Computing system including virtual agent bot providing semantic topic model-based response

1. A computer-implemented method of executing a virtual agent bot, the computer-implemented method comprising:

receiving, via a computer server, at least one input query from a user;

analyzing the at least one input query to extract at least one input keyword;

determining a semantic skill set of the virtual agent bot among a plurality of different candidate skill sets based at least in part on the at least one input keyword; and

invoking the virtual agent bot to provide a semantic topic response corresponding to the semantic skill set to provide an answer to the at least one input query,

wherein determining the semantic skill set further comprises:

comparing the at least one input keyword to a plurality of intent keywords, each intent keyword corresponding to an individual skill set among the different candidate skill sets;

determining at least one keyword match between the at least one input keyword and at least one matching intent keyword;

performing a semantic analysis based at least in part on the at least one keyword match and calculating a semantic score based at least in part on the semantic analysis.

2. The computer-implemented method of claim 1 , wherein the semantic score indicates a relatedness between the at least one input query and a given candidate skill set.

3. The computer-implemented method of claim 2 , wherein the determined semantic skill set includes at least one keyword match having a highest semantic score among a plurality of semantic scores.

4. The computer-implemented method of claim 3 , wherein the highest semantic score is calculated in response to adding together an individual first semantic score associated with a first candidate skill set and an individual second semantic score associated with the first candidate skill set.

5. The computer-implemented method of claim 1 , wherein performing the semantic analysis further comprises:

performing a first semantic analysis based at least in part on skill comparisons between the at least one input keyword and each candidate skill set;

calculating a first semantic score associated with each skill comparison;

performing a second semantic analysis based at least in part on intent comparisons between the at least one input keyword and each of the plurality of intent keywords; and

calculating a second semantic score associated with at least one of the intent comparisons.

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

receiving a first input query and determining a first semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the first input query;

providing, via the virtual agent bot, a first semantic topic response corresponding to a first semantic skill set to provide a first answer to the first input query;

receiving a second input query subsequent to the first input query and determining a second semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the second input query; and

providing, via the virtual agent bot, a second semantic topic response corresponding to a second semantic skill set to provide a second answer to the second input query,

wherein the second semantic skill set is determined based at least in part on a time duration between receiving the first input query and the second input query.

7. The computer-implemented method of claim 6 , further comprising determining the first and second input queries correspond to a conversation session such that the second skill set matches the first skill set in response to determining the time duration is below a time duration threshold,

wherein the virtual agent bot provides a subsequent semantic topic response based on the second input query and at least one historical input query and at least one historical semantic topic response.

8. A system configured to execute a virtual agent bot, the system comprising:

a storage medium;

a processor in signal communication with the storage medium and configured to:

receive at least one input query from a user;

analyze the at least one input query to extract at least one input keyword;

determine a semantic skill set of the virtual agent bot among a plurality of different candidate skill sets based at least in part on the at least one input keyword;

invoke the virtual agent bot to provide a semantic topic response corresponding to the semantic skill set to provide an answer to the at least one input query,

compare the at least one input keyword to a plurality of intent keywords, each intent keyword corresponding to an individual skill set among the different candidate skill sets;

determine at least one keyword match between the at least one input keyword and at least one matching intent keyword;

perform a semantic analysis based at least in part on the at least one keyword match and calculate a semantic score based at least in part on the semantic analysis; and

determine the semantic skill set based on the semantic score.

9. The system of claim 8 , wherein the semantic score indicates a relatedness between the at least one input query and a given candidate skill set.

10. The system of claim 9 , wherein the determined semantic skill set includes at least one keyword match having a highest semantic score among a plurality of semantic scores.

11. The system of claim 10 , wherein the processor is further configured to calculate the highest semantic score in response to adding together an individual first semantic score associated with a first candidate skill set and an individual second semantic score associated with the first candidate skill set.

12. The system of claim 8 , wherein the processor is further configured to:

perform a first semantic analysis based at least in part on skill comparisons between the at least one input keyword and each candidate skill set;

calculate a first semantic score associated with each skill comparison;

perform a second semantic analysis based at least in part on intent comparisons between the at least one input keyword and each of the plurality of intent keywords; and

calculate a second semantic score associated with at least one of the intent comparisons.

13. The system of claim 8 , wherein the processor is further configured to:

receive a first input query and determining a first semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the first input query;

provide, via the virtual agent bot, a first semantic topic response corresponding to a first semantic skill set to provide a first answer to the first input query;

receive a second input query subsequent to the first input query and determining a second semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the second input query; and

provide, via the virtual agent bot, a second semantic topic response corresponding to a second semantic skill set to provide a second answer to the second input query,

wherein the processor is further configured to determine the second semantic skill set based at least in part on a time duration between receiving the first input query and the second input query.

14. The system method of claim 13 , wherein the processor is further configured to: determine the first and second input queries correspond to a conversation session such that the second skill set matches the first skill set in response to determining the time duration is below a time duration threshold,

wherein the virtual agent bot is configured to provide a subsequent semantic topic response based on the second input query and at least one historical input query and at least one historical semantic topic response.

15. A computer program product configured to execute a virtual agent bot, the 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:

receive at least one input query from a user;

analyze the at least one input query to extract at least one input keyword;

determine a semantic skill set of the virtual agent bot among a plurality of different candidate skill sets based at least in part on the at least one input keyword;

invoke the virtual agent bot to provide a semantic topic response corresponding to the semantic skill set to provide an answer to the at least one input query,

compare the at least one input keyword to a plurality of intent keywords, each intent keyword corresponding to an individual skill set among the different candidate skill sets;

determine at least one keyword match between the at least one input keyword and at least one matching intent keyword;

perform a semantic analysis based at least in part on the at least one keyword match and calculate a semantic score based at least in part on the semantic analysis; and

determine the semantic skill set based on the semantic score.

16. The computer program product of claim 15 , wherein the program instructions are further executable by the processor to cause the processor to:

perform a first semantic analysis based at least in part on skill comparisons between the at least one input keyword and each candidate skill set;

calculate a first semantic score associated with each skill comparison;

perform a second semantic analysis based at least in part on intent comparisons between the at least one input keyword and each of the plurality of intent keywords; and

calculate a second semantic score associated with at least one of the intent comparisons.

17. The computer program product of claim 15 , wherein the program instructions are further executable by the processor to cause the processor to:

receive a first input query and determining a first semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the first input query;

provide, via the virtual agent bot, a first semantic topic response corresponding to a first semantic skill set to provide a first answer to the first input query;

receive a second input query subsequent to the first input query and determining a second semantic skill set of the virtual agent bot based at least in part on at least one input keyword of the second input query; and

provide, via the virtual agent bot, a second semantic topic response corresponding to a second semantic skill set to provide a second answer to the second input query,

wherein the processor determines the second semantic skill set based at least in part on a time duration between receiving the first input query and the second input query.