135 results about "Affiliation network" patented technology

The invention relates to the technical field of geographic space information systems, and discloses an immersive visual analysis method for spatio-temporal data on the basis of a multilayer association network. The invention has the concept that: firstly, abstracting and extracting an object node related to a task from a scene; then, analyzing and calculating an association relationship among nodes, and carrying out hierarchical division on the association relationship among multi-granularity spatio-temporal objects; according to a spatial topological relationship, a semantic association relationship layer and a multi-modal characteristic association relationship layer, constructing a multilayer association network, and carrying out collaborative visual processing on the constructed multilayer association network and a scene; and finally, through a human-computer interaction operation, realizing a final purpose that inferential reasoning and discovery ability of a human brain can be combined and a potential and complex association relationship is assisted in discovery. Therefore, the method is favorable for people to quickly discover a new knowledge rule, and the progress and the development of human scientific knowledge are accelerated.

The invention discloses a pedestrian multi-target tracking method combining attention mechanism end-to-end training, and the method comprises the steps of collecting a pedestrian data set of a video sequence with a label, employing a first frame real boundary frame of each video in the label as a template sample, cutting a positive search region sample in a second frame according to the center ofthe sample, and cutting out a negative search area sample in an area which is not the same kind of target; forming triple data input; extracting feature information of the sample by using a convolutional neural network; using an attention mechanism module for guiding the network model to tend to important feature information, and finally calculating similarity and data association. According to the invention, single-target tracking based on the twin network and the association network are integrated into a unified network structure, and the attention mechanism is combined to serve as meaningful feature information for network bias learning, so that the feature expression capability of a network model is improved, the calculation efficiency is improved, and the training process is simplified.

The invention provides a situation awareness node defense method and system for APT attacks, and relates to the technical field of network security. The node defense method comprises the following steps: collecting information that a network node is attacked by APT, and setting a virtual backup node for the network node; establishing a communication connection between the network node and the virtual backup node, storing the data information of the network node into the virtual backup node, and cutting off the connection between the network node and the associated network node; and establishing a connection between the virtual backup node and the associated network node. According to the method, the storage path of the data information is changed in real time based on the attack mode information in the network, so that an attacker is difficult to find the storage address of the data information to attack, and situation awareness system node defense is realized on the basis of ensuring normal communication of the whole network.

Apparatus, methods, and computer program products are provided for that automatically identify transactions and/or items in a transaction that are associated with a group of individuals, such as a family, co-workers, a special interest group, a demographic group a social network group or the like. Once transactions and/or items in the transaction have been identified as being associated with the group, the transaction data associated with the transactions and/or the items in the transactions is aggregated and aggregated views of the data are made accessible to individuals in the group, such as through a financial institution financial management application, e.g., online or mobile banking application.

The invention relates to a pedestrian target tracking method based on a convolutional association network in an automatic driving scene. Characteristics are shared by using a convolution association network and a lightweight target detection network, the relevance between the targets is captured, and then target tracking is achieved. The method specifically comprises the following steps: A1-1, obtaining a one-stage target detection model, performing down-sampling for five times in total; performing prediction on the feature maps of the last three scales; adopting a common convolution module except during first downsampling, replacing adopted models designed in a multi-scale downsampling module during subsequent four downsampling with separable convolution modules, performing target frame prediction on the models on a feature map of the last three downsampling, and finally forming a lightweight pedestrian target detection network is formed; A2-1, predicting a target incidence matrix toobtain a target incidence matrix; and A3-1, designing a pedestrian target tracking strategy through a convolutional association network, and finally obtaining a pedestrian associated target tracking result. The method can well adapt to an automatic driving scene in the aspects of tracking precision and speed.

The invention relates to the field of data associated processing and data visualization, in particular to a representing method and system capable of dynamically expanding a data associated network diagram. The representing method comprises the following steps: establishing a data associated network model through the back end so as to respond to a request from the front end and return a result; according to a user's operation, generating an operating command and requesting the back end for data through the front end, and further drawing and updating the data associated network diagram according to the data associated network model after receiving data fed back by the back end, wherein the data associated network can be continuously and dynamically expanded under the operation of the user. According to the representing method and system capable of dynamically expanding the data associated network diagram, provided by the invention, an entity relationship network with infinitely many elements can be supported, and entities of different types, relationships and entity aggregations can be expanded; the representing method and system can further intuitively and friendly represent complex data associated diagrams, bring great convenience to data analysis personnel for work and can be applicable to a data analysis and assistance decision making system.

The invention provides a multi-party evidence association model construction method based on a Bayesian network and an evidence chain extraction method and device. The method comprises evidence network construction based on a fact judgment chain, evidence weight calculation and an evidence chain reasoning method based on a Bayesian network. Evidence sources are divided into original evidences, informed evidences, judicial expertise evidences, third-party evidences and the like. Firstly, a multi-party evidence association network is constructed, each evidence entity serves as a node in the network, and the correlation probability between the nodes in the network is calculated based on the association relationship between the evidence elements; then, based on the evidence type of the event judgment chain, a multi-party evidence association model based on the Bayesian network is constructed; and finally, the Bayesian network is optimized by adopting a genetic algorithm to obtain a credible evidence chain. According to the method, the evidence chain with the maximum credibility can be found from multiple sources, and judicial personnel are helped to screen the credible evidence chain from multi-party certification or contradictory evidences.

An Internet affiliate marketing method and associated computer program whereby a next generation affiliate network acts as an exchange for advertisers and merchants on one side and affiliates and next generation affiliates on the other. Affiliates and next generation affiliates sell content advertising in creatives to advertisers and merchants. Parties use this network to find each other, evaluate each other, and establish a purchase or advertising agreement using rewards. Creatives, using traditional advertising, familiar creative advertising, and combination advertising, are transmitted to the network website which posts them on selected social media sites. Parties accessing these sites are exposed to advertisers' and merchants' products appearing on creatives found therein. The network interfaces with enhanced capability supply-side platforms, real-time bidding platforms, and demand-side platforms that accommodate the new advertising concepts, familiar creative advertising and combination advertising.

The invention relates to an ecological index efficiency evaluation method based on network analysis. The method comprises the steps that a, according to the objective level and the content of a system to be evaluated, a to-be-evaluated ecological index system with a level structure is constructed; b, through literature research and expert consultation, a theoretical perfect standard ecological index system level network is constructed, and the index weight is calculated; c, a relevance network between the operation layers of two index systems is constructed; d, according to the relevance network, the index weight of the to-be-evaluated index system is calculated; and e, the coverage degree and the characterization degree of the to-be-evaluated index system are calculated. According to the invention, the science connection in the to-be-evaluated index system is explicated from the three aspects of the relevance, the coverage degree and the characterization degree; the application efficiency of an operation index is improved; the method can be applied to the efficiency evaluation of an index system related to ecological construction, such as the evaluation of an ecological province construction index system and other problems; and the method can be applied to the efficiency evaluation of other similar complex index systems, such as regional society, economic index evaluation and the like.

The invention discloses a method and device for identifying a risk user, a storage medium and an electronic device. The method comprises the following steps: acquiring target data; preprocessing the target data to obtain a preprocessing result; an association network is constructed based on the preprocessing result, the vertex of the association network is a target entity associated with the target user, and the edge of the association network is the relationship between the target entities; performing feature extraction processing according to the associated network to obtain a first user feature, a second user feature and a third user feature; and performing risk identification processing on the first user feature, the second user feature and the third user feature by using a first model to obtain a risk identification result corresponding to the target user, the risk identification result being used for formulating a target risk strategy. The technical problems that in the prior art, a method for identifying a risk user is high in rule making cost and poor in interpretability are solved.

The invention provides a risk assessment method and device based on an association network, equipment and a storage medium, and the method comprises the steps: obtaining a target community of a target node in the association network, wherein the target node is a node, corresponding to a to-be-assessed target object, in the association network, and the target community is composed of a plurality of nodes with the association degree greater than a preset value; acquiring community features of a target community, wherein the community features are determined based on the features of each node in the target community; inputting the community features and the first features into a risk assessment model to obtain a risk assessment result of the target object, wherein the risk assessment model is obtained by training based on a neural network model, Wherein the first feature is determined based on the features of the n-order neighbor nodes of the target node, so that the risk of the target object is comprehensively and accurately evaluated.

The invention discloses an urban and rural infrastructure system collaborative planning method based on population flow data, and the method comprises the steps: determining the grouping division, node levels and network positions of different urban and rural nodes through an urban and rural associated network established through the population flow data, comparing according to the current multi-element association network formed by the infrastructures with different types of functions to find the supply and demand difference between the urban and rural association network influencing the target decision and the current multi-element association network, and adjusting the spatial layout and configuration of the infrastructures in the multi-element association network, so as to match the node level and position in the urban and rural associated network, so that effective planning and reasonable adjustment of urban and rural infrastructure matching are realized, efficient and accurate resource configuration and global pattern optimization of infrastructure integration are realized, and a new planning means is provided for promoting urban and rural infrastructure integration and system collaborative development.

Methods, systems, and machine readable media are disclosed for managing bandwidth usage of a content provider. According to one embodiment, a system for managing bandwidth usage of a content provider can comprise a content provider system adapted to maintain and provide content and a first affiliate system comprising an affiliate network, an affiliate server communicatively coupled with the affiliate network, and a client. The client can be adapted to selectively request the content from either the content provider system or the affiliate server of the first affiliate system based on bandwidth costs for the content provider system.

The invention provides a defense method, device and system based on an existing threat in a target node, and relates to the technical field of network security. The processing method comprises the following steps: acquiring log information and threat intelligence information of network nodes in a network environment; the network nodes comprise a to-be-defended target node and an associated network node; selecting any to-be-defended target node, determining a threat item of the target node based on the threat intelligence information of the target node, and calling a defense scheme for defense; obtaining access information of interaction between the target node and the associated network node from the log information of the network node; and in combination with the access information and the threat intelligence information of the target node, obtaining a threat item corresponding to the associated network node, and calling a defense scheme for defense. According to the method, the target node and the associated network node thereof are effectively defended by acquiring the log information and the threat intelligence information of the network node, so that resources consumed during network security defense are reduced.

In an embodiment, a network entity schedules, as part of a positioning procedure for a UE, a first set of resources for transmission of DL RS(s) by at least one BS to the UE. The network entity associates the DL RS(s) with UL RS(s) for transmission by the UE on a second set of resources to one or more BSs as part of the positioning procedure for the UE. The network entity transmits, to the UE, anindication of the association between the DL RS(s) and the UL RS(s). The UE receives the indication along with the DL RS(s) from the at least one BS. The UE transmits the UL RS(s) to the one or more BSs on the second set of resources in response to the received indication.