IP Library Granted Patent US 12681966
Granted Patent B2
US 12681966 · App. 18/525,122 · Granted Jul 14, 2026

System for the interpretation and querying of content generated by an artificial intelligence model

Inventors: Christophe Aliaga (Abidjan, CI); Yvan Erbs (Abidjan, CI)
G06F16/3329G06F16/338G06F40/289
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12681966
App. No.
18/525,122
Granted
Jul 14, 2026
Kind
B2
Abstract

A system for querying interpreted content from a generative artificial intelligence model is disclosed. The system includes a generative artificial intelligence model and one or more processors. The model is configured to accept a natural language text input and produce a human-like text response. The system performs operations including receiving a natural language text input representative of a query subject and a query context, receiving an input representative of a query response structure, amplifying a combination of the inputs, providing the amplified query to the model, receiving the human-like text response generated by the model, accumulating the responses to form a global query response, and providing the global query response to a computerized interface.

Claims (46)

1 . A system to query interpreted content from a generative artificial intelligence model, comprising:

a computerized database including a plurality of prestored query response structures, each of which includes at least two individual segment type identifiers, and at least one query generation rule associated with each one of the segment type identifiers;

a computerized input device configured to receive a natural language text input, said text input includes a query subject, query context, and a structure template identifier representative of a selected query response structure;

a computerized interface configured to display a human-like text response;

a computerized circuitry having a generative artificial intelligence model configured to accept said text input and configured to use deep learning to produce said human-like text response as a function of the accepted natural language text input; and

one or more processors; and

one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the instructions being representative of steps of:

receiving said text input from said computerized input device;

defining a query response framework, including said query context, and said selected query response structure;

receiving from said computerized database segment type identifiers of said selected query response structure, and said at least one query generation rule associated with each one of the segment type identifiers of the selected query response structure;

for each segment type identifier of the selected query response structure:

forming a data combination through concatenation, including of the inputs representative of the query context, the segment type identifier, the query generation rule associated with the segment type identifier, and query subject,

providing the data combination to the generative artificial intelligence model,

receiving the human-like text response generated by the generative artificial intelligence model as a function of the provided data combination,

accumulating the human-like text responses received for each segment to form a global query response, and

displaying the global query response on said computerized interface.

2 . The system according to claim 1 , in which, during the step of receiving an input representative of a query response structure, said structure comprises at least one sub-segment type identifier, said sub-segment type identifier being associated with a segment type identifier or with a sub-segment type identifier.

3 . The system according to claim 1 , which further comprises:

prior to the step of receiving a natural language text input representative of a query subject, a step of providing, to a computerized interface, a preset natural language text input comprising an incomplete natural language text,

a step of completing, by a user upon the computerized interface, the preset natural language text input by adding natural language text to the preset natural language text,

said completed preset natural language text being used during the step of receiving a natural language text input representative of a query subject.

4 . The system according to claim 1 , in which at least one preset generation rules is defined by a hybrid query input, comprising both natural language text input and interpretable programming language text input, said hybrid query input being used during the step of forming a combination.

5 . The system according to claim 4 , which further comprises:

a step of dynamically instantiating interpretable programming language variables representative of natural language text elements as a function of at least one of:

the received natural language text input representative of a query subject,

the received natural language text input representative of a query context, and

the received input representative of a query structure,

a step of transposing, in the hybrid query input, said natural language text elements by said instantiated variables in the interpretable programming language to form an adapted hybrid query input, said adapted hybrid query input being used during the step of forming a combination.

6 . The system according to claim 1 , in which the step of defining a query response framework comprises a step of receiving a digital identifier representative of a query intention.

7 . The system according to claim 1 , in which the step of defining a query response framework comprises a step of receiving a digital identifier representative of a query objective.

8 . The system according to claim 1 , in which the step of defining a query response framework comprises a step of receiving a digital identifier representative of a query audience.

9 . The system according to claim 1 , in which the step of defining a query response framework comprises a step of receiving a digital identifier representative of a query skillset.

10 . The system according to claim 9 , in which at least one preset generation rule is set as a function of the query skillset received.

11 . The system according to claim 1 , in which the step of defining a query response framework comprises a step of receiving a digital identifier representative of a query objective.

12 . The system of claim 1 , wherein said computerized input device is further configured to receive input text representative of a query response structure including at least two segment type identifiers and at least one preset query generation rule associated with each segment type identifier; and,

wherein said one or more processors are configured to add said query response structure to said plurality of prestored query response structures in said computerized database.

13 . A computer-implemented method to query interpreted content from a generative artificial intelligence model, comprising the steps of:

receiving a text input, said text input is a natural language text including a query subject, query context, and a structure template identifier representative of a selected query response structure, wherein said query response structure is selected from a library of a plurality of prestored query response structures, each of which includes at least two individual segment type identifiers, and at least one query generation rule associated with each one of the segment type identifiers;

defining a query response framework, including said query context, and said selected query response structure;

receiving from said library segment type identifiers of said selected query response structure, and said at least one query generation rule associated with each one of the segment type identifiers of the selected query response structure;

for each segment type identifier of the selected query response structure:

forming a data combination through concatenation, including of the inputs representative of the query context, the segment type identifier, the query generation rule associated with the segment type identifier, and query subject,

providing the data combination to the generative artificial intelligence model,

receiving the human-like text response generated by the generative artificial intelligence model as a function of the provided combination,

accumulating the human-like text responses received for each segment to form a global query response, and

providing the global query response to a computerized interface.