# US 12,222,984 B1 · System and method for providing video query > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,222,984 B1 - Document ID: US12222984B1 - Status: Granted - Kind: B1 - Application number: 18/367,197 - Filed: 2023-09-12 - Granted: 2025-02-11 - Earliest claimed: 2023-09-12 - Assignees: JPMorgan Chase Bank, N.A. - Applicants: JPMorgan Chase Bank, N.A. - Inventors: Vali Tawosi; Salwa Husam Alamir; Natraj Raman; Sameena Shah - Web page: https://patentgrep.com/patent/US12222984B1 ## CPC - G06F 16/732: Query formulation - G06F 16/738: Presentation of query results - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method and system for providing a video query are disclosed. The method includes acquiring context information, training a first machine learning (ML) model using historical data of the software life cycle tool, and removing, by the first ML model, noise from the context information for generating a query including at least one keyword. Once the query is generated, executing, by a second ML model, the query to retrieve at least one video segment from a learning repository. Scoring and ranking is then performed on the at least one video segment. The ranked video segment is then transmitted, to the user interface of the software life cycle tool, and displayed in an ad-hoc manner. ## Claims ### Claim 1 A method for performing a video query, the method comprising: acquiring, by a processor, context information via a user interface of a software life cycle tool, wherein the context information is based on a current task being processed by a user and amount of time expanded for the current task; training, by the processor, a first machine learning (ML) model using historical data of the software life cycle tool; removing, by the first ML model executed by the processor, extraneous information and noise from the acquired context information; generating, by the first ML model executed by the processor, a query, the query including at least one keyword; executing, by a second ML model executed by the processor, the generated query to retrieve at least one video segment of a video file from a learning repository, wherein the video file has a plurality of segments, and each segment of the plurality of segments corresponds to a different topic; scoring, by the second ML model executed by the processor, the at least one video segment based on a number of matches between the at least one keyword and transcription of the at least one video segment; ranking, by the second ML model executed by the processor, the at least one video segment based on the scoring; transmitting, by the second ML model executed by the processor and to the user interface of the software life cycle tool, the ranking of the at least one video segment; and displaying, via the user interface of the software life cycle tool, the ranked at least one video segment. ### Claim 2 (depends on 1) The method according to claim 1, wherein the at least one video segment has been transcribed before retrieving the at least one video segment. ### Claim 3 (depends on 1) The method according to claim 1, wherein the learning repository is an internal database. ### Claim 4 (depends on 1) The method according to claim 1, wherein the learning repository is a public storage. ### Claim 5 (depends on 1) The method according to claim 1, wherein the learning repository is a combination of an internal database and a public storage. ### Claim 6 (depends on 5) The method according to claim 5, wherein the internal database is searched prior to the public storage for the at least one video segment. ### Claim 7 (depends on 5) The method according to claim 5, wherein the public storage is searched only when the at least one video segment is not stored in the internal database. ### Claim 8 (depends on 1) The method according to claim 1, wherein the generated query includes less information than the acquired context information. ### Claim 9 (depends on 1) The method according to claim 1, further comprising: identifying a supplemental data item included in the at least one video segment; retrieving the supplemental data item; and providing the supplemental data item along with the at least one video segment for selection. ### Claim 10 (depends on 9) The method according to claim 9, wherein the supplemental data item is indicated as corresponding to the at least one video segment. ### Claim 11 (depends on 1) The method according to claim 1, wherein the software life cycle tool is either an issue tracking system or an integrated development environments. ### Claim 12 (depends on 1) The method according to claim 1, wherein the context information is acquired based on input provided on the user interface of the software life cycle tool. ### Claim 13 (depends on 1) The method according to claim 1, wherein the context information includes at least one of a file path, software application being used, environment, network, data type, severity of issue, systems of impact, and dependencies. ### Claim 14 (depends on 1) The method according to claim 1, wherein a portion of the context information is passively captured based on a current task of a developer. ### Claim 15 (depends on 1) The method according to claim 1, wherein, in the ranking, the ranking is performed for video segments that receive a score above a reference threshold. ### Claim 16 (depends on 1) The method according to claim 1, wherein, in the transmitting, only video segments above a predetermined ranking are transmitted to the user interface. ### Claim 17 (depends on 1) The method according to claim 1, wherein, in the displaying, highest ranking video segment is played automatically upon receipt by the user interface of the software life cycle tool. ### Claim 18 A system for performing a video query, the system comprising: a memory; and a processor, wherein the system is configured to perform: acquiring context information via a user interface of a software life cycle tool, wherein the context information is based on a current task being processed by a user and amount of time expanded for the current task; training a first machine learning (ML) model using historical data of the software life cycle tool; removing, by the first ML model executed by the processor, extraneous information and noise from the acquired context information; generating, by the first ML model executed by the processor, a query, the query including at least one keyword; executing, by a second ML model executed by the processor, the generated query to retrieve at least one video segment of a video file from a learning repository, wherein the video file has a plurality of segments, and each segment of the plurality of segments corresponds to a different topic; scoring, by the second ML model executed by the processor, the at least one video segment based on a number of matches between the at least one keyword and transcription of the at least one video segment; ranking, by the second ML model executed by the processor, the at least one video segment based on the scoring; transmitting, by the second ML model executed by the processor and to the user interface of the software life cycle tool, the ranking of the at least one video segment; and displaying, via the user interface of the software life cycle tool, the ranked at least one video segment. ### Claim 19 A non-transitory computer readable storage medium that stores a computer program for performing a video query, the computer program, when executed by a processor, causing a system to perform a plurality of processes comprising: acquiring context information via a user interface of a software life cycle tool, wherein the context information is based on a current task being processed by a user and amount of time expanded for the current task; training a first machine learning (ML) model using historical data of the software life cycle tool; removing, by the first ML model executed by the processor, extraneous information and noise from the acquired context information; generating, by the first ML model executed by the processor, a query, the query including at least one keyword; executing, by a second ML model executed by the processor, the generated query to retrieve at least one video segment of a video file from a learning repository, wherein the video file has a plurality of segments, and each segment of the plurality of segments corresponds to a different topic; scoring, by the second ML model executed by the processor, the at least one video segment based on a number of matches between the at least one keyword and transcription of the at least one video segment; ranking, by the second ML model executed by the processor, the at least one video segment based on the scoring; transmitting, by the second ML model executed by the processor and to the user interface of the software life cycle tool, the ranking of the at least one video segment; and displaying, via the user interface of the software life cycle tool, the ranked at least one video segment.