Back to results
US 11,768,893 B2Granted
Concept networks and systems and methods for the creation, update and use of same in artificial intelligence systems
AssigneeRealpage, Inc.
InventorsRichard Lawrence Stillwell, Jr., Carter Myers Brooking, Jed Jackoway, Brandon Michael Burkett
Life of this patent
Estimating the term…
Abstract
Systems and methods for concept based searching or recommendation based on a concept networks are disclosed. More particularly, embodiments of a concept based approach to the search and analysis of data, including the creation, update or use of concept networks in searching and analyzing data are disclosed, including embodiments of the usage of such concept networks in artificial intelligence systems that are capable of utilizing concepts expressed by users to return or evaluate associated entities or content.
Claims14
A system, comprising:
- a data store in which a concept network is stored;
- wherein the concept network comprises a plurality of nodes, the plurality of nodes including a first node and a second node;
- and
- a non-transitory computer readable medium comprising instructions for:
- presenting, via a widget and on a user device, a chat driven interface comprising a chat portion and a display portion;
- receiving a request via the chat portion of the chat driven interface;
- wherein the request includes natural language data;
- analyzing the request using a natural language processor;
- extracting, using the analysis of the request by the natural language processor, a determined concept associated with the request;
- wherein the determined concept is associated with the concept network stored in the data store;
- and
- wherein the determined concept is represented by the first node of the plurality of nodes of the concept network;
- accessing the concept network associated with the determined concept;
- selecting the second node from the plurality of nodes of the concept network;
- wherein the first and second nodes of the plurality of nodes of the concept network have a navigational path between them;
- wherein the navigational path includes a set of relationships between the first and second nodes;
- and
- wherein the second node is associated with content relevant to the determined concept and to the request;
- determining a first score for the second node;
- wherein the first score is associated with a first relationship of the set of relationships;
- and
- wherein the first score is determined by traversing the first relationship from the first node to the second node;
- determining a second score for the second node;
- wherein the second score is associated with a second relationship of the set of relationships;
- and
- wherein the second score is determined by traversing the second relationship from the second node to the first node;
- wherein the scores are based on weights on the relationships indicating degrees of affinity between the first and second nodes;
- presenting, via the chat portion of the chat driven interface, a response to the request;
- wherein the response is based at least in part on the relevant content associated with the second node;
- and
- wherein the response includes additional natural language data;
- presenting, via the display portion of the chat driven interface, the relevant content;
- wherein the chat portion of the chat driven interface and the display portion of the chat driven interface are kept in synchronicity;
- updating, based on previous interactions with the chat portion of the chat driven interface, the natural language processor to refine the analysis of the natural language processor with respect to future requests;
- and
- updating, based on previous requests, frequency of appearance of related content, frequency with which navigational paths are traversed, and interactions with presented content via the chat driven interface, the concept network including the plurality of nodes, the plurality of relationships, and the weights on the relationships.
33 more elements
A method, comprising:
- storing a concept network in a data store;
- wherein the concept network comprises a plurality of nodes, the plurality of nodes including a first node and a second node;
- presenting, via a widget and on a user device, a chat driven interface comprising a chat portion and a display portion;
- receiving, using one or more processors and via the chat portion of the chat driven interface, a request;
- wherein the request includes natural language data;
- analyzing the request using a natural language processor;
- extracting, using the one or more processors and the analysis of the request by the natural language processor, a determined concept associated with the request;
- wherein the determined concept is associated with the concept network stored in the data store;
- and
- wherein the determined concept is represented by the first node of the plurality of nodes of the concept network;
- accessing, using the one or more processors, the concept network associated with the determined concept;
- selecting, using the one or more processors, the second node from the plurality of nodes of the concept network;
- wherein the first and second nodes of the plurality of nodes of the concept network have a navigational path between them;
- wherein the navigational path includes a set of relationships between the first and second nodes;
- and
- wherein the second node is associated with content relevant to the determined concept and to the request;
- determining, using the one or more processors, a first score for the second node;
- wherein the first score is associated with a first relationship of the set of relationships;
- and
- wherein the first score is determined by traversing the first relationship from the first node to the second node;
- determining a second score for the second node;
- wherein the second score is associated with a second relationship of the set of relationships;
- and
- wherein the second score is determined by traversing the second relationship from the second node to the first node;
- wherein the scores are based on weights on the relationships indicating degrees of affinity between the first and second nodes;
- presenting, using the one or more processors and via the chat portion of the chat driven interface, a response to the request;
- wherein the response is based at least in part on the relevant content associated with the second node;
- and
- wherein the response includes additional natural language data;
- presenting, using the one or more processors and via the display portion of the chat driven interface, the relevant content;
- wherein the chat portion of the chat driven interface and the display portion of the chat driven interface are kept in synchronicity;
- updating, using the one or more processors and based on previous interactions with the chat portion of the chat driven interface, the natural language processor to refine the analysis of the natural language processor with respect to future requests;
- and
- updating, using the one or more processors and based on previous requests, frequency of appearance of related content, frequency with which navigational paths are traversed, and interactions with presented content via the chat driven interface, the concept network including the plurality of nodes, the plurality of relationships, and the weights on the relationships.
31 more elements
Dependencies are inferred from the claim text.