Method And System For Delivering Response Based On Context Aware Intent Recognition

Flipkart Internet Private Limited
Application Awaiting Examination App No 202341079316 Computer Science

Patent information

IP India · live record
Application number
202341079316
Filing date
22 November 2023
Status
Application Awaiting Examination
Publication number
21/2025
Publication type
INA
Invention field
Computer Science

Abstract

The present disclosure relates to method and system for delivering response to a user based on a recognized context-aware intent of the user. The method comprises: (1) generating, by processing unit [102], a present turn system-response based on a previous turn user-response and a previous turn intent; (2) receiving, by processing unit [102] via user interface [110], present turn user-response; (3) generating, via embeddings generator unit, embedding vectors for present turn system-response, and embedding vectors for present turn user-response; (4) generating, via a concatenation unit, concatenated vector embedding based on embedding vectors for the present turn system-response and the embedding vectors for present turn user-response; (5) generating, via an intent recognition unit, present turn intent based on concatenated vector embedding and previous turn intent; (6) delivering a next turn system-response based on the concatenated vector embedding and the present turn intent. [FIG. 2]

Applicants

1
India
FLIPKART INTERNET PRIVATE LIMITED Buildings Alyssa, Begonia & Clover, Embassy Tech Village, Outer Ring Road, Devarabeesanahalli Village, Bengaluru - 560103, Karnataka, India.

Inventors

2
U.S.A.
Amogh Batwal18100 NE 95TH ST APT TT2094, REDMOND, WA 98052, United States of America.
U.S.A.
Kyung Hyuk Kim2815 112th AVE SE Bellevue WA 98004, United States of America.

Specification

Show full textCollapse

1. A method for delivering response to a user based on a recognized context‐ aware intent of the user, the method comprising: ‐ generating, by a processing unit [102], a present turn system‐response based on a previous turn user‐response and a previous turn intent; ‐ receiving, by the processing unit [102] via a user interface [110], a present turn user‐response; ‐ generating, by the processing unit [102] via an embeddings generator unit [104], one or more embedding vectors for the present turn system‐response, and one or more embedding vectors for the present turn user‐response; ‐ generating, by the processing unit [102] via a concatenation unit [106], a concatenated vector embedding based on the one or more embedding vectors for the present turn system‐response and the one or more embedding vectors for the present turn user‐response; ‐ generating, by the processing unit [102] via an intent recognition unit

[108], a present turn intent based on the concatenated vector embedding and the previous turn intent; and ‐ delivering, by the processing unit [102] via the user interface [110], a next turn system‐response based on the concatenated vector embedding and the present turn intent. 2. The method as claimed in claim 1, wherein the intent recognition unit [108] implements an intent recognition model, wherein the intent recognition model is trained based on a combination of cross entropy losses, and wherein the combination of cross entropy losses comprises a first weighted loss and a second weighted loss. 22 3. The method as claimed in claim 1, wherein the generating, by the processing unit [102] via the intent recognition unit [108], the present turn intent based on the concatenated vector embedding and the previous turn intent further comprises generating the present turn intent based on a first weighted logits and a second weighted logits. 4. The method as claimed in claim 1, wherein prior to the generating, by the processing unit [102] via the concatenation unit [106], the concatenated vector embedding, the method comprises: ‐ performing, by the processing unit [102], a truncation process on the present turn system‐response. 5. The method as claimed in claim 1, wherein prior to the delivering, by the processing unit [102] via the user interface [110], the next turn system‐ response, the method comprises: ‐ triggering, by the processing unit [102], an idiom tool. 6. The method as claimed in claim 1, wherein the present turn system‐ response is a first turn system‐response and the previous turn intent is a one‐hot encoded vector with all zero values. 7. A system for delivering response to a user based on a recognized context‐ aware intent of the user, the system comprising: 23 ‐ a processing unit [102] configured to: o generate a present turn system‐response based on a previous turn user‐response and a previous turn intent; o receive, via a user interface [110], a present turn user‐response; o generate, via an embeddings generator unit [104], one or more embedding vectors for the present turn system‐response, and one or more embedding vectors for the present turn user‐ response; o generate, via a concatenation unit [106], a concatenated vector embedding based on the one or more embedding vectors for the present turn system‐response and the one or more embedding vectors for the present turn user‐response; o generate, via an intent recognition unit [108], a present turn intent based on the concatenated vector embedding and the previous turn intent; and o deliver, via the user interface [110], a next turn system‐ response based on the concatenated vector embedding and the present turn intent. 8. The system as claimed in claim 7, wherein the intent recognition unit [108] is configured to implement an intent recognition model, wherein the intent recognition model is trained based on a combination of cross entropy losses, and wherein the combination of cross entropy losses comprises a first weighted loss and a second weighted loss. 24 9. The system as claimed in claim 7, wherein the processing unit [102] via the intent recognition unit [108], is configured to generate the present turn intent based on a first weighted logits and a second weighted logits. 10. The system as claimed in claim 7, wherein the processing unit [102], prior to the generating, via a concatenation unit [106], a concatenated vector embedding, is configured to: ‐ perform a truncation process on the present turn system‐response.

Documents

Sign in to open
Application documents
1 202341079316-STATEMENT OF UNDERTAKING (FORM 3) [22-11-2023(online)].pdf 22 Nov 2023
2 202341079316-REQUEST FOR EXAMINATION (FORM-18) [22-11-2023(online)].pdf 22 Nov 2023
3 202341079316-PROOF OF RIGHT [22-11-2023(online)].pdf 22 Nov 2023
4 202341079316-POWER OF AUTHORITY [22-11-2023(online)].pdf 22 Nov 2023
5 202341079316-FORM 18 [22-11-2023(online)].pdf 22 Nov 2023
6 202341079316-FORM 1 [22-11-2023(online)].pdf 22 Nov 2023
7 202341079316-FIGURE OF ABSTRACT [22-11-2023(online)].pdf 22 Nov 2023
8 202341079316-DRAWINGS [22-11-2023(online)].pdf 22 Nov 2023
9 202341079316-DECLARATION OF INVENTORSHIP (FORM 5) [22-11-2023(online)].pdf 22 Nov 2023
10 202341079316-COMPLETE SPECIFICATION [22-11-2023(online)].pdf 22 Nov 2023