5 results about "Mashup" patented technology

The application provides a Mashup service multi-label classification method based on double manifold regularization width learning, mainly comprising: using a hidden Dirichlet distribution topic model to extract features from preprocessed Mashup description documents; linearly mapping a Mashup description document topic feature matrix into n groups of feature nodes respectively; processing the feature nodes through an activation function to generate enhanced nodes; splicing the feature nodes and the enhanced nodes to generate enhanced feature nodes as the input of the model; constructing a target function of a Mashup service multi-label classification model based on double manifold regularization width learning; using a least square method to solve the target function to obtain a weight matrix of a double manifold regularization width learning network; obtaining a description document of a test Mashup service and sending it into a trained model to predict a multi-label classification result. The application improves a width learning model by using double manifold regularization, and realizes a Mashup service multi-label classification function by using an improved BLS model.

Device for controlling the execution of a mashup WoT service, the device comprising: a Web of Things mashup service function entity, WoT mashup service function entity, (52) configured to execute a mashup WoT service adapted for a WoT service user (10); a WoT service execution function entity (54) configured to handle the execution of simple WoT services for the execution of the mashup WoT service of the WoT mashup service function entity; and a WoT service repository (56) configured to store WoT service execution descriptions (56a, 56b, 56n), each describing execution logic for each of the simple WoT services; wherein the WoT mashup service functionality entity comprises: a WoT mashup engine (52b) configured to execute the mashup WoT service in accordance with the service instruction read from the relevant WoT service execution description;wherein each of the WoT service execution descriptions includes information about the mashup WoT service, a service instruction designed to execute the mashup WoT service created by combining the two or more simple WoT services, and service profiles representing parameters designed to identify the mashup WoT service customized for the WoT service user.

The application discloses a kind of based on the recommendation method of multi-modal service feature of meta-path fusion, belong to service recommendation and representation learning field.It includes: collection Mashup application and Service service, and constructs historical call matrix and the multi-modal feature of Service service;Meta-path and similarity calculation are used to Service service, respectively obtain meta-path isomorphism and modal isomorphism;Introduce multilayer perceptron and filter, further combined with all isomorphism, contrast loss and fusion modal feature are obtained by graph convolution network;Based on fusion modal feature and historical call matrix, respectively calculate to obtain second contrast loss and BRP loss;Regularization loss is introduced, to minimize all loss sum reverse training all network parameters, obtain the service retrieval table of training completion.The method of the application can accurately fuse the features of multiple modalities of traditional services, significantly enhance the generalization capability in cold start and sparse scenarios.

The invention relates to an interactive Web API recommendation method based on reinforcement learning, which belongs to the field of Web API recommendation, and comprises the following steps: abstracting multiple rounds of Web API recommendation problems into a Markov decision process; designing a state representation module fusing user positive and negative feedback, demand semantic features and a Mashup and Web API feature interaction relationship; designing and deploying an environment simulator based on an offline data set; a double-layer deep Q network is adopted as a strategy function, and recommended actions are output according to the current state. A priority experience playback mechanism based on a time sequence difference error is introduced, and sampling priorities are dynamically distributed for interaction samples in the training process; and performing multiple rounds of interaction through a simulator, storing interaction samples in a priority experience playback buffer pool, periodically updating DDQN network parameters, synchronizing a target network by adopting a soft update strategy, evaluating a trained learning strategy, and outputting a recommendation list. According to the method, the sample utilization efficiency and the sorting quality in a sparse feedback scene can be effectively improved.

The application discloses a Mashup service clustering method based on feature semantic enhancement and graph contrast learning. Mashup service data participating in clustering is preprocessed, then a service function vector is generated based on a singular value decomposition and a standardized space distribution correction method, and a feature semantic enhancement method of the service function vector is based on a non-functional entity word, a named entity recognition method is used to extract the non-functional entity word in the description text, and a feature semantic enhancement vector is constructed. The feature semantic enhancement vector and the service function vector are spliced; on this basis, two kinds of Mashup service association graphs facing sharing dependence are established, and a service function vector fusing a label association neighborhood feature and a fusion Web service association neighborhood feature is constructed. Finally, the two vectors are optimized through an infoNCE loss function, a service representation vector is constructed, and a spectral clustering algorithm is adopted to realize Mashup service clustering, so that the clustering quality can be effectively improved.