7 results about "Predicate logic" patented technology

The invention discloses a logic knowledge construction method and device based on a large language model and logic programming, electronic equipment and a storage medium, and belongs to the field of artificial intelligence knowledge engineering. According to the method, automatic conversion from multi-source heterogeneous knowledge to machine reasonable logic knowledge is realized through combination of semantic understanding capability of a large language model and standardized processing of logic programming. The method specifically comprises the steps of obtaining unstructured / semi-structured original knowledge data, performing entity relationship recognition and predicate logic detection by utilizing a large language model to generate a preliminary logic expression, performing grammar normalization processing to form standard logic facts and rules, and constructing a consistent logic knowledge base through a conflict detection and resolution mechanism. According to the method, a mixed conversion framework of natural language and formalized logic is innovatively provided, and the maintainability and expandability of the knowledge base are remarkably improved by introducing timestamp metadata, a rule dependence graph and an incremental updating mechanism. The technology provides structured logic support for subsequent large model reasoning, and can be widely applied to intelligent questions and answers, decision support and other scenes requiring precise logic reasoning.

The invention relates to the technical field of knowledge management and artificial intelligence, and discloses a knowledge management system based on artificial intelligence big data. The system comprises knowledge flow capture, symbol reasoning, neural embedding, strategy synthesis and strategy deployment components. The system generates structured knowledge through multi-modal data acquisition and cleaning; performing symbolic reasoning by utilizing predicate logic and a rule base, and constructing a symbolic knowledge graph; a deep learning model is adopted to generate low-dimensional vector representation; fusing the symbolized knowledge graph and the vector representation, and generating a knowledge management strategy through a strategy gradient algorithm; and asynchronously executing the strategy in the cloud environment. According to the scheme, through combination of symbol reasoning and a neural network technology, interpretability and logic preciseness of a knowledge processing process are ensured, and meanwhile, the dynamic adaptive capacity and decision accuracy of system strategy generation are improved.

This invention provides a method, apparatus, device, and medium for identifying the intent of aerial targets, comprising the following steps: acquiring continuously collected multidimensional feature data of aerial targets to construct a target temporal feature dataset, and preprocessing and labeling each sample in the dataset with target intent tags to construct a training dataset; constructing a domain rule set expressing the logical constraint relationships between target intents using first-order predicate logic rules; constructing a neural symbolic joint reasoning model, and jointly training the neural symbolic joint reasoning model using the training dataset and the domain rule set to obtain a trained neural symbolic joint reasoning model; and predicting the target intent based on the temporal feature data of the aerial target to be predicted using the trained neural symbolic joint reasoning model. This invention achieves an organic unity of data-driven and knowledge-driven approaches by embedding logical rules in a differentiable form into the training objective and reasoning structure of the neural network.

The invention provides an aerial target intention recognition method, device and equipment and a medium, and the method comprises the following steps: obtaining continuously collected multi-dimensional feature data of an aerial target to construct a target time sequence feature data set, and carrying out the preprocessing and target intention label labeling of each sample in the data set to construct a training data set; constructing a domain rule set which is expressed by a first-order predicate logic rule and describes a logic constraint relationship between target intentions; constructing a neural symbol joint inference model, and performing joint training on the neural symbol joint inference model by using the training data set and the domain rule set to obtain a trained neural symbol joint inference model; and performing target intention prediction on the time sequence characteristic data of the air target to be predicted based on the trained neural symbol joint inference model. According to the method, the logic rule is embedded into the training target and reasoning structure of the neural network in a microform, so that organic unification of data driving and knowledge driving is realized.

Example computer executable instructions for determining a consumer's offer eligibility using a predicate logic tree against sets of input data are provided. In particular, the disclosed examples recite a rewards engine capable of determining a consumer's offer eligibility using a predicate logic tree against sets of input data. The rewards engine applies rules that are relevant to a particular deal offered by a retail establishment to the consumer's records to determine the consumer's offer eligibility. In some examples, the rewards engine sorts or partially sorts some or all of the consumer's records to determine the consumer's offer eligibility.

The invention relates to a business rule processing method and device, computer equipment and a storage medium, and relates to the technical field of data processing, business logic is formally described as a proposition structure based on predicate logic, and proposition metadata in a JSON format is utilized to drive front-end dynamic rendering, so that the business rule processing efficiency is improved. According to the method, thorough decoupling of the front end and the rear end on business rule processing is achieved, when data items or judgment logic related to business rules are changed, only the rear end needs to update proposition metadata and analysis logic, the front end can be automatically adapted without any modification, expandability and maintainability of the system are improved, and meanwhile, the data items or the judgment logic related to the business rules can be automatically decoupled. According to the method, a quadruple structure of predicate types, operators, operands and quantifiers is introduced, so that complex business rules with limiting conditions can be accurately described, the problem that related schemes are insufficient in modeling capacity for an internal structure of a single proposition is solved, the flexibility and accuracy of business rule expression are enhanced, and the business rule modeling efficiency is improved. And the repeated development cost in multiple scenes is effectively reduced.

The application relates to the technical field of knowledge management and artificial intelligence, and discloses a knowledge management system based on artificial intelligence big data. The system comprises knowledge flow capturing, symbolic reasoning, neural embedding, strategy synthesis and strategy deployment components. The system generates structured knowledge through multi-modal data acquisition and cleaning; carries out symbolic reasoning by using predicate logic and a rule base, constructs a symbolic knowledge graph; generates low-dimensional vector representation by using a deep learning model; fuses the symbolic knowledge graph and the vector representation, generates a knowledge management strategy by using a strategy gradient algorithm; and asynchronously executes the strategy in a cloud environment. The scheme combines symbolic reasoning and neural network technology, ensures the explainability and logical rigor of the knowledge processing process, and improves the dynamic adaptability and decision accuracy of the system strategy generation.