Assisted shopping server

• US 8,977,554 B1
• Filed: 12/23/2013
• Issued: 03/10/2015
• Est. Priority Date: 06/29/2011
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hertschuh, Fabien G., St-Pierre, Benoit, Ford, James L., Cier, Sean P., Wong, Peter C., Hall, Samuel P.
• Primary Examiner(s): He, Jialong
• Application Number:
  US14/138,925
• Time in Patent Office: 442 Days
• Field of Search: 704/235, 704/270, 704/275
• US Class Current: 704/270
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00

Abstract

Disclosed are various embodiments for facilitating an assisted shopping experience. A speech input can be captured and transcribed. The transcribed speech input can be transmitted to a customer service agent in a data session that is contemporaneous with a voice session. The customer service agent can then facilitate an assisted shopping experience via the voice session and data session.

Claims

1. A system comprising:

an electronic data store configured to store at least specific computer-executable instructions; and

a first computing device comprising a hardware processor and in communication with the electronic data store, the first computing device configured to execute the specific computer-executable instructions to at least;

receive a request from a second computing device for assistance on behalf of a user of the second computing device, the request comprising a representation of a speech input, the representation of the speech input comprising a text representation of the speech input;

establish a data session with the second computing device in response to receiving the request for assistance; and

during a voice session established with the second computing device in which a user of the first computing device communicates with a user of the second computing device,

receive, at the first computing device via the data session with the second computing device, data from the second computing device;

conduct a search based at least in part on at least one of the data or the text representation of the speech input received from the second computing device;

remove a first term from the text representation, the first term being associated with a first number of search results that do not satisfy a first threshold;

remove a second term from the text representation, the second term being associated with a second number of search results that do not satisfy a second threshold; and

transmit, from the first computing device to the second computing device via the data session, a search result from the conducted search.

2. The system of claim 1, the second computing device further comprises a proximity sensor and the data comprises proximity data from the proximity sensor.

3. The system of claim 1, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least remove the first term from the text representation by determining that the first term appears within an extraneous term dictionary.

4. The system of claim 1, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least obtain, from the second computing device, an identifier associated with a user account of the user of the second computing device, the user account associated with an electronic commerce system.

5. The system of claim 4, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least:

identify at least one of a search history or a purchase history associated with the user account; and

transmit the at least one of the search history or the purchase history to the second computing device.

6. The system of claim 1, wherein the data session is contemporaneous with the voice session.

7. The system of claim 1, wherein the data comprises at least one of a location, a speed or a direction associated with the second computing device.

8. The system of claim 1, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least transcribe the speech input obtained from the second computing device into the text representation.

9. The system of claim 1, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least output a customer service agent user interface comprising at least one of a purchase history associated with the user, a location of the second computing device, a velocity of the second computing device, or a search history of the user.

10. A computer-implemented method comprising:

receiving, at a first computing device, a request from a second computing device for assistance on behalf of a user of the second computing device, the request comprising a text representation of a speech input;

in response to the request for assistance, establishing a data session and a voice session between the first computing device and the second computing device;

during the voice session between the first computing device and the second computing device,

receiving, at the first computing device via the data session with the second computing device, data from the second computing device;

conducting a search based at least in part on at least one of the text representation of the speech input or the data received from the second computing device;

remove a first term from the text representation, the first term being associated with a first number of search results that do not satisfy a first threshold;

remove a second term from the text representation, the second term being associated with a second number of search results that do not satisfy a second threshold; and

transmitting, from the first computing device to the second computing device via the data session, a search result from the conducted search.

11. The computer-implemented method of claim 10, further comprising causing the first computing device to output a customer service agent user interface comprising at least one of a purchase history associated with the user, a location of the second computing device, a velocity of the second computing device, or a search history of the user.

12. The computer-implemented method of claim 10, wherein the data received from the second computing device further comprises a state associated with at least one proximity sensor associated with the second computing device.

13. The computer-implemented method of claim 10, wherein the voice session and the data session are executed contemporaneously with one another.

14. The computer-implemented method of claim 10, wherein the voice session further comprises a voice over internet protocol session between the first computing device and the second computing device.

15. The computer-implemented method of claim 10, further comprising transcribing, via the first computing device, the speech input obtained from the second computing device into the text representation.

16. The computer-implemented method of claim 15, further comprising removing, via the first computing device, the second term from the text representation in response to determining that the second term appears within an extraneous term dictionary.

17. A non-transitory computer-readable medium having instructions executable by a first computing device stored thereon, the instructions, when executed by the first computing device, causing the first computing device to at least:

obtain a speech input from a second computing device associated with a user, the speech input comprising a text representation of the speech input;

initiate a voice session between the first computing device and the second computing device;

initiate a data session with the second computing device, the data session being executed contemporaneously with the voice session;

during the voice session between the first computing device and the second computing device,

receive, at the first computing device via the data session with the second computing device, data from the second computing device;

conduct a search based at least in part on at least one of the text representation of the speech input or the data received from the second computing device;

remove a first term from the text representation, the first term being associated with a first number of search results that do not satisfy a first threshold;

remove a second term from the text representation, the second term being associated with a second number of search results that do not satisfy a second threshold; and

transmit, from the first computing device to the second computing device via the data session, a search result from the conducted search.

18. The non-transitory computer-readable medium of claim 17, wherein the instructions, when executed, are further configured to cause the first computing device to at least:

obtain a state associated with at least one proximity sensor of the second computing device, the state corresponding to a proximity of the second computing device to another object; and

output the state associated with the at least one proximity sensor to a customer service agent user interface.

19. The non-transitory computer-readable medium of claim 17, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least remove the first term from the text representation by determining that the first term appears within an extraneous term dictionary.

20. The non-transitory computer-readable medium of claim 17, wherein the first computing device is further configured to execute the specific computer-executable instructions to at least transcribe the speech input obtained from the second computing device into the text representation.