6 results about "Topic Maps" patented technology

Techniques for receiving, storing, analyzing, and utilizing raw content are disclosed. The system receives raw text from a user, including a first tag and second tags. The system identifies and removes formatting attributes in the raw text, including whitespace characters, to generate a normalized input. The system stores the normalized input in target dataset(s) and parses the normalized input for the first tag and the second tags. In this case, the first tag corresponds to one or more topics, and the second tags represent a computing system associated with corresponding portions of the normalized input. The system analyses the first tag and the second tags to identify the topics. The system generates one or more topic maps for the target dataset(s) based on the first tag and the one or more second tags. The topic map(s) include one or more references to content items within the target dataset(s).

Current generative AI systems using large language models (LLMs) face challenges including non-deterministic outputs, hallucinations, outdated information, and resource-intensive training. This disclosure introduces topic maps for constrained retrieval augmented generation to address these issues. The technique leverages existing LLMs while constraining outputs to specific, user-defined content domains. Topic maps, composed of topic names, descriptions, and relevant resource references, create a curated knowledge base that guides agent responses. This approach reduces hallucinations, improves consistency, and allows for dynamic updates without model retraining. The method involves receiving a query, identifying relevant topic maps, transmitting the query and references to an AI agent, and generating constrained responses. By providing a structured, updatable knowledge framework, this method enhances the accuracy, reliability, and adaptability of generative AI systems.

The application discloses a patent theme graph generation method and system based on deep semantic hierarchical clustering, comprising: obtaining a patent literature set PT to be generated into a patent theme graph; using a patent deep semantic representation model to perform semantic coding on each patent literature in the patent literature set PT, and obtaining a semantic representation vector matrix V={v1,...,v N}; inputting the semantic representation vector matrix V into a hierarchical clustering algorithm to obtain a hierarchical clustering tree structure corresponding to the patent literature set PT; generating a corresponding theme description for each non-leaf node on the hierarchical clustering tree structure; and combining the generated theme description and the hierarchical clustering tree structure into a patent theme graph with an upper and lower hierarchical structure. The patent theme graph generation method and system can help users quickly mine upper and lower hierarchical relationships of patent literatures at a theme level, meet the analysis needs of users for large-scale patent information, and improve the efficiency of patent analysis of users.

A method for generating topic maps includes receiving user data via an editor, transmitting the data to a remote device, synchronizing an access, monitoring a remote topic, updating a local topic, and causing the editor to display the local topic. A computing system includes one or more processors and a memory including computer executable instructions that, when executed by the one or more processors, cause the computing system to receive data via an editor, transmit the data to a remote device, synchronize an access, monitor a remote topic, update a local topic, and cause the editor to display the local topic. A non-transitory computer readable medium containing program instructions that when executed, cause a computer system to receive data via an editor, transmit the data to a remote device, synchronize an access, monitor a remote topic, update a local topic, and cause the editor to display the local topic.

The present invention provides a distance pre-school learning platform, including bilingual learning, using artificial intelligence algorithms, that combines the functionality of automatic recommendation of classes templates with their thematic matching and teacher support in planning and implementation of educational activities. The platform according to the invention uses educational scenarios assigned to specific thematic circles. Thanks to the use of Al algorithms and a tagging system, the platform automatically recommends appropriate activities, adapted to the language level of children and the subject of classes. The invention provides a computer-implemented method for recommending classes scenarios based on attributes and keywords, using artificial intelligence algorithms, in which classes scenarios, attributes and keywords are previously recorded in a database. The method comprises the following steps: providing attributes describing classes scenarios, the attributes comprising thematic circles with topics assigned thereto, presented as a topic map in a graph form, operative verbs and nouns, and providing keywords for each scenario; entering a query to the neural network containing at least one attribute and at least one keyword; filtering the database by neural networks to obtain the recommended classes scenario most consistent with the said set of attributes and keywords. Artificial intelligence algorithms are implemented using hybrid neural structures. The invention also provides a system for recommending classes scenarios based on attributes and keywords, configured and programmed for the implementation of the described method, including: a database containing pre-recorded classes scenarios, attributes and keywords; a hybrid neural network for recommending a classes scenario; a server or user terminal.

Current generative AI systems using large language models (LLMs) face challenges including non-deterministic outputs, hallucinations, outdated information, and resource-intensive training. This disclosure introduces topic maps for constrained retrieval augmented generation to address these issues. The technique leverages existing LLMs while constraining outputs to specific, user-defined content domains. Topic maps, composed of topic names, descriptions, and relevant resource references, create a curated knowledge base that guides agent responses. This approach reduces hallucinations, improves consistency, and allows for dynamic updates without model retraining. The method involves receiving a query, identifying relevant topic maps, transmitting the query and references to an AI agent, and generating constrained responses. By providing a structured, updatable knowledge framework, this method enhances the accuracy, reliability, and adaptability of generative AI systems.