	US 12,204,323 B1
	Mapping identified gaps in controls to operative standards using a generative artificial intelligence model
Shardul Malviya, London (GB); Samantha Cory, London (GB); Mariusz Saternus, Cracow (PL); Daniel Lewandowski, Cracow (PL); Biraj Krushna Rath, London (GB); Stuart Murray, London (GB); Philip Davies, London (GB); Payal Jain, London (GB); and Tariq Husayn Maonah, London (GB)
Assigned to CITIBANK, N.A.
Filed by Citibank, N.A., New York, NY (US)
Filed on Jul. 12, 2024, as Appl. No. 18/771,876.
Application 18/771,876 is a continuation in part of application No. 18/661,519, filed on May 10, 2024, granted, now 12,106,205.
Application 18/771,876 is a continuation in part of application No. 18/661,532, filed on May 10, 2024, granted, now 12,111,747.
Application 18/661,519 is a continuation in part of application No. 18/633,293, filed on Apr. 11, 2024.
Int. Cl. G05B 23/02 (2006.01)

CPC G05B 23/0281 (2013.01) [G05B 23/0216 (2013.01); G05B 23/0272 (2013.01)]

20 Claims

1. A non-transitory computer-readable storage medium comprising instructions stored thereon, wherein the instructions when executed by at least one data processor of a system, cause the system to:

determine a set of vector representations of alphanumeric characters represented by one or more operative standards containing a first set of actions configured to adhere to constraints in the set of vector representations;

receive, via a user interface, an output generation request including an input for generation of an output using a large-language model (LLM),

wherein the input includes a set of gaps associated with one or more scenarios failing to satisfy the one or more operative standards of the set of vector representations,

wherein each scenario is associated with a unique identifier and corresponding metrics indicating one or more actions in the first set of actions absent from the scenario, and

wherein each gap in the set of gaps maps to a set of attributes defining the scenario including two or more of: the unique identifier of the scenario, the corresponding metrics of the scenario, corresponding vector representations associated with the scenario, a title of the scenario, a summary of the scenario, or a severity level of the scenario;

using the received input, construct a set of prompts for each gap in the set of gaps,

wherein the set of prompts for a particular gap includes the set of attributes defining the scenario and one or more of: (1) the first set of actions of the one or more operative standards or (2) the set of vector representations, and

wherein one or more prompts in the set of prompts is configured to cause the LLM to compare a corresponding gap against one or more of: (1) the first set of actions of the one or more operative standards or (2) the set of vector representations;

for each gap in the set of gaps, map each gap to one or more operative standards of the set of vector representations by:

supplying each prompt of the set of prompts of the particular gap into the LLM, and

responsive to supplying each prompt of the set of prompts, receiving, from the LLM, a gap-specific set of operative standards comprising the one or more operative standards associated with the particular gap;

generate for display at the user interface, a graphical representation indicating the gap-specific set of operative standards,

wherein the graphical representation includes a first representation of each gap in the set of gaps and a second representation of corresponding gap-specific set of operative standards; and

using the gap-specific set of operative standards, generate a second set of actions for each gap in the set of gaps including one or more actions in the first set of actions indicated by the corresponding gap-specific set of operative standards,

wherein the second set of actions is configured to modify a portion of the scenario in the corresponding gap to satisfy the one or more operative standards of the set of vector representations.