EP-4740110-A1 - KNOWLEDGE BOT AS A SERVICE

Abstract

Methods and systems are presented for providing a knowledge bot configurable to interact with users across multiple domains. The knowledge bot includes at least a text-based search engine and a semantic-based search engine. Each of the search engine is configured to retrieve documents from a corpus of documents based on the user query. The user query is in a natural language format. The retrieved documents may be ranked according to how relevant the documents are to the user query. A subset of the documents is used as the search results based on the ranking. The search results from the search engine are combined with the user query to generate a prompt for an artificial intelligence model. Based on the prompt, a response in the natural language format is generated by the artificial intelligence model.

Inventors

• ADDANKI, SANTOSH
• LANKA, Soujanya
• MURTHY, NANDANA
• PATHURI, Koteswara Rao
• RANJAN, Bineet
• XI, Liang
• HAN, Xiaoying
• SRIPADRAJ, RAGHOTHAM

Assignees

• PayPal, Inc.

Dates

Publication Date

20260513

Application Date

20240730

Claims (20)

1. 1. A system, comprising: a non-transitory memory; and one or more hardware processors coupled with the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising: receiving, from a user device, a user query associated with a first domain; identifying, from a corpus of documents corresponding to the first domain, a set of documents relevant to the user query using one or more search models; generating an input for a generative artificial intelligence (Al) model based on combining the user query and the set of documents; generating, using the generative Al model and based on the input, a response to the user query, wherein the response is based on information from at least two documents in the set of documents; and providing the response to the user device.
2. 2. The system of claim 1, wherein the user query is in a natural language format.
3. 3. The system of claim 1, wherein the one or more search models comprise a text-based search model configured to identify, from the corpus of documents, one or more documents based on one or more keywords extracted from the user query.
4. 4. The system of claim 1 , wherein the one or more search models comprise a semantic -based search model configured to (i) derive a contextual meaning of the user query based on parsing a plurality of words within the user query and (ii) identify, from the corpus documents, one or more documents based on the contextual meaning of the user query.
5. 5. The system of claim 4, wherein the semantic-based search model is further configured to analyze the plurality of words based on parsing the plurality of words forward and backward.
6. 6. The system of claim 1 , wherein the one or more search models comprise (i) a text-based search model configured to identify, from the corpus of documents, one or more first documents associated with the user query based on one or more keywords extracted from the user inquiry and (ii) a semantic -based search model configured to identify, from the corpus of documents, one or more second documents associated with the user query based on a contextual meaning derived from the user query, and wherein the operations further comprise: analyzing the one or more first documents and the one or more second documents; ranking the one or more first documents and the one or more second documents based on the analyzing; and selecting, from the one or more first documents and the one or more second documents, the set of documents relevant to the user query based on the ranking.
7. 7. The system of claim 1, wherein the response comprises a paragraph of words in a natural language format.
8. 8. A method, comprising: receiving, by a computer system and from a user device, a user query; accessing, from a plurality of corpuses of documents, a corpus of documents based on a particular domain associated with the user query; determining, by the computer system and from the corpus of documents, that one or more documents are associated with a response to the user query using one or more search models; generating, using a machine learning model and based on the user query and the one or more documents, the response to the user query, wherein the response comprises content generated based on information extracted from at least two documents in the one or more documents; and providing the response to the user device.
9. 9. The method of claim 8, wherein the user query is a first user query that is part of a dialogue between a user of the user device and a knowledge bot, and wherein the method further comprises: retrieving a chat history associated with a user of the user device, wherein the chat history comprises one or more user queries previously submitted by the user and one or more responses generated by the machine learning model for the one or more user queries; deriving a context based on the chat history; and modifying the first user query based on the context, wherein the one or more documents are determined to be associated with the to the first query based on the modified user first user query.
10. 10. The method of claim 9, wherein the modifying comprises at least one of adding one or more words to, deleting one or more words from, or revising one or more words from the first user query based on at least one of the one or more user queries or the one or more responses.
11. 11 . The method of claim 9, wherein the input is generated further based on combining the context with the modified user question and the set of documents.
12. 12. The method of claim 8, further comprising: determining, from a plurality of domains, that the user query is associated with the particular domain based on analyzing the user query.
13. 13. The method of claim 8, wherein the one or more search models comprise (i) a text-based search model configured to identify, from the corpus of documents, a first set of documents based on one or more keywords extracted from the user query and (ii) a semanticbased search model configured to identify, from the corpus of documents, a second set of documents based on a contextual meaning derived from the user query, and wherein the method further comprises: determining a score for each document in the first set of documents and the second set of documents; ranking the first and second set of documents based on the score determined for each document in the first set of documents and the second set of documents; and selecting, from the first set of documents and the second set of documents, the one or more documents based on the ranking.
14. 14. The method of claim 8, wherein the response comprises words in a natural language format.
15. 15. A non-transitory machine-readable medium having stored thereon machine- -An- readable instructions executable to cause a machine to perform operations comprising: receiving, from a user device, a user query during a session with a service provider; determining, from a corpus of documents, that one or more documents are associated with a response to the user query using one or more search models; generating, using a machine learning model and based on the user query and the one or more documents, the response to the user query, wherein the response comprises content generated based on information extracted from at least two documents in the one or more documents; and providing the response on a user interface of the user device during the session.
16. 16. The non-transitory machine-readable medium of claim 15, wherein the one or more search models comprise a text-based search model configured to identify, from the corpus of documents, a first set of documents based on one or more keywords extracted from the user query.
17. 17. The non-transitory machine-readable medium of claim 15, wherein the one or more search models comprise a semantic -based search model configured to (i) derive a contextual meaning of the user query based on parsing a plurality of words within the user query and (ii) identify, from the corpus documents, a second set of documents based on the contextual meaning of the user query.
18. 18. The non-transitory machine-readable medium of claim 17, wherein the semantic -based search model is further configured to analyze the plurality of words based on parsing the plurality of words forward and backward.
19. 19. The non-transitory machine-readable of claim 15, wherein the user query is a first user query that is part of a dialogue between a user of the user device and a knowledge hot during the session, and wherein the operations further comprise: retrieving a chat history associated with a user of the user device, wherein the chat history comprises one or more user queries previously submitted by the user and one or more responses generated by the machine learning model for the one or more user queries; deriving a context based on the chat history; and modifying the first user query based on the context, wherein the one or more documents are determined to be associated with the response to the first user query based on the modified first user query.
20. 20. The non-transitory machine-readable of claim 19, wherein the modifying comprises at least one of adding one or more words to, deleting one or more words from, or revising one or more words from the first user query based on at least one of the one or more user queries or the one or more responses.

Description

KNOWLEDGE BOT AS A SERVICE Santosh Addanki, Soujanya Lanka, Nandana Murthy, Koteswara Pathuri, Bineet Ranjan, Liang Xi, Xiaoying Han, and Raghotham Sripadraj BACKGROUND [0001] The present specification generally relates to computer-based automated interactive services, and more specifically, to a framework for providing a knowledge hot configurable to interact with users across multiple domains according to various embodiments of the disclosure. Related Art [0002] Service providers typically provide a platform for interacting with their users. The platform can be implemented as a website, a mobile application, or a phone service, through which the users may access data and/or services offered by the service provider. While these platforms can be interactive in nature (e.g., the content of the platform can be changed based on different user interactions, etc.), they are fixed and bound by their structures. In other words, users have to navigate through the platform to obtain the desired data and/or services. When the data and/or the service desired by a user is “hidden” (e.g., requiring multiple navigation steps that are not intuitive, etc.), it may be difficult for the user to access the data and/or the service purely based on manual navigation of the platform. [0003] In the past, service providers have often dedicated one or more information pages, such as a “Frequently Asked Questions (FAQ)” page, within the platforms for assisting users to access data and/or services that are popular in demand. The information pages may include predefined questions, such as “how to change my password” and pre-populated answers to the questions. However, given that the questions were pre-generated, a user who is looking for data and/or services is still required to navigate through the information pages to find a question that matches the data and/or services that the user desires. If the desired data and/or services do not match any of the questions on the information pages, the user will have to manually navigate the platform or contact a human agent of the service provider. Furthermore, the information pages also create an additional burden for the service provider, as the answers to the pre-generated questions would need to be reviewed and/or modified as necessary whenever any one of the platform, the data, and/or the services offered by the service provider is updated. Thus, there is a need for an advanced framework for providing data and/or services to users in a natural and intuitive way. BRIEF DESCRIPTION OF THE FIGURES [0004] FIG. I is a block diagram illustrating an electronic transaction system according to an embodiment of the present disclosure; [0005] FIG. 2 is a block diagram illustrating a knowledge bot according to an embodiment of the present disclosure; [0006] FIG. 3 is a block diagram illustrating a document retrieval module that utilizes multiple search engines for generating search results according to an embodiment of the present disclosure; [0007] FIG. 4 illustrates an example flow for generating a knowledge bot according to an embodiment of the present disclosure; [0008] FIG. 5 illustrates an example flow for using a knowledge bot to generate a free-form answer according to an embodiment of the present disclosure; [0009] FIG. 6 illustrates an example flow for using multiple search engines for generating search results according to an embodiment of the present disclosure; [00010] FIG. 7 illustrates an example neural network that can be used to implement a machine learning model according to an embodiment of the present disclosure; and [00011] FIG. 8 is a block diagram of a system for implementing a device according to an embodiment of the present disclosure. [00012] Embodiments of the present disclosure and their advantages are best understood by referring to the detailed description that follows. It should be appreciated that like reference numerals are used to identify like elements illustrated in one or more of the figures, wherein showings therein are for purposes of illustrating embodiments of the present disclosure and not for purposes of limiting the same. DETAILED DESCRIPTION [00013] The present disclosure describes methods and systems for providing a knowledge bot configurable to interact with users across multiple domains. Similar to a chat bot, a knowledge bot is a software module that is capable of interacting with users through dialogues in natural languages (e.g., free-form/unstructured texts). However, unlike a chat bot that typically uses pre-defined rules and structured texts for interacting with the users, a knowledge bot configured using the techniques disclosed herein can dynamically search for relevant documents within one or more specific domains based on a user query, and generate a free-form response to the user query using content extracted from the relevant documents. [00014] In some embodiments, knowledge bots may be dynamically generated (e.g., as a service) for diff