Concept networks and systems and methods for the creation, update and use of same in artificial intelligence systems

1. 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.

2. The system of claim 1 ,

wherein the navigational path further comprises a set of intervening nodes between the first node and the second node;

wherein the first score is based on each of the weights assigned to a first subset of relationships of the set of relationships traversed from the first node to the second node;

wherein the second score is based on each of the weights assigned to a second subset of relationships of the set of relationships traversed from the second node to the first node; and

wherein the second node represents a physical entity associated with the determined concept.

3. The system of claim 1 ,

wherein the plurality of nodes are scored; and

wherein a highest score is given to a node with the greatest degree of affinity to the first node in comparison to other nodes in the plurality of nodes.

4. The system of claim 3 , wherein the non-transitory computer medium further comprises instructions for:

returning, to the chat driven interface, relevant content associated with the highest scoring node.

5. The system of claim 4 ,

wherein the degree of affinity is based on the navigational path;

wherein the degree of affinity is based on how far away a particular node is from the determined concept; and

wherein the highest score is given to a node with the shortest navigational path to the determined concept.

6. The system of claim 1 ,

wherein an edge connects a set of two nodes from the plurality of nodes together, the edge representing a set of relationships between the set of two nodes; and

wherein the set of relationships is associated with the weight indicating the degree of affinity between the set of two nodes connected by the edge.

7. The system of claim 6 ,

wherein the set of two nodes and the edge are presented as a trie;

wherein a first level of the trie has the first node;

wherein a second level of the trie is connected to the first level through the edge; and

wherein the second level has at least one node that is associated with a sub-concept of the first node.

8. 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.

9. The method of claim 8 ,

wherein the navigational path further comprises a set of intervening nodes between the first node and the second node;

wherein the first score is based on each of the weights assigned to a first subset of relationships of the set of relationships traversed from the first node to the second node;

wherein the second score is based on each of the weights assigned to a second subset of relationships of the set of relationships traversed from the second node to the first node; and

wherein the second node represents a physical entity associated with the determined concept.

10. The method of claim 8 ,

wherein the plurality of nodes are scored; and

wherein a highest score is given to a node with the greatest degree of affinity to the first node in comparison to other nodes in the plurality of nodes.

11. The method of claim 10 , further comprising:

returning, to the chat driven interface and using the one or more processors, relevant content associated with the highest scoring node.

12. The method of claim 11 ,

wherein the degree of affinity is based on the navigational path;

wherein the degree of affinity is based on how far away a particular node is from the determined concept; and

wherein the highest score is given to a node with the shortest navigational path to the determined concept.

13. The method of claim 8 ,

wherein an edge connects a set of two nodes from the plurality of nodes together, the edge representing a set of relationships between the set of two nodes; and

wherein the set of relationships is associated with the weight indicating the degree of affinity between the set of two nodes connected by the edge.

14. The method of claim 13 ,

wherein the set of two nodes and the edge are presented as a trie;

wherein a first level of the trie has the first node;

wherein a second level of the trie is connected to the first level through the edge; and

wherein the second level has at least one node associated with a sub-concept of the first node.