inversed parameters jointly; a material static force model is a Duncan EB model, and a rheological model is a Nanjing-Hydraulic-Research-Institute five-parameter model; the implicit relationship between the finite-element-calculated settling volume and the calculation parameters is represented through a specific-form response surface function, undetermined coefficients of a response surface equation set are solved through several times of finite element calculation, and therefore the nonlinear mapping relationship between the settling volume and the calculation parameters is built.On the bases of the response surface equation, the objective function aims at obtaining the minimum root-mean-square error between the calculated settling volume and the practically-measured settling volume, the transient parameters and the rheological parameters are inversed with the genetic algorithm at the same time, and the obtained set of optimal calculation parameters are the inversion result.

The invention provides an implicit inter-sentence relationship analysis method based on a multi-task bi-directional long-short time memory network. The method comprises the following steps: obtaininga Chinese text-level semantic relationship corpus, comprising implicit inter-sentence relationship statements and explicit inter-sentence relationship statements; obtaining a Chinese text-level semantic relationship corpus. Using the method of multi-task learning, the input sequence of the model is obtained by using implicit inter-sentence relation recognition task as the main task and explicit inter-sentence relation recognition task as the auxiliary task. Enter both primary and secondary tasks into Bi-LSTM recurrent neural network, through learning the implicit relationship between sentencesrecognition model; The implicit inter-sentence relation recognition model adopts a fusion word embedding method and introduces a priori knowledge so as to make full use of text features and obtain abetter recognition result. The present invention fully utilizes the semantic connection between the implicit sentence-to-sentence relation sentence and the explicit sentence-to-sentence relation sentence, and solves the problem that the implicit sentence-to-sentence relation sentence does not have good characteristics, which leads to bad implicit sentence-to-sentence relation recognition effect.

Implied relationships between entities, such as network endpoints, are automatically discovered based on co-temporal events. Events involving pairs of endpoints, such as messaging events in which one endpoint acts as a source and another endpoint acts as a destination, may be detected. Edges between nodes representing those endpoints and other nodes representing other endpoints involved in other recent (co-temporal) events may be added to a progressively constructed graph. Over time, such edges may be progressively weighted in response to the detection of further co-temporal events involving the same endpoints. Relationships between endpoints may be implied based on the resulting accumulated weights of edges linking those endpoints' nodes in the graph even if there is no express relationship between those endpoints in any real-word context (e.g., even if those endpoints are not directly connected in any network, and even if no single event involves both of those endpoints together).

A system and method for controlling access to components in a database is provided. The system and method provides flexible access control with variable granularity using a generalized mapping model (GMM) transform of data from one or more databases into a plurality of GMM objects, and mapping the GMM objects to access control settings using an access control mapping. The database access control system and method uses the structures of objects created by the GMM transform to identify and facilitate selective access control to any part or combination of components in the database, including the data and implicit relationships among data. The system and method facilitates individual control of the security permissions and conditions for the components using one or more access control maps to define which data components and relationships different access control procedures are applied.

The invention provides an equivalent LED light source establishing method. An implicit function relationship between the LED luminous intensity and the LED major parameters (such as insertion depth of a chip, refractive index of a surrounding filling material, absorption coefficient of the material, and thickness of a package lens) can be established by the prediction algorithm through measuring actual LED light distribution. Then, by assuming a set of initial LED model parameters, optical equivalent parameters can be found out by the global optimization algorithm on the basis of the implicit relationship between the LED luminous intensity and the LED major parameters; and by the optical equivalent parameters, an equivalent accurate LED light source model can be established. With the adoption of the method, the equivalent LED light source model extremely approximate to an actual light source can be established quickly and accurately, so that an equivalent accurate LED light source model can be obtained through an LED light source provided by any LED light source manufacturer by virtue of measuring the luminous intensity of the LED light source. The light source model can be used for the design of an illumination system.

The invention discloses a cold start fraud comment detection method based on social attention mechanism representation learning, and the method comprises the steps: constructing an initial target function representing the entity relation of a user, a project, comments and scores based on a given online comment data set; constructing an explicit user characteristic matrix of the display relationship between the users and an implicit user characteristic matrix of the implicit relationship between the users according to the scores, and then constructing a social coupling matrix of the users; integrating the social coupling matrix of the user into the user representation matrix by adopting an attention mechanism, and adjusting the initial target function to obtain a new target function; and determining an attention mechanism of the new user, and identifying whether the comment is a fraudulent comment or not according to the determined classifier. The entity relationship, the user social coupling relationship and the fraud related information are embedded into the user representation space of the social attention mechanism, so that the defect of lack of user historical information in the cold start problem is effectively overcome, and the fraud comments under the cold start condition can be effectively detected.

A neural network for mining implicit relations between features based on short connection comprises: an input layer provided with an input space; a first embedding layer which is used for subsequentlyextracting nonlinear low-order feature interaction; a second embedding layer which is used for subsequently extracting linear features; a nonlinear interaction pooling layer which is used for extracting nonlinear low-order feature interaction from the dense feature matrix output by the first embedding layer; a layer loss neural network which is used for converting the low-order interaction features output by the nonlinear interaction pooling layer into high-order feature interaction output; a linear model which is used for extracting linear features from the dense feature vectors output by the second embedding layer; and a combination layer which is used for fusing the high-order feature interaction output by the layer loss neural network and the linear features output by the linear modelto obtain a final prediction value. According to the method, more characteristics can be fully utilized, the low-order characteristic interaction vector which is more effective for the target task isconstructed, and the prediction capability of the model is further improved.

The invention discloses a vehicle OD flow prediction model construction method and a vehicle OD flow prediction method. In the vehicle OD flow prediction model construction method, a multi-granularityspace partitioning method using grid and road segment nesting is used for representing vehicle OD data at regional and road node levels; the number of trips and travel time between the OD are extracted simultaneously; and a deep prediction model LSTM-traf-deepCNN mixed with CNN and LSTM is used for predicting the OD flow combined with OD travel time. Compared with the traditional OD flow prediction method, the method disclosed by the invention fully considers the implicit relationship between the travel time and the OD flow, and trains the deep network by combining the travel time and the number of trips between the OD; and the obtained model has more accurate predictive power. The invention belongs to the technical field of transportation information engineering and can be used for predicting the OD flow of city-scale taxis.

The present invention discloses a color space converting method based on a fuzzy theory, which comprises the following steps: input and output equipment is adjusted to guarantee the equipment to be normally used; according to color space needing to be changed, sampling points are selected, and the modeling data of the sampling points is acquired; input and output color space fuzzy subsets are divided, and fuzzy subset subjection degree functions are selected; at the same time, fuzzy control rules are established, each fuzzy control rule has a fuzzy implicit relationship correspondingly, and the combination of the fuzzy implicit relationships of all the fuzzy control rules is the chief fuzzy implicit relationship of the system; and the chief fuzzy implicit relationship of the system is clearly treated so as to obtain an output value. The color space converting method based on the fuzzy theory uses an artificial intelligence fuzzy set theory and fuzzy logical deduction, so that the conversion of the color space is completed. The method has the advantages of simple step and high data conversion precision.

The invention discloses a method for generating a text based on the pre-trained structured data, and relates to a method for generating the text based on the structured data. The objective of the invention is to solve the problem of low text generation accuracy caused by the fact that an internal implicit relationship between data is not considered when an existing model models the table data on the generation of the text based on the structured data. The method comprises the following steps of 1, randomly masking one piece of data in one triad in a plurality of triads, and replacing the datawith a symbol; obtaining a characterization symbol implicit calculation sequence according to a calculation sequence relationship between data in a table; 2, obtaining the row vectors of all records in the same row in the table after mean pooling; 3, obtaining a pre-training model, and reserving the parameters of the pre-training model; 4, obtaining a table row vector; 5, verifying the pre-training model in the step 3; 6, obtaining the row vectors of all records in the same row in the table after pooling; and 7, obtaining the information represented by the data in the table. The method is usedin the field of text generation.

The invention provides a code reviewer recommendation method based on collaborative filtering. The method comprises the three parts of data processing, implicit relation mining and logic recommendation, wherein in the data processing part, historical review data is displayed in the form of a matrix; the implicit relation mining part is used for mining an implicit relation implicit in the data according to information of the matrix; and in the logic recommendation part, a general recommendation process is described, and ordering rules are given. Based on realization of the framework, the implicit relation in the data can be effectively utilized to recommend a code reviewer. Through the method, an implicit relation mining mechanism is proposed according to a recommendation scene of the codereviewer. According to the mechanism, a neighborhood model and an implicit factor model in a recommendation system are utilized to serve recommendation work of the code reviewer, and the defects of existing methods in reviewer recommendation are overcome.

The invention relates to an item semantic annotation method based on a use event of a heterogeneous item. The method comprises the following steps: step 1) of establishing an item potential relationship intensity mining model; step 2) of extracting an item implicit feature; step 3) of extracting an item explicit feature; step 4) of training an item semantic annotation model; after the above four features are extracted, combining (FLatent+Ftext+FS+FT) together as training data of a binary classification SVM classifier, and gathering labels predicted by all independent binary classification device as the semantic annotation result of the item. The item semantic annotation method has the advantages that based on a latent variable model establishing item implicit relationship strength based onthe use event of the heterogeneous item, the item implicit feature is extracted therefrom, the category semantic label of the given item is predicted by comprehensively utilizing the explicit and implicit features, and the method is significantly superior to an existing item labeling method based on explicit features in terms of efficiency and performance and the like.