| CPC G06F 16/345 (2019.01) [G06F 16/383 (2019.01); G06F 40/242 (2020.01); G06F 40/289 (2020.01)] | 20 Claims |
|
1. A method comprising:
receiving, by a device, a status inquiry for a service ticket from a customer device;
obtaining, by the device, a time series of documents associated with the service ticket;
determining, by the device, query scores for particular documents of the time series of documents based on a set of query terms;
determining, by the device, time scores for the particular documents based on timestamps associated with the particular documents;
computing, by the device, document relevancy scores for the particular documents based on a combination of the query scores and the time scores for the particular documents, wherein computing the document relevancy scores for the particular documents based on the combination of the query scores and the time scores for the particular documents includes:
computing a document relevancy score for a particular document as a product of the query score for the particular document and the time score for the particular document;
ordering, by the device, the particular documents based on the computed relevancy scores;
generating, by the device, a document summary by applying a document summarizer to the ordered particular documents, wherein the document summarizer includes a machine learning model trained on a corpus of service ticket documents associated with service tickets in different phases of resolution; and
providing, by the device, the generated document summary to the customer device as a response to the received status inquiry.
|