System and method for making engagement offers based on observed navigation path

1. A method for making engagement offers comprising:

monitoring, by a processor, a navigation path of a user navigating a website;

making, by the processor, an offer for engagement with the user on a first web page reached by the user upon following the navigation path, wherein the offer for engagement is suggesting knowledge to the user;

monitoring, by the processor, interaction by the user with the knowledge suggested on the first web page, wherein the knowledge is associated with a particular user intent;

updating, by the processor, based on the interaction by the user with the knowledge suggested on the first web page, tag data associated with a second web page encountered by the user while traversing the navigation path, wherein the tag data is further associated with the particular user intent and includes a value correlated to a navigation distance to the first web page;

detecting, by the processor, a second user landing on the second web page, wherein the second user is detected to have followed at least a portion of the navigation path;

calculating, by the processor, a confidence level as a function of the value included as the tag data, wherein the confidence level decreases as the navigation distance correlated to the value increases, the confidence level being indicative of confidence that the second user landing on the second web page has the particular user intent and will accept, on the second web page, a same knowledge suggested on the first web page;

anticipating, by the processor, intent of the second user landing on the second web page based on the calculated confidence level;

generating, by the processor, a search query based on the anticipated intent of the second user;

prior to the second user expressly requesting the knowledge suggested on the first web page, proactively identifying and suggesting the knowledge to the second user based on the generated search query, wherein the proactively identifying and suggesting the knowledge further includes:

retrieving a classifier model for the knowledge;

determining a relevance score based on the classifier model, wherein the relevance score is indicative of a probability that the search query is relevant to the knowledge; and

outputting the suggested knowledge based on the relevance score;

receiving, by the processor, feedback relating to the suggested knowledge;

updating, based on the feedback, the relevance score for the suggested knowledge; and

adding, by the processor, the search query as one of a positive sample or a negative sample for the classifier model, based on the feedback.

2. The method of claim 1 , wherein the navigation path identifies a sequence of web pages visited by the user during a current web session.

3. The method of claim 1 , wherein the offer for engagement is an offer for a knowledge article.

4. The method of claim 1 , wherein the tag data includes information relating to user intent.

5. The method of claim 4 , wherein the tag data includes a distance to the first web page where the offer for engagement was made, and outcome of the offer for engagement.

6. The method of claim 1 , wherein the confidence level is calculated based on a likelihood that the second user will follow the navigation path.

7. The method of claim 1 , wherein the confidence level is based on identification of redirection to the website.

8. The method of claim 1 , wherein the offer for engagement is paced based on the calculated confidence level.

9. The method of claim 8 , wherein the pacing is based on availability of agents to handle requests for interactions based on transmitted offers for engagement.

10. The method of claim 8 , wherein the pacing includes transmitting, by the processor, more invitations for offers for engagement than what are expected to be accepted by users.

11. The method of claim 1 , wherein the navigation path is processed for determining user intent, and the offer for engagement is associated with the determined user intent.

12. The method of claim 10 further comprising:

generating, by the processor, a query descriptive of the user intent, wherein the offer for engagement is a knowledge article related to the user intent.

13. A system for making engagement offers comprising:

processor; and

memory, wherein the memory includes instructions that, when executed by the processor, cause the processor to:

monitor a navigation path of a user navigating a website;

make an offer for engagement with the user on a first web page reached by the user upon following the navigation path, wherein the offer for engagement is suggesting knowledge to the user;

monitor interaction by the user with the knowledge suggested on the first web page, wherein the knowledge is associated with a particular user intent;

update, based on the interaction by the user with the knowledge suggested on the first web page, tag data associated with a second web page encountered by the user while traversing the navigation path, wherein the tag data is further associated with the particular user intent and includes a value correlated to a navigation distance to the first web page;

detect a second user landing on the second web page, wherein the second user is detected to have followed at least a portion of the navigation path;

calculate a confidence level as a function of the value included as the tag data, wherein the confidence level decreases as the navigation distance correlated to the value increases, the confidence level being indicative of confidence that the second user landing on the second web page has the particular user intent and will accept, on the second web page, a same knowledge suggested on the first web page;

anticipate intent of the second user landing on the second web page based on the calculated confidence level;

generate a search query based on the anticipated intent of the second user;

prior to the second user expressly requesting the knowledge suggested on the first web page, proactively identify and suggest the knowledge to the second user based on the generated search query, wherein the instructions that cause the processor to proactively identify and suggest the knowledge further includes instructions that cause the processor to:

retrieve a classifier model for the knowledge;

determine a relevance score based on the classifier model, wherein the relevance score is indicative of a probability that the search query is relevant to the knowledge; and

output the suggested knowledge based on the relevance score;

receive feedback relating to the suggested knowledge;

update, based on the feedback, the relevance score for the suggested knowledge; and

add the search query as one of a positive sample or a negative sample for the classifier model, based on the feedback.

14. The method of claim 1 , wherein the function causes the value computed for a particular web page to decrease, as the navigation distance from the particular web page to the first web page increases.

15. The method of claim 1 , wherein the generating of the search query includes:

identifying, by the processor, terms for describing the anticipated need.

16. The method of claim 1 , wherein the feedback is implied from actions by the second user.

17. The method of claim 1 , wherein the classifier model includes query samples for which the suggested knowledge was tagged as being relevant or not relevant.