Techniques for graph based natural language processing
Techniques for graph based natural language processing are described. In one embodiment an apparatus may comprise a client service component operative on the processor circuit to receive a natural language user request from a device and to execute the natural language user request based on matched one or more objects and a social object relation component operative on the processor circuit to match the natural language user request to the one or more objects in an object graph, the object graph comprising token mappings for objects within the object graph, the token mappings based on data extracted from a plurality of interactions by a plurality of users of the network system, wherein the one or more objects are matched with the natural language user request based on the token mappings. Other embodiments are described and claimed.
1. A computer-implemented method, comprising:
receiving a natural language user request;
matching the natural language user request to one or more objects in an object graph, the object graph comprising a plurality of nodes interconnected by edges, the nodes representing related entities and the edges between the nodes corresponding to relationships between the entities and representing at least one of: a relationship between natural language words, a semantic understanding between the natural language words, or a correlation between the natural language words and the semantic understanding;
returning the matched at least one object in response to the natural language user request;
based on the matched at least one object, generating a proposed execution strategy responsive to the natural language user request;
generating an instruction configured to cause a user service component to display the proposed execution strategy; and
receiving an approval to execute the proposed execution strategy.
2. The method of claim 1 , the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings.
3. The method of claim 2 , wherein the token mappings are generated based on a frequency with which a plurality of users associate tokens with the objects in a plurality of interactions.
4. The method of claim 2 , wherein the token mappings are generated based on a success rate for executions of a plurality of natural language user requests by a plurality of users of the network system.
5. The method of claim 1 , further comprising executing the natural language user request based on the matched one or more objects in the object graph.
6. The method of claim 1 , the natural language user request mapped to one or more local objects stored in a locally cached version of the object graph.
7. The method of claim 1 , the natural language user request received at a network server.
8. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:
receive a natural language user request;
match the natural language user request to one or more objects in an object graph, the object graph comprising a plurality of nodes interconnected by edges, the nodes representing related entities and the edges between the nodes corresponding to relationships between the entities and representing at least one of: a relationship between natural language words, a semantic understanding between the natural language words, or a correlation between the natural language words and the semantic understanding;
return the matched at least one object in response to the natural language user request;
based on the matched at least one object, generate a proposed execution strategy responsive to the natural language user request;
generate an instruction configured to cause a user service component to display the proposed execution strategy; and
receive an approval to execute the proposed execution strategy.
9. The medium of claim 8 , the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings.
10. The medium of claim 9 , wherein the token mappings are generated based on a frequency with which a plurality of users associate tokens with the objects in a plurality of interactions.
11. The medium of claim 9 , wherein the token mappings are generated based on a success rate for executions of a plurality of natural language user requests by a plurality of users of the network system.
12. The medium of claim 8 , further comprising executing the natural language user request based on the matched one or more objects in the object graph.
13. The medium of claim 8 , the natural language user request mapped to one or more local objects stored in a locally cached version of the object graph.
14. The medium of claim 8 , the natural language user request received at a network server.
15. An apparatus, comprising:
a processor circuit on a device;
a client service component operative on the processor circuit to receive a natural language user request;
a social object relation component operative on the processor circuit to match the natural language user request to one or more objects in an object graph, the object graph comprising a plurality of nodes interconnected by edges, the nodes representing related entities and the edges between the nodes corresponding to relationships between the entities and representing at least one of: a relationship between natural language words, a semantic understanding between the natural language words, or a correlation between the natural language words and the semantic; and
an interface configured to:
return the matched at least one object in response to the natural language user request,
based on the matched at least one object, generating a proposed execution strategy responsive to the natural language user request,
generating an instruction configured to cause a user service component to display the proposed execution strategy, and
receiving an approval to execute the proposed execution strategy.
16. The apparatus of claim 15 , the object graph comprising one or more token mappings matching one or more objects in the object graph, the natural language user request matched to the one or more objects based on the one or more token mappings.
17. The apparatus of claim 16 , wherein the token mappings are generated based on a frequency with which a plurality of users associate tokens with the objects in a plurality of interactions.
18. The apparatus of claim 16 , wherein the token mappings are generated based on a success rate for executions of a plurality of natural language user requests by a plurality of users of the network system.
19. The apparatus of claim 15 , the processor circuit configured to execute the natural language user request based on the matched one or more objects in the object graph.
20. The apparatus of claim 15 , the natural language user request mapped to one or more local objects stored in a locally cached version of the object graph.