US-20260127172-A1 - SYSTEMS AND METHODS FOR EXTRACTING PUBLIC INFORMATION BOOK (PIB) DATA FROM NEWS AND EVENT STREAMS

Abstract

At least one aspect of this disclosure is directed to method of scraping, by a first computing system, one or more first data sources of the first computing system, and one or more second data sources of one or more external computing systems, to compile a first dataset, standardizing, by the first computing system, the first dataset to generate a standardized dataset, applying, by the first computing system, a first artificial intelligence (AI) algorithm to assign labels to data entries of the standardized dataset, compiling, by the first computing system, the standardized dataset having the labels assigned to the respective data entries in a database, receiving, by an AI interface of the first computing system, a query from a computing device, and generating, by the first computing system, a response to the query for delivering via the AI interface to the computing device.

Inventors

• Shobha Duggirala
• Ashish B. Kurani
• Amruth Kumar
• Antonio Iniguez
• Nick Heim
• Justin Robert Wolf

Assignees

• WELLS FARGO BANK, N.A.

Dates

Publication Date

20260507

Application Date

20251229

Claims (20)

1. 1 . A method comprising: scraping, by a first computing system, first data of one or more first data sources of the first computing system, and second data one or more second data sources of one or more external computing systems, wherein the one or more second data sources are scrapped according to a time period; receiving, by an AI interface of the first computing system, a string of queries from a computing device relating to a target entity; generating, by the first computing system, for each query of the string of queries, a respective response according to the first data and the second data, and a prior query of the string of queries, each response displayed within the AI interface; and causing, by the first computing device, display of a plurality of tabs within the AI interface, each tab corresponding to at least a portion of information relating to the responses to the string of queries to be displayed within the AI interface.
2. 2 . The method of claim 1 , wherein a tab of the plurality of tabs comprises a nested menu for displaying different views of the portion of the information.
3. 3 . The method of claim 1 , wherein at least one of the one or more second data sources comprise an external news source, and wherein the first computing system scrapes the second data sources using at least one of an application program interface (API) call of the external news source, a standard query language (SQL) request, or a hyptertext transfer protocol (HTTP) GET request.
4. 4 . The method of claim 3 , wherein scraping the one or more second data sources is responsive to receiving at least one query of the string of queries, and wherein the one or more second data sources are scraped according to a context of the at least one query.
5. 5 . The method of claim 1 , further comprising generating, by the first computing system, a plurality of presentations responsive to a request from at least one of the string of queries.
6. 6 . The method of claim 5 , wherein each tab corresponds to a respective presentation of the plurality of presentations.
7. 7 . The method of claim 1 , further comprising: receiving, by the first computing system, following selection of a first tab of the plurality of tabs to display the corresponding portion of information within the AI interface, a subsequent query via the AI interface; generating, by the first computing system, a subsequent response according to the subsequent query and using at least some of the portion of information within the AI interface; and displaying, by the first computing system, information relating to the response within the AI interface.
8. 8 . The method of claim 7 , wherein displaying the information relating to the response comprises: overlaying, by the first computing system, the information relating to the response, within a region of the AI interface which corresponds to the portion of information.
9. 9 . The method of claim 1 , further comprising: for each query of the string of queries, generating, by the first computing system, a plurality of tokens representing the query; encoding, by the first computing system, each token into a corresponding encoded token; applying, by the first computing system, the encoded tokens to an AI model, to determine a context associated with the query; requesting, by the first computing system, one or more data entries the one or more first data sources or the one or more second data sources, the one or more data entries requested according to the determined context; applying, by the first computing system, data corresponding to the one or more data entries and the encoded tokens to the AI model; and generating, by the first computing system, the response based on an output from the AI model.
10. 10 . A first computing system, comprising: one or more processors configured to: scrape first data of one or more first data sources of the first computing system, and second data one or more second data sources of one or more external computing systems, wherein the one or more second data sources are scrapped according to a time period; receive, via an AI interface of the first computing system, a string of queries from a computing device relating to a target entity; generate, for each query of the string of queries, a respective response according to the first data and the second data, and a prior query of the string of queries, each response displayed within the AI interface; and cause display of a plurality of tabs within the AI interface, each tab corresponding to at least a portion of information relating to the responses to the string of queries to be displayed within the AI interface.
11. 11 . The first computing system of claim 10 , wherein a tab of the plurality of tabs comprises a nested menu for displaying different views of the portion of the information.
12. 12 . The first computing system of claim 10 , wherein at least one of the one or more second data sources comprise an external news source, and wherein the one or more processors scrape the second data sources using at least one of an application program interface (API) call of the external news source, a standard query language (SQL) request, or a hyptertext transfer protocol (HTTP) GET request.
13. 13 . The first computing system of claim 12 , wherein the one or more processors scape the one or more second data sources responsive to receiving at least one query of the string of queries, and wherein the one or more second data sources are scraped according to a context of the at least one query.
14. 14 . The first computing system of claim 10 , wherein the one or more processors are configured to generate a plurality of presentations responsive to a request from at least one of the string of queries.
15. 15 . The first computing system of claim 14 , wherein each tab corresponds to a respective presentation of the plurality of presentations.
16. 16 . The first computing system of claim 10 , wherein the one or more processors are configured to: receive, following selection of a first tab of the plurality of tabs to display the corresponding portion of information within the AI interface, a subsequent query via the AI interface; generate a subsequent response according to the subsequent query and using at least some of the portion of information within the AI interface; and display information relating to the response within the AI interface.
17. 17 . The first computing system of claim 16 , wherein, to display the information relating to the response, the one or more processors are configured to overlay the information relating to the response, within a region of the AI interface which corresponds to the portion of information.
18. 18 . The first computing system of claim 10 , wherein the one or more processors are configured to: for each query of the string of queries, generate a plurality of tokens representing the query; encode each token into a corresponding encoded token; apply the encoded tokens to an AI model, to determine a context associated with the query; request one or more data entries the one or more first data sources or the one or more second data sources, the one or more data entries requested according to the determined context; apply data corresponding to the one or more data entries and the encoded tokens to the AI model; and generate the response based on an output from the AI model.
19. 19 . A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to: scrape first data of one or more first data sources of the computing system, and second data one or more second data sources of one or more external computing systems, wherein the one or more second data sources are scrapped according to a time period; receive, via an AI interface of the computing system, a string of queries from a computing device relating to a target entity; generate, for each query of the string of queries, a respective response according to the first data and the second data, and a prior query of the string of queries, each response displayed within the AI interface; and cause display of a plurality of tabs within the AI interface, each tab corresponding to at least a portion of information relating to the responses to the string of queries to be displayed within the AI interface.
20. 20 . The non-transitory computer readable medium of claim 19 , wherein the instructions further cause the computing system to: for each query of the string of queries, generate a plurality of tokens representing the query; encode each token into a corresponding encoded token; apply the encoded tokens to an AI model, to determine a context associated with the query; request one or more data entries the one or more first data sources or the one or more second data sources, the one or more data entries requested according to the determined context; apply data corresponding to the one or more data entries and the encoded tokens to the AI model; and generate the response based on an output from the AI model.

Description

CROSS-REFERENCE TO RELATED PATENT APPLICATIONS This Application is a continuation of U.S. application Ser. No. 18/734,448, filed Jun. 5, 2024, which claims the benefit of and priority to U.S. Provisional Application Ser. No. 63/471,453, filed Jun. 6, 2023, U.S. Provisional Application Ser. No. 63/544,865, filed Oct. 19, 2023, and U.S. Provisional Application Ser. No. 63/549,411, filed Feb. 2, 2024, the contents of each of which are incorporated herein by reference in their entirety. TECHNICAL FIELD The present disclosure relates to systems and methods for an intelligent banking service. More specifically, the present disclosure relates to systems and methods of providing curated datasets according to data from disparate data sources using an intelligent banking service which leverages artificial intelligence (AI) modeling and cross-platform data to provide real-time or nearly real-time information in response to inquiries. BACKGROUND Various settings require access to information to make informed decisions. In various banking contexts, such as preparing for an investment banking meeting, a user must perform data gathering, presentation creation with the gathered data, and coordinate schedules with the pertinent personnel for the presentation. These tasks consume valuable time and resources, often leading to inefficiencies. Additionally, such tasks often involve pulling duplicative or redundant data across multiple platforms, accessing each of such platforms independently, and compiling the data to generate the deliverable. This leads to increased bandwidth occupancy as well as increased processing power requirements. SUMMARY Systems, methods, and computer-readable media for providing curated datasets may include a first computing system which scrapes one or more first data sources of the first computing system, and one or more second data sources of one or more external computing systems, to compile a first dataset. The first computing system may standardize the first dataset to generate a standardized dataset. The first computing system may apply a first artificial intelligence (AI) algorithm to assign labels to data entries of the standardized dataset. The first computing system may compile the standardized dataset having the labels assigned to the respective data entries in a database. The first computing system may receive, via an AI interface, a query from a computing device. The first computing system may generate a response to the query for delivering via the AI interface to the computing device. In some embodiments, the query includes an inquiry for information relating to an enterprise, and the response includes values for a plurality of fields relating to the enterprise. In some embodiments, the one or more first data sources include a customer relationship management (CRM) platform and a document database. In some embodiments, generating the response includes the first computing system generating a plurality of tokens representing the query, encoding each token into a corresponding encoded token, applying the encoded tokens to an AI model to determine a context associated with the query, requesting one or more data entries from the database and/or from the one or more first data sources or the one or more second data sources according to the determined context; applying data corresponding to the one or more data entries and the encoded tokens to the AI model, and generating the response based on an output from the AI model. In some embodiments, the first computing system may scrub the response to the query based on a user of the first computing device. In some embodiments, the first computing system generates the response to the query using at least a portion of the data from the database populated with the standardized dataset. In some embodiments, the first computing system trains the first AI algorithm, using a training dataset including a plurality of standardized data entries and corresponding labels associated with respective data entries. The first computing system may deploy the first AI algorithm responsive to the first AI algorithm satisfying a training criteria. In some embodiments, the first computing system generates the response to the query by applying data corresponding to the query to a second AI algorithm, the second AI algorithm configured to generate a response to the query using data from the database. This summary is illustrative only and is not intended to be in any way limiting. Other aspects, inventive features, and advantages of the devices or processes described herein will become apparent in the detailed description set forth herein, taken in conjunction with the accompanying figures, wherein like reference numerals refer to like elements. BRIEF DESCRIPTION OF THE FIGURES Before turning to the Figures, which illustrate certain example embodiments in detail, it should be understood that the present disclosure is not limited to the details or methodology set forth in the