10 results about "Markov logic network" patented technology

The embodiment of the invention discloses an intelligent reasoning method and device based on neural symbols and a medium, and relates to the technical field of artificial intelligence, the method comprises the steps that user input information corresponding to a user and a pre-constructed mixed domain knowledge base are acquired, and the mixed domain knowledge base comprises a first-order predicate logic rule base and a closed Markov logic network; analyzing the user input information, determining an input feature vector, performing neural network reasoning on the input feature vector through a pre-constructed neural reasoning module, and determining corresponding pseudo tag information; and determining a candidate rule through a pre-constructed symbol reasoning module according to the pseudo-tag information and a first-order predicate logic rule base, so as to carry out collaborative reasoning on the pseudo-tag information and the candidate rule by utilizing a closed Markov logic network, and determine corresponding reasoning knowledge information.

The invention is suitable for the technical field of artificial intelligence and multi-modal reasoning, and provides a neural symbol reasoning method and system for multi-modal information processing, and the method comprises the following steps: obtaining multi-modal input data; respectively extracting semantic attribute representations of the image data and the text data on a predefined attribute set to obtain a multi-modal semantic attribute representation; mapping the multi-modal semantic attribute representation into a predicate in a first-order logic form, and constructing a symbolized multi-modal attribute fact set; inputting the multi-modal attribute fact set and a logic rule in a pre-constructed first-order logic knowledge base into a Markov logic network for reasoning to obtain a reasoning result; and integrating the reasoning results, and generating an interpretable decision result and a reasoning logic link. According to the method, multi-modal shared attribute symbols are taken as bridges, information fusion, conflict resolution and high-level consistency constraint among multiple modals are realized, and a reasoning result with interpretability, high robustness and strong generalization ability can be obtained.

The invention discloses an enterprise core talent loss analysis method based on a Markov logic network. The method comprises the following steps: S1, collecting a multi-dimensional data set related to enterprise core talent loss; s2, generating a structured multi-dimensional data set; s3, forming an enterprise core talent loss feature set; s4, constructing an initial improved Markov logic network model by using the enterprise core talent loss feature set; s5, forming an optimized causal path structure; and S6, updating the improved Markov logic network model according to the optimized Snake control path, performing online reasoning and risk assessment on the updated improved Markov logic network model by using enterprise core talent loss related data collected in real time, and outputting a loss risk assessment result of each core talent. According to the method, the adaptive capacity of the model to the individual difference of the employees and the modeling depth of a causal chain are remarkably improved, and a more interpretable loss early warning basis is provided for enterprise managers.

The present invention relates to a method for extracting a molecular structural formula, a computer-readable medium, and a computing device. The method for extracting a molecular structural formula according to the present invention includes: a target detection step of detecting a molecular structural formula in an information source file and segmenting out a molecular structural formula image including the molecular structural formula from the information source file; a graphic recognition step of performing graphic recognition on the molecular structural formula image to obtain a character part and a skeleton part of the molecular structural formula; a feature point marking step of marking feature points in the skeleton part as first type feature points or second type feature points, the skeleton part including one or more line segments, and the feature points including endpoints of the one or more line segments; and a connection relationship inference step of using a Markov logic network to infer connection relationships between first type feature points, between second type feature points, and between first type feature points and second type feature points according to a predefined inference formula.

The invention relates to a knowledge graph reasoning method oriented to information with time information, and belongs to the field of knowledge graph reasoning. The method comprises the following steps: initializing acquired intelligence with time information, vectorizing a head entity and a tail entity in a fact by utilizing embedded learning, and capturing a time dependency relationship of a timestamp sequence to generate high-dimensional time; using a scoring function to score unknown facts in the knowledge graph and then converting the unknown facts into approximate posterior probabilities of the unknown facts; generating a Markov logic network by using a time logic rule mined from the knowledge graph, and establishing a known and unknown fact joint probability distribution model for solving an unknown fact probability; and iteratively solving the joint probability distribution model by using variation reasoning and taking the approximate posterior probability of the unknown fact as initial input, and predicting the unknown fact. According to the method, stable prediction under the sparse sample condition is realized, and the method has relatively high information extrapolation capability.

The application discloses a complex action recognition method and device based on a learnable Markov logic network, comprising: using a policy network to automatically learn a set of logic rules corresponding to each action from training data; cutting a video to be detected into a plurality of video clips, and calculating a confidence score for a <action participant, visual relationship, object> triple in each video clip; inputting the set of logic rules and the confidence scores of all triples in a video clip into an improved Markov logic network to obtain the occurrence probability of each action in the video clip; and obtaining an action recognition result of the video to be detected according to the occurrence probability. The application does not need to rely on the definition of a domain expert, has significant interpretability and good compatibility and efficiency, and can not only recognize the category of an action, but also locate the position of the action in a video clip.

The invention relates to an intelligence knowledge graph completion method based on knowledge and data dual drive, and belongs to the field of knowledge graph reasoning. The method comprises the steps of performing intelligence entity extraction and intelligence relationship extraction based on acquired intelligence data to obtain an entity relationship triple representing intelligence facts, and constructing an intelligence knowledge graph; calculating to obtain an approximate posterior distribution probability of each intelligence fact by constructing a fact establishment possibility evaluation function; constructing a Markov logic network, and establishing a joint probability distribution model of known information facts and missing information facts; and improving an optimization function of the variational reasoning calculation process based on the approximate posterior distribution probability, and solving the joint probability distribution model based on the step E and the step M of the variational reasoning calculation process to obtain missing intelligence. According to the method, logic rules and neural network embedded representation are combined, efficient reasoning is achieved, and complex and diversified intelligence reasoning tasks can be conducted on a large-scale intelligence knowledge graph.

This invention relates to the fields of artificial intelligence and multimodal reasoning technology, and provides a neural symbolic reasoning method and system for multimodal information processing. The method includes the following steps: acquiring multimodal input data; extracting semantic attribute representations of image data and text data on a predefined attribute set to obtain multimodal semantic attribute representations; mapping the multimodal semantic attribute representations to predicates in first-order logic form to construct a symbolic multimodal attribute fact set; inputting the multimodal attribute fact set and logical rules from a pre-constructed first-order logic knowledge base into a Markov logic network for reasoning to obtain a reasoning result; integrating the reasoning result to generate an interpretable decision result and a reasoning logic chain. This invention uses shared attribute symbols across multiple modalities as a bridge to achieve information fusion, conflict resolution, and high-level consistency constraints among modalities, resulting in reasoning results with interpretability, high robustness, and strong generalization ability.

The invention discloses a photovoltaic facility operation and maintenance decision-making method based on a knowledge graph, and the method comprises the steps: S1, constructing the knowledge graph, and building equipment, fault modes, feature parameter nodes and causal association; s2, performing state diagnosis based on an improved Markov logic network, and obtaining an equipment state probability, a fault propagation chain and an influence degree by using a structure regularization factorization model and a confidence degree adjustment mechanism; s3, constructing an operation and maintenance index system, extracting risks, fault influences and performance degradation, and forming an evaluation vector in combination with the cost and the power generation recovery rate; s4, optimizing an operation and maintenance strategy based on an improved VIKOR method, introducing an index coupling degree matrix and a compromise correction factor, and calculating group utility, individual regret and a compromise evaluation value; and S5, outputting an operation and maintenance decision, generating priority and alternative schemes, and providing a basis for fault chain interpretation and weight correction. Intelligent diagnosis and operation and maintenance auxiliary decision making of the photovoltaic facility are realized, the operation and maintenance efficiency is improved, the fault risk is reduced, and the power generation income is optimized.

The present disclosure relates to a method, device and medium for performing retrosynthesis analysis on a compound molecule. A method for performing retrosynthesis analysis on a compound molecule is provided, comprising: determining probability graph weights of single-step reactions of a Markov logic network based on actual reaction learning data, thereby obtaining a trained Markov logic network; receiving an encoded molecular structure of a target compound; inputting the encoded molecular structure into the trained Markov logic network, and predicting a plurality of candidate retrosynthesis paths of the target compound through the Markov logic network; inputting the plurality of candidate retrosynthesis paths into a reinforcement learning model, training the reinforcement learning model based on existing actual reaction processes, so that a path consistent with an actual synthesis path obtains a reward, and updating a transition matrix in the reinforcement learning model; and determining one or more selected retrosynthesis paths from the plurality of candidate retrosynthesis paths by using the finally obtained transition matrix through the reinforcement learning model.