Content discovery systems and methods

1. A computer implemented method for identifying one or more documents of potential relevance to an input query, the method comprising:

receiving, in an issue ticket creation interface, issue ticket information including input text entered into an input field of the issue ticket creation interface;

generating an input query using the issue ticket information;

processing the input query to generate an input query vector;

accessing document records from a record database, each document record associated with an issue ticket in an issue tracking system and including a document vector;

generating a document similarity score in respect of each accessed document record, the document similarity score for a given document record being generated using the document vector for the given document record and the input query vector, the document similarity score for a given document record indicating a similarity of the input query to an issue ticket that the given document record is in respect of; and

identifying one or more potentially relevant document records based on their document similarity scores.

2. The computer implemented method of claim 1 , further comprising:

processing the input query to identify one or more products, and wherein

accessing document records from a record database, comprises accessing only document records associated with at least one of the one or more products identified.

3. The computer implemented method of claim 1 , wherein:

each document record further includes a document weight;

the method further comprises generating a weighted document similarity score in respect of each accessed document record, the weighted document similarity score for a given document record being generated based on the document vector for the given document record, the document weight for the given document record, and the input query vector; and

the one or more potentially relevant document records are identified based on their weighted document similarity scores.

4. The computer implemented method of claim 1 , wherein processing the input query to generate an input query vector comprises:

tokenizing input text of the input query to identify input text sentences and input text document words;

processing the tokenized input text to generate an initial input text vector; and

normalizing the initial input text vector to generate the input query vector.

5. The computer implemented method of claim 4 , wherein processing the tokenized input text to generate the initial input text vector comprises:

retrieving, from a language model, word vectors in respect of each relevant word identified in the input text; and

summing the retrieved word vectors to generate the initial input text vector.

6. The computer implemented method of claim 4 , wherein processing the tokenized input text to generate the initial input text vector comprises:

calculating a weighted word vector for each relevant word identified in the input text; and

summing the weighted word vectors to generate the initial input text vector.

7. The computer implemented method of claim 6 , wherein calculating a weighted word vector for a given word comprises:

retrieving, from a language model, a word vector in respect of the given word;

retrieving, from a frequency model, a training set frequency in respect of the given word, the training set frequency in respect of the given word being the frequency of the given word in a training set of data;

calculating the frequency of the given word in the input text; and

applying a term frequency-inverse input text frequency weighting to the retrieved word vector, the term frequency being the training set frequency in respect of the given word and the input text frequency being a frequency of the given word in the input text.

8. The computer implemented method of claim 1 , wherein the input query is received from an issue tracking system and the method further comprises:

retrieving documents associated with the one or more potentially relevant document records identified; and

communicating the retrieved documents to the issue tracking system.

9. The computer implemented method of claim 1 , wherein the input query is received from an issue tracking system and the method further comprises:

retrieving document links associated with the one or more potentially relevant document records identified, a document link in respect of a given document record providing access to a document associated with the given document record; and

communicating the document links to the issue tracking system.

10. A computer system comprising:

a processor;

a communication interface; and

a non-transitory computer-readable storage medium storing sequences of instructions, which when executed by the processor, cause the processor to implement a method comprising:

receiving, in an issue ticket creation interface, issue ticket information including input text entered into an input field of the issue ticket creation interface;

generating an input query using the issue ticket information

processing the input query to generate an input query vector;

accessing document records from a record database, each document record associated with an issue ticket in an issue tracking system and including a document vector;

generating a document similarity score in respect of each accessed document record, the document similarity score for a given document record being generated using the document vector for the given document record and the input query vector, the document similarity score for a given document record indicating a similarity of the input query to an issue ticket that the given document record is in respect of;

identifying one or more potentially relevant document records based on their document similarity scores.

11. The computer system of claim 10 , wherein the method the sequences of instructions cause the processor to implement further comprises:

processing the input query to identify one or more products, and wherein

accessing document records from a record database, comprises accessing only document records associated with at least one of the one or more products identified.

12. The computer system of claim 10 , wherein:

each document record further includes a document weight;

the method further comprises generating a weighted document similarity score in respect of each accessed document record, the weighted document similarity score for a given document record being generated based on the document vector for the given document record, the document weight for the given document record, and the input query vector; and

the one or more potentially relevant document records are identified based on their weighted document similarity scores.

13. The computer system of claim 11 , wherein processing the input query to generate an input query vector comprises:

tokenizing input text of the input query to identify input text sentences and input text document words;

processing the tokenized input text to generate an initial input text vector; and

normalizing the initial input text vector to generate the input query vector.

14. The computer system claim 13 , wherein processing the tokenized input text to generate the initial input text vector comprises:

retrieving, from a language model, word vectors in respect of each relevant word identified in the input text; and

summing the retrieved word vectors to generate the initial input text vector.

15. The computer system of claim 13 , wherein processing the tokenized input text to generate the initial input text vector comprises:

calculating a weighted word vector for each relevant word identified in the input text; and

summing the weighted word vectors to generate the initial input text vector.

16. The computer system of claim 15 , wherein calculating a weighted word vector for a given word comprises:

retrieving, from a language model, a word vector in respect of the given word;

retrieving, from a frequency model, a training set frequency in respect of the given word, the training set frequency in respect of the given word being the frequency of the given word in a training set of data;

calculating the frequency of the given word in the input text; and

applying a term frequency-inverse input text frequency weighting to the retrieved word vector, the term frequency being the training set frequency in respect of the given word and the input text frequency being a frequency of the given word in the input text.

17. The computer system of claim 10 , wherein the input query is received from an issue tracking system and wherein the method the sequences of instructions cause the processor to implement further comprises:

retrieving documents associated with the one or more potentially relevant document records identified; and

communicating the retrieved documents to the issue tracking system.

18. The computer system of claim 10 , wherein the input query is received from an issue tracking system and wherein the method the sequences of instructions cause the processor to implement further comprises:

retrieving document links associated with the one or more potentially relevant document records identified, a document link in respect of a given document record providing access to a document associated with the given document record; and

communicating the document links to the issue tracking system.

19. A computer implemented method comprising:

initiating, at an issue tracking system, a ticket creation process;

receiving, by the issue tracking system, user input including issue ticket information describing an issue corresponding to a product;

generating, by the issue tracking system, an input query based on the user input;

communicating by the issue tracking system, the input query to a content identification system;

receiving, by the issue tracking system, a response from the content identification system, the response identifying one or more stored issue tickets of potential relevance to the issue ticket information;

causing, by the issue tracking system, information in respect of at least one of the one or more stored issue tickets identified in the response to be displayed;

in response to detecting a first user input, causing a new issue ticket to be generated based on the issue ticket information; and

in response to detecting a second user input, cancelling the ticket creation process without creating a ticket.

20. The computer implemented method of claim 19 , wherein the response from the content identification system further includes one or more knowledge article documents.