System and method for establishing an interactive communication session

1. A method of establishing a communication session, comprising:

receiving, by a computing system from a camera of a client device, a live stream of a textual document comprising text-based content;

receiving, by the computing system, an interrogatory related to the text-based content in the textual document;

analyzing, by the computing system, the textual document to identify an answer to the interrogatory in the textual document; and

augmenting the textual document illustrated on a display associated with the client device, while the textual document remains within a line-of-vision of the camera by:

identifying a location of the identified answer within a portion of the textual document within the line-of-vision of the camera, and

highlighting the identified answer on the display by augmenting the display corresponding to the location of the identified answer, wherein the highlighting comprises:

generating a meta information, wherein the meta information indicates the location of the identified answer within the portion of the textual document, and

overlaying the meta information over the portion of the textual document within the line-of-vision of the camera.

2. The method of claim 1 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory in the textual document comprises:

analyzing one or more metatags injected into the textual document to identify the answer in the textual document.

3. The method of claim 1 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a confidence score for each possible answer of the one or more possible answers;

identifying a possible answer that is associated with a highest confidence score; and

setting the possible answer associated with the highest confidence score as the answer to the interrogatory.

4. The method of claim 1 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a confidence score for each possible answer of the one or more possible answers;

determining that the confidence score for each possible answer is below a threshold confidence score;

based on the determining, generating a clarification question seeking clarification of the identified interrogatory; and

transmitting the clarification question to the client device.

5. The method of claim 4 , further comprising:

receiving, from the client device, a clarification answer from the client device; and

parsing the clarification answer to identify a revised interrogatory contained therein.

6. The method of claim 5 , further comprising:

analyzing the textual document to identify a revised answer to the revised interrogatory;

generating a second confidence score for the revised answer;

determining that the second confidence score for the revised answer is at least greater than the threshold confidence score; and

setting the revised answer as the answer to the interrogatory.

7. The method of claim 1 , wherein receiving, by the computing system, the interrogatory related to the text-based content in the textual document comprises:

receiving a voice message comprising the interrogatory; and

converting the voice message to text using natural language processing techniques.

8. A non-transitory computer readable medium comprising one or more sequences of instructions which, when executed by a processor, causes a computing system to perform operations comprising:

receiving, by the computing system from a camera of a client device, a live stream of a textual document comprising text-based content;

receiving, by the computing system, an interrogatory related to the text-based content in the textual document;

analyzing, by the computing system, the textual document to identify an answer to the interrogatory in the textual document; and

augmenting the textual document illustrated on a display associated with the client device, while the textual document remains within a line-of-vision of the camera by:

identifying a location of the identified answer within a portion of the textual document within the line-of-vision of the camera, and

highlighting the identified answer on the display by augmenting the display corresponding to the location of the identified answer, wherein the highlighting comprises:

generating a meta information, wherein the meta information indicates the location of the identified answer within the portion of the textual document, and

overlaying the meta information over the portion of the textual document within the line-of-vision of the camera.

9. The non-transitory computer readable medium of claim 8 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory in the textual document comprises:

analyzing one or more metatags injected into the textual document to identify the answer in the textual document.

10. The non-transitory computer readable medium of claim 8 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a confidence score for each possible answer of the one or more possible answers;

identifying a possible answer that is associated with a highest confidence score; and

setting the possible answer associated with the highest confidence score as the answer to the interrogatory.

11. The non-transitory computer readable medium of claim 8 , wherein analyzing, by the computing system, the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a second confidence score for each possible answer of the one or more possible answers;

determining that the second confidence score for each possible answer is below a threshold confidence score;

based on the determining, generating a clarification question seeking clarification of the identified interrogatory;

transmitting the clarification question to the client device;

receiving, from the client device, a clarification answer from the client device; and

parsing the clarification answer to identify a revised interrogatory contained therein.

12. The non-transitory computer readable medium of claim 11 , further comprising:

analyzing the textual document to identify a revised answer to the revised interrogatory;

generating a confidence score for the revised answer;

determining that the confidence score for the revised answer is at least greater than the threshold confidence score; and

setting the revised answer as the answer to the interrogatory.

13. The non-transitory computer readable medium of claim 8 , wherein receiving, by the computing system, the interrogatory related to the text-based content in the textual document comprises:

receiving a voice message comprising the interrogatory; and

converting the voice message to text using natural language processing techniques.

14. A system comprising:

one or more processors; and

a memory having programming instructions stored thereon, which, when executed by the one or more processors, causes the system to perform operations comprising:

receiving, by a computing system from a camera of a client device, a live stream of a textual document comprising text-based content;

receiving, by the computing system, an interrogatory related to the text-based content in the textual document;

analyzing, by the computing system, the textual document to identify an answer to the interrogatory in the textual document; and

augmenting the textual document illustrated on a display associated with the client device, while the textual document remains within a line-of-vision of the camera by:

identifying a location of the identified answer within a portion of the textual document within the line-of-vision of the camera, and

highlighting the identified answer on the display by augmenting the display corresponding to the location of the identified answer, wherein the highlighting comprises:

generating a meta information, wherein the meta information indicates the location of the identified answer within the portion of the textual document, and

overlaying the meta information over the portion of the textual document within the line-of-vision of the camera.

15. The system of claim 14 , wherein analyzing the textual document to identify the answer to the interrogatory in the textual document comprises:

analyzing one or more metatags injected into the textual document to identify the answer in the textual document.

16. The system of claim 14 , wherein analyzing the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a confidence score for each possible answer of the one or more possible answers;

identifying a possible answer that is associated with a highest confidence score; and

setting the possible answer associated with the highest confidence score as the answer to the interrogatory.

17. The system of claim 14 , wherein analyzing the textual document to identify the answer to the interrogatory, comprises:

identifying one or more possible answers to the interrogatory;

generating a confidence score for each possible answer of the one or more possible answers;

determining that the confidence score for each possible answer is below a threshold confidence score;

based on the determining, generating a clarification question seeking clarification of the identified interrogatory; and

transmitting the clarification question to the client device.

18. The system of claim 17 , wherein the operations further comprise:

receiving, from the client device, a clarification answer from the client device; and

parsing the clarification answer to identify a revised interrogatory contained therein.

19. The system of claim 18 , further comprising:

analyzing the textual document to identify a revised answer to the revised interrogatory;

generating a second confidence score for the revised answer;

determining that the second confidence score for the revised answer is at least greater than the threshold confidence score; and

setting the revised answer as the answer to the interrogatory.