Chat management to address queries

1. A method comprising:

receiving a query from a user within an instant messaging chat environment;

determining whether the query has already been answered by comparing the query to text within a chat database, wherein the chat database stores textual chat history data which occurred over the instant messaging chat environment;

identifying, in response to determining that the query has not been answered, a set of prospective experts;

ranking each prospective expert of the set of prospective experts based on a plurality of factors, each of the plurality of factors having a weight, wherein a first factor of the plurality factors is an experience factor, wherein a first factor score of the first factor is based on a number of years of experience, wherein a second factor of the plurality of factors is an education factor, wherein a second factor score of the second factor is based on a level of education, wherein a third factor of the plurality of factors is a keyword match factor, wherein a third factor score of the third factor is based on a number of times a keyword within the query appears within chat history of each prospective expert;

identifying a first ranked expert based on the ranking, wherein the first ranked expert is a highest ranked expert of the set of prospective experts based on the plurality of factors;

initiating a chat window between the user and the first ranked expert to allow the first ranked expert to address the query in real-time with the user;

receiving an answer to the query from the first ranked expert within the chat window;

validating the answer received from the first ranked expert by referencing an external source;

increasing a confidence score that the answer is a correct answer based on the answer being validated; and

outputting a triple including the query, the answer, and the confidence score.

2. The method of claim 1 , wherein the set of prospective experts is filtered based on at least one threshold prior to ranking.

3. The method of claim 1 , further comprising:

receiving a second query;

determining whether the second query has already been answered by comparing the second query to text within the chat database; and

retrieving, in response to determining that the second query has already been answered, an answer to the second query from the chat database.

4. A system comprising:

a memory storing program instructions; and

a processor, wherein the processor is configured to execute the program instructions to perform a method comprising:

receiving a query from a user within an instant messaging chat environment;

determining whether the query has already been answered by comparing the query to text within a chat database, wherein the chat database stores textual chat history data which occurred over the instant messaging chat environment;

identifying, in response to determining that the query has not been answered, a set of prospective experts;

ranking each prospective expert of the set of prospective experts based on a plurality of factors, each of the plurality of factors having a weight, wherein a first factor of the plurality factors is an experience factor, wherein a first factor score of the first factor is based on a number of years of experience, wherein a second factor of the plurality of factors is an education factor, wherein a second factor score of the second factor is based on a level of education, wherein a third factor of the plurality of factors is a keyword match factor, wherein a third factor score of the third factor is based on a number of times a keyword within the query appears within chat history of each prospective expert, wherein the number of times the keyword within the query appears within chat history of each prospective expert is determined by:

extracting the keyword from the query; and

searching chat history of each prospective expert for the number of times the keyword appears within the chat history of each prospective expert;

identifying a first ranked expert based on the ranking, wherein the first ranked expert is a highest ranked expert of the set of prospective experts based on the plurality of factors;

initiating a chat window between the user and the first ranked expert to allow the first ranked expert to address the query in real-time with the user; and

receiving an answer to the query from the first ranked expert within the chat window.

5. The system of claim 4 , wherein the set of prospective experts is filtered based on at least one threshold prior to ranking.

6. The system of claim 4 , wherein the method performed by the processor further comprises:

determining whether the answer is correct;

transmitting, in response to determining that the answer is incorrect, the query to a second ranked expert; and

receiving an answer from the second ranked expert.

7. The system of claim 4 , wherein the method performed by the processor further comprises:

receiving a second query;

determining whether the second query has already been answered by comparing the second query to text within the chat database; and

retrieving, in response to determining that the second query has already been answered, an answer to the second query from the chat database.

8. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving a query from a user within an instant messaging chat environment;

determining whether the query has already been answered by comparing the query to text within a chat database, wherein the chat database stores textual chat history data which occurred over the instant messaging chat environment;

identifying, in response to determining that the query has not been answered, a set of prospective experts;

ranking each prospective expert of the set of prospective experts based on a plurality of factors, each of the plurality of factors having a weight, wherein a first factor of the plurality factors is an experience factor, wherein a first factor score of the first factor is linearly based on a number of years of experience, wherein a second factor of the plurality of factors is an education factor, wherein a second factor score of the second factor is exponentially based on a level of education, wherein a third factor of the plurality of factors is a keyword match factor, wherein a third factor score of the third factor is based on a number of times a keyword within the query appears within chat history of each prospective expert;

identifying a first ranked expert based on the ranking, wherein the first ranked expert is a highest ranked expert of the set of prospective experts based on the plurality of factors;

initiating a chat window between the user and the first ranked expert to allow the first ranked expert to address the query in real-time with the user; and

receiving an answer to the query from the first ranked expert within the chat window.

9. The computer program product of claim 8 , wherein the set of prospective experts is filtered based on at least one threshold prior to ranking.

10. The computer program product of claim 8 , wherein the method performed by the processor further comprises:

determining whether the answer is correct;

transmitting, in response to determining that the answer is incorrect, the query to a second ranked expert; and

receiving an answer from the second ranked expert.

11. The computer program product of claim 8 , wherein the method performed by the processor further comprises:

receiving a second query;

determining whether the second query has already been answered by comparing the second query to text within the chat database; and

retrieving, in response to determining that the second query has already been answered, an answer to the second query from the chat database.