Abstract:
A method and apparatus for detection of relationships between objects in a meta-model semantic network is described. Semantic objects and semantic relations of a meta-model of business objects are generated from a meta-model semantic network. The semantic relations are based on connections between the semantic objects. A probability model of terminology usage in the semantic objects and the semantic relations is generated. A neural network is formed based on usage of the semantic objects, the semantic relations, and the probability model. The neural network is integrated with the semantic objects, the semantic relations, and the probability model to generate a contextual network. The generated probability model is integrated with semantic objects and neural networks for form parallel networks.
Abstract:
Methods and systems are provided for processing natural language queries. Such methods and systems may receive a natural language query from a user and generate corresponding semantic tokens. Information may be retrieved from a knowledge base using the semantic tokens. Methods and systems may leverage an interpretation module to process and analyze the retrieved information in order to determine an intention associated with the natural language query. Methods and systems may leverage an actuation module to provide results to the user, which may be based on the determined intention.
Abstract:
Providing a natural-language interface to a repository includes retrieving information from at least one repository, and generating a computer-readable ontology using the information. The computer-readable ontology is configured for use in interpreting user-entered natural-language statements regarding the at least one repository. A computer system including at least one repository has an ontology-generating module generating a computer-readable ontology using information retrieved from the at least one repository. The ontology may be created in any or all of several forms, such as a separate entity, a pointer structure or an index.
Abstract:
Operations to represent a computer system state to a user include maintaining a model in a computer system. The model is updated at times and represents a current state of the computer system. The model uses formal-language statements to associate each of several predefined goals with at least one of several predefined actions that can be performed in the computer system to accomplish the associated predefined goal. The operations comprise providing an output to a user regarding the current state of the computer system, the output comprising a natural-language statement generated using at least one of the formal-language statements. A statement generating module may include a text planner, a grammar, a lexicon, a translator or a text post-processor.
Abstract:
Providing a natural-language interface to a repository includes retrieving information from at least one repository, and generating a computer-readable ontology using the information. The computer-readable ontology is configured for use in interpreting user-entered natural-language statements regarding the at least one repository. A computer system including at least one repository has an ontology-generating module generating a computer-readable ontology using information retrieved from the at least one repository. The ontology may be created in any or all of several forms, such as a separate entity, a pointer structure or an index.
Abstract:
Methods and systems are provided for processing natural language queries. Such methods and systems may receive a natural language query from a user and generate corresponding semantic tokens. Information may be retrieved from a knowledge base using the semantic tokens. Methods and systems may leverage an interpretation module to process and analyze the retrieved information in order to determine an intention associated with the natural language query. Methods and systems may leverage an actuation module to provide results to the user, which may be based on the determined intention.
Abstract:
In an embodiment, a method is provided for utilizing a meta-model semantic network. In this method, a meta-model of the enterprise data is obtained. The meta-model provides semantic information regarding a definition of a business object. The meta-model is then used to generate a rule definition that maps enterprise data to a semantic object definition and a semantic relation definition. With the rule definition, embodiments may then generate a semantic object and a semantic relation from data extracted from the enterprise data. The semantic object and semantic relation are stored in the meta-model semantic network.
Abstract:
An input handler may receive natural language input associated with a command from a user through a user interface, and a language parser may parse the natural language input to determine parsed natural language input. A context monitor may receive context information associated with the user, and a context parser may parse the context information to obtain parsed context information associated with the natural language input and with the command. A command interpreter may interpret the parsed natural language input, using the parsed context information, to thereby determine the command.
Abstract:
User interaction with a computer system is supported by maintaining, in a computer system, a model comprising several concepts having properties associated therewith and any relationships existing between the several concepts. A current state of the several concepts, properties and relationships reflects a real-world situation that involves a user of the computer system. An output is made to the user that identifies at least a subset of several predefined goals, the model indicating the subset as being possible to accomplish based on the current state. At least a first action of several predefined actions in the computer system is performed, the model associating the several predefined actions with accomplishing respective ones of the several predefined goals. The first action is identified as associated with accomplishing a first goal that the user selects from the subset. The current state is updated based on performing at least the first action.
Abstract:
Operations to manage statements relating to a computer system state include obtaining, in a computer system and from any of several sources, statements that relate to a current state of the computer system. Each statement comprises several elements. The operations comprise assigning focus values to the elements of each statement, each focus value indicating a relevance of the element to the current state of the computer system. The operations comprise identifying a subset of the statements based on the focus values. The operations comprise making a first output to a user, the first output being selected from several predefined outputs using the subset of the statements. The output may represent the current state to the user or it may present at least one of several predefined goals to the user for selection, the at least one goal being identified as being possible to accomplish based on the current state.