16 results about "Multi aspect" patented technology

The invention discloses a multi-aspect reasoning graph method of an NLP interaction model based on reinforcement learning. The method comprises the following steps: extracting entities and relationships from an input text to construct an initial reasoning graph comprising a plurality of reasoning aspects; a reinforcement learning agent is initialized, a state space of the reinforcement learning agent comprises a graph state and user query, and an action space comprises reasoning operation on a graph; the agent updates a graph or generates a path based on a state selection action, and improves performance through continuous interaction based on a comprehensive reward signal optimization policy; according to the method, the limitation that the prior art focuses on a single reasoning dimension is overcome by constructing the multi-dimensional reasoning graph integrating semantics, logic, context and the like and cooperatively operating the sub-graphs by utilizing the reinforcement learning agent, so that the model can carry out all-dimensional and multi-angle deep analysis on complex queries, and the accuracy of the analysis is improved. The reasoning comprehensiveness and the comprehensive judgment accuracy are greatly improved, and therefore more accurate and complete responses are given in tasks such as questions and answers or dialogues.

The invention discloses a next interest point recommendation method based on multi-aspect continuous dynamic preference modeling of hypergraph ODE. According to the method, modeling can be efficiently carried out on multi-aspect dynamic preferences of the user from a continuous angle, and more personalized recommendation is provided for the user. Multi-aspect user preferences are decoupled by constructing a multi-view hypergraph from collaborative, geographic, and transformational aspects. By expanding discrete hypergraph convolution operation into a continuous form based on an ordinary differential equation (ODE), continuous evolution of multi-aspect user dynamic preferences is modeled. User preferences under different views are integrated by adopting a self-adaptive fusion mechanism, and a dynamic relationship between the user preferences is captured. In addition, an inter-view and in-view comparative learning normal form is designed to enhance the expressivity and robustness of interest point representation. A large number of experiments carried out on four real spatio-temporal data sets with different scales verify that the method has remarkable advantages and efficiency.

Disclosed examples create a multi-aspect object, the multi-aspect object represented using a class definition; assign a first capability to the multi-aspect object, the first capability to communicate with equipment in a control system; assign a second capability to the multi-aspect object, the second capability to communicate with the equipment in the control system; create a semantic data model in the multi-aspect object, the semantic data model to share information between the first capability and the second capability of the multi-aspect object; deploy the first capability of the multi-aspect object on a first runtime platform; and deploy the second capability of the multi-aspect object on a second runtime platform, the semantic data model to communicate between the first and second runtime platforms to share the information between the first and second capabilities of the multi-aspect object.

The invention belongs to the technical field of algorithm models, and discloses a sentence-level multi-aspect sentiment analysis method based on a double-graph convolutional neural network. Comprising the steps of data acquisition and preprocessing, aspect identification and index system construction, model construction and training, and emotion prediction of user generated content. The multi-aspect dependency matrix is adopted, redundant dependency relations are filtered, interaction among multi-aspect words is enhanced, externally-enhanced emotional knowledge is introduced, interaction among semantics is improved, and robustness and accuracy of emotional analysis are effectively improved.

The invention relates to the field of medical systems, in particular to an auxiliary diagnosis system for child developmental dysplasia of hip joints, which comprises an information input module used for inputting multi-aspect information of children; the analysis module comprises a trained convolutional neural network, the convolutional neural network is used for training hip joint ultrasonic images of children of 4-6 months old under multi-aspect information, the convolutional neural network is used for judging whether diagnosis features in the hip joint ultrasonic images meet diagnosis requirements or not, and the convolutional neural network is used for collecting input information of the information input module; and outputting the reference probability that the ultrasonic detection meets the diagnosis requirement. By the adoption of the technical scheme, the method is used for predicting the developmental hip joint dysplasia probability of 4-6-month-old children through multi-aspect information, medical workers are assisted to make examination mode decisions, and the frequency of invalid ultrasonic detection conducted by the medical workers is reduced.

The application discloses a kind of civil aviation pilot artificial operation proficiency quantitative evaluation method and device, its method includes: S1, setting research flight phase, research flight phase includes take-off to climb phase, approach to landing phase, intercepts research flight phase QAR data;S2, the data of take-off to climb phase and approach to landing phase are respectively manipulated proficiency quantitative evaluation.This application takes off to climb phase and approach to landing phase as research flight phase, with high artificial operation intensity and great difficulty, can obtain multi-aspect evaluation value according to take-off to climb phase and approach to landing phase respectively, and simultaneously adopts weighted fusion to obtain take-off to climb phase evaluation result, approach to landing phase evaluation result and research flight phase comprehensive evaluation result, realizes the quantitative evaluation of artificial operation in stage, in aspect and multi-fusion, is favorable for improving flight training effect and the operation skill of pilot.

The application provides a system and method for multi-angle examination and evaluation of engineering contractors and employees, which can instantly manage and record multi-aspect data related to the examination of the contractors and employees, determine examination results by using corresponding examination models according to examination requirements, provide data display services and examination result output services matched with instructions in response to the operation of users, identify data attributes and decide storage paths based on received data, decide management action signals based on received instructions, distribute and store multiple data, support real-time data state updating in response to management action instructions, and form prompt instructions according to set rules on data state information. The system can overcome the defects of the prior art, such as complicated data entry, limited application range of evaluation and analysis, and insufficient reliability, form a comprehensive business data examination and management system for engineering contractors and employees, and provide business monitoring and credit repair and update services based on examination data.

The application discloses a double-layer evaluation method and system for elastic power distribution network recovery force evaluation, obtains power grid historical disaster information for a planning evaluation level, generates a disaster scene through disaster simulation of the planning level, and realizes real-time prediction of the disaster scene according to meteorological and multi-aspect prediction information for an operation evaluation level. Disaster scene simulation analysis is carried out to obtain a load change curve of the power distribution system at each time interval, and the maximum load loss ratio, system load loss time and system power loss amount of the power distribution system are extracted. New disaster scenes are continuously simulated for the planning level until the simulation of the scenes is finished, and then the index expectation values are obtained by counting the indexes obtained under all the scenes. The index results are fed back in real time for the operation level. The application can be used for elastic power distribution network recovery force evaluation of the planning and operation levels, and realizes unification of the two-level evaluation methods.

The application provides a person image clustering method and device, relates to the technical field of image clustering, and is used for improving the accuracy of person image clustering. In the person image clustering method, the self-organizing mapping network is used to process the multi-aspect attribute features of the lens, so as to determine the winning neuron corresponding to the lens, and the winning neurons to which the multiple lenses respectively belong are used to determine the cluster to which the multiple lenses belong, so that a spatial domain clustering manner for person images is provided. Since the clustering results of the multiple lenses are not affected by the quality of the person images, the reliability of the lens clustering is improved, and the reliability of the person image clustering is improved.

The application realizes a commodity search method with query-related multi-aspect explainability by means of a method in the field of artificial intelligence. The search information of an input commodity is searched and the query commodity result is fed back by using a multi-path query perception graph convolution network for explainable commodity search. The multi-path query perception graph convolution network for explainable commodity search comprises two components: a query perception graph convolution sorter and a query perception multi-path reasoner. The query perception graph convolution sorter models the representation of a user and a commodity according to different knowledge relationship domains in a knowledge graph by using a graph convolution network. The query perception multi-path reasoner is responsible for exploring a query-specific multi-path from the knowledge graph to meet the search intention of the user. The two components share basic parameters and are collaboratively trained to constitute a complete network. The method can significantly improve the retrieval performance and generate better explanations for the search result.

The application belongs to the technical field of artificial intelligence, and discloses a multi-behavior sequence recommendation system and method for capturing user multi-aspect preferences and intentions, which comprises a preprocessing module, a multi-aspect preference modeling module, a multi-aspect intention modeling module, a preference and intention fusion module and a probability output module. The preprocessing module pre-processes multi-type behavior data; the multi-aspect preference modeling module models user multi-aspect preferences through a multi-aspect projection mechanism; the multi-aspect intention modeling module models user multi-aspect intentions through a behavior detail perception LSTM and a preference-guided multi-aspect attention mechanism; the preference and intention fusion module adaptively integrates user preference and intention information through a multi-aspect preference and intention fusion mechanism; and the probability output module, which is connected to the preference and intention fusion module, predicts the next item and category that the user is interested in. The system can capture user multi-aspect preferences and intentions and obtain accurate prediction results.

The application discloses a zero-shot stance detection method and system based on multi-expert collaborative learning, which introduces multiple experts to learn the underlying multi-aspect features of text semantic expression, so as to improve the zero-shot stance classification accuracy of unknown targets. First, an expert model is constructed based on BERT, and different experts use different underlying outputs of BERT as text encoding to obtain different aspects of text semantic representation. Second, a gating mechanism is used to filter the effective feature aspects of the stance, so as to improve the feature quality of the stance prediction. Finally, the filtered multi-aspect semantic deconstruction features and high-level semantic features are comprehensively used to realize the detection of the text stance. The application is based on the deconstruction of the text semantic expression features, and the text semantic features are modeled in a fine-grained manner, so as to improve the feature transferability, obtain more effective features, and improve the zero-shot stance classification accuracy of unknown targets.

The application discloses a small sample target detection method based on contrast learning and multi-aspect distillation, constructs a small sample target detection network model based on contrast learning and multi-aspect distillation, carries out basic class basic training on the small sample target detection network model, obtains a small sample target detection basic class model, carries out new class fine-tuning training on the small sample target detection basic class model, obtains a final small sample target detection model, and finally detects small sample targets according to the final small sample target detection model. The method solves the problems that the traditional target detection method is prone to class confusion and weak information capturing capacity, greatly improves the capturing capacity of the detection model on target features, simultaneously strengthens foreground representation and reduces the interference of background information, and improves target detection performance.

The utility model discloses equipment capable of carrying out multi-aspect testing on a tested plastic cable tie, which relates to the technical field of design of plastic cable tie testing devices and comprises a fixed bottom plate, an environment regulation control unit and a tension detection unit, and supporting legs are respectively arranged at four corners of the lower side surface of the fixed bottom plate. The device comprises a fixed bottom plate, a control display is fixedly connected to the upper side surface of the fixed bottom plate, a control display screen is arranged on the control display, and an environment adjustment control unit and a tension detection unit are arranged at the position, located on the left side of the control display, of the upper side surface of the fixed bottom plate and comprise a detection fixing base, a supporting vertical rod, a threaded column and a movable sliding block. A detection fixing seat is fixedly connected to the surface of the inner bottom end of a protection cover in the environment adjustment control unit, during detection, the external environment can be adjusted, the plastic cable tie can be detected in multiple aspects, and inconvenience in use is not likely to be caused.

Disclosed examples create a multi-aspect object, the multi-aspect object represented using a class definition; assign a first capability to the multi-aspect object, the first capability to communicate with equipment in a control system; assign a second capability to the multi-aspect object, the second capability to communicate with the equipment in the control system; create a semantic data model in the multi-aspect object, the semantic data model to share information between the first capability and the second capability of the multi-aspect object; deploy the first capability of the multi-aspect object on a first runtime platform; and deploy the second capability of the multi-aspect object on a second runtime platform, the semantic data model to communicate between the first and second runtime platforms to share the information between the first and second capabilities of the multi-aspect object.

The embodiment of the invention provides a method and device for detecting an unauthorized operation behavior, a processor and a storage medium. The method comprises the following steps: taking a teller historical operation log of a working system, and establishing an employee menu transaction code peak baseline based on the teller historical operation log; a teller operation log and an employee transaction message of a working system and information safely provided by a terminal are obtained; based on the teller operation log and the employee menu transaction code peak baseline, judging whether suspicious operation exists or not; if the suspicious operation exists, judging whether an unauthorized alarm event exists or not based on the employee transaction message; and if the unauthorized alarm event exists, determining unauthorized attack event information based on the information safely provided by the terminal, and judging whether an unauthorized operation behavior exists based on the unauthorized attack event information. The method is used for performing multi-aspect judgment on the unauthorized operation behavior so as to improve the detection effect.