Method and system for generating dynamic text responses for display after a search
A system and method for operating the same includes a language processing module generating a search request text signal and determining identified data from the search request text signal. A search module generates search results in response to the search request text signal. A dialog manager classifies the search request text signal into a response classification associated with a plurality of templates, selects a first template from the plurality of templates in response to the response classification and corrects search results in response to the identified data and the template to form a corrected response signal. A device receives and displays the corrected response signal.
1. A method comprising:
forming, by a processing system including a processor, a last merged context object from a first intent object and a combination of all prior related search requests after a previous context switch, wherein the first intent object includes text of a first audible request;
receiving, by the processing system, a second audible request;
generating, by the processing system, a second intent object from the second audible request;
using, by the processing system, a state vector machine to determine whether a new context switch has occurred based on whether the last merged context object and the second intent object are related; and
responsive to determining that the new context switch has occurred, performing, by the processing system, a subsequent content search based on the last merged context object and the second intent object.
2. The method of claim 1 , wherein determining whether the last merged context object and the second intent object are related is based on keywords in the last merged context object and the second intent object.
3. The method of claim 1 , further including generating, after receiving the first audible request and by the processing system, a text signal, wherein the generating the first intent object is performed from the text signal.
4. The method of claim 1 , wherein receiving the first audible request includes receiving a search request.
5. The method of claim 1 , wherein forming the last merged context object includes timestamping the last merged context object.
6. The method of claim 1 , further including:
after forming the last merged context object, encoding, by the processing system, the last merged context object to form a context token; and
communicating, by the processing system, the context token to a first device.
7. The method of claim 1 , wherein determining whether the last merged context object and the second intent object are related includes classifying keyword or qualifiers from the second audible request.
8. The method of claim 1 , wherein determining whether the last merged context object and the second intent object are related includes determining a classification weight in response to the second intent object.
9. The method of claim 8 , further including adjusting the classification weight responsive to a connector word.
10. The method of claim 8 , further including adjusting the classification weight responsive to a switching word.
11. The method of claim 9 , further including adjusting the classification weight responsive to a reference word.
12. The method of claim 6 , wherein determining whether the last merged context object and the second intent object are related includes using a state vector machine based on the last merged context object, the second intent object and a trained model.
13. A system comprising:
a conversation manager forming a last merged context object from a first intent object and a combination of all prior related search requests after a previous context switch, wherein the first intent object includes text of a first audible request; and
a first device receiving a second audible signal,
said conversation manager generating a second intent object from the second audible signal and using a state vector machine to determine whether a new context switch has occurred based on whether the last merged context object and the second intent object are related, and
responsive to the new context switch occurring, said first device performing a subsequent content search based on the last merged context object and the second intent object.
14. The system of claim 13 , wherein the first audible request includes a first search request and the second audible signal includes a second search request.
15. The system of claim 13 , wherein the conversation manager further includes a classifier module to determine whether the last merged context object and the second intent object are related based on keywords in the last merged context object and the second intent object.
16. The system of claim 13 , wherein the conversation manager further includes a classifier module to determine whether the last merged context object and the second intent object are related by classifying keyword or qualifiers from the second audible signal.
17. The system of claim 13 , wherein the conversation manager further includes a classifier module to determine whether the last merged context object and the second intent object are related by determining a classification weight in response to the second intent object.
18. A machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations including:
forming a last merged context object from a first intent object and a combination of all prior related search requests after a previous context switch, wherein the first intent object includes text of a first audible request;
generating a second intent object from a second audible request;
using a state vector machine to determine whether a new context switch has occurred based on whether the last merged context object and the second intent object are related; and
responsive to determining that the new context switch has occurred, performing a subsequent content search based on the last merged context object and the second intent object.