Granted Patent B1

US 12,505,133 · App. 19/191,042 · Granted Dec 23, 2025

Inventor: Steven David Alperin (New York, NY)

Assignee: SurvivorNet, Inc.

G06F16/3334G06F16/33295G06F16/583

Abstract

Claims (96)

1 . An apparatus for generating resource output as a function of a plurality of queries and multimodal data, wherein the apparatus comprises:

at least a computing device, wherein the computing device comprises:

a memory; and

at least a processor communicatively connected to the memory, wherein the memory contains instructions configuring

the at least a processor to:

receive, using the at least a processor, the multimodal data associated with a user profile, wherein the multimodal data comprises passive data and active data, wherein receiving the multimodal data associated with the user profile comprises retrieving passive data using a web-crawler as a function of user data;

receive, using a chatbot, a first query of the plurality of queries;

generate, using the chatbot, at least a first output of a plurality of outputs as a function of the first query and the multimodal data, wherein the plurality of outputs comprises a question data structure, wherein the question data structure comprises each output associated with a weight which comprises a relevance of the at least a first output;

generate, using an evaluation model, a score associated with the at least a first output using system feedback, wherein the score reflects an accuracy of the at least a first output in addressing the received first query of the plurality of queries and wherein generating the score using the evaluation model further comprises:

receiving a chatbot training dataset, wherein the chatbot training dataset correlates a plurality of historical output data to a plurality of historical subsequent query data;

training, iteratively, the evaluation model using the chatbot training dataset, wherein training the evaluation model includes retraining the evaluation model with feedback from previous iterations of the evaluation model;

generate the score using the retrained evaluation model; and

recommend adjustments to improve future output of the evaluation model;

adjust, within the question data structure, at least the weight associated with the at least a first output;

select, from the question data structure, a plurality of questions, wherein the plurality of questions comprises a first question having a highest weight within the data structure and a successive question having a second highest weight within the question data structure; and

display, using a downstream device communicatively connected to the computing device, the first question followed temporally by the second question.

2 . The apparatus of claim 1 , wherein the processor is further configured to process, using an image processor, the multimodal data by:

receiving image data;

identifying one or more features within the image data;

determining a correlation between the one or more features and the successive question;

generating a processed image output based on the correlation; and

displaying, using the downstream device, the at least a first output comprising the processed image output.

3 . The apparatus of claim 1 , wherein the at least a processor is configured to utilize a first application programming interface, wherein the application programming interface is configured to:

authenticate user credentials associated with the user profile;

access, using the authenticated user credentials, a data repository;

retrieve the multimodal data comprising a plurality of electronic records from the data repository; and

transmit the plurality of electronic records to the chatbot, wherein the chatbot is configured to generate the at least a first output.

4 . The apparatus of claim 3 , wherein the at least a processor is configured to utilize a second application programming interface, wherein the application programming interface is configured to:

identify, using a node protocol, an optimal node of an edge system;

establish a connection to the optimal node of the edge system;

process, using the optimal node, the multimodal data;

generate, using the optimal node, the plurality of outputs; and

transmit the plurality of outputs to the downstream device.

5 . The apparatus of claim 4 , wherein the node protocols comprise choosing the optimal node as a function of geolocation data.

6 . The apparatus of claim 4 , wherein the at least a processor is configured to utilize a third application programming interface, wherein the application programming interface is configured to:

establish a cloud computing connection to a remote data center;

receive multimodal data from the remote data center as a function of the first query; and

transmit processed data to the chatbot from the remote data center.

7 . The apparatus of claim 1 , wherein the chatbot comprises a machine learning model, wherein the machine learning model is iteratively trained on the chatbot training dataset.

8 . The apparatus of claim 1 , wherein the chatbot further comprises a large language model, wherein the large language model is configured to:

receive the multimodal data;

processes the multimodal data using a trained neural network, wherein processing comprises:

extracting, using embedding techniques, at least an attribute from the multimodal data;

identifying, using the at least an attribute, at least a pattern from the multimodal data; and

generating, using the at least a pattern, return data;

generate, using the return data, the at least a first output of the plurality of outputs.

9 . The apparatus of claim 1 , further comprising:

identifying, using the evaluation model, recalibration data comprising a variance from target output, wherein the variance is derived from the score; and

retraining, the evaluation model, using the recalibration data.

10 . The apparatus of claim 1 , wherein the at least a first output of the plurality of outputs comprises at least a resource.

11 . A method for generating resource output as a function of a plurality of queries and multimodal data, wherein the method comprises:

receiving, using the at least a processor, the multimodal data associated with a user profile, wherein the multimodal data comprises passive data and active data, wherein receiving the multimodal data associated with the user profile comprises retrieving passive data using a web-crawler as a function of user data;

receiving, using a chatbot, a first query of the plurality of queries;

generating, using the chatbot, at least a first output of a plurality of outputs as a function of the first query and the multimodal data, wherein the plurality of outputs comprises a question data structure, wherein the question data structure comprises each output associated with a weight which comprises a relevance of the at least a first output;

generating, using an evaluation model, a score associated with the at least a first output using system feedback, wherein the score reflects an accuracy of the at least a first output in addressing the received first query of the plurality of queries and wherein generating the score using the evaluation model further comprises:

receiving a chatbot training dataset, wherein the chatbot training dataset correlates a plurality of historical output data to a plurality of historical subsequent query data;

training, iteratively, the evaluation model using the chatbot training dataset, wherein training the evaluation model includes retraining the evaluation model with feedback from previous iterations of the evaluation model;

generate the score using the retrained evaluation model; and

recommend adjustments to improve future output of the evaluation model;

adjusting, within the question data structure, at least the weight associated with the at least a first output;

selecting, from the question data structure, a plurality of questions, wherein the plurality of questions comprises a first question having a highest weight within the data structure and a successive question having a second highest weight within the question data structure; and

displaying, using a downstream device communicatively connected to the computing device, the first question followed temporally by the second question.

12 . The method of claim 11 , wherein the processor is further configured to process, using an image processor, the multimodal data by:

receiving image data;

identifying one or more features within the image data;

determining a correlation between the one or more features and the successive question;

generating a processed image output based on the correlation; and

displaying, using the downstream device, the at least a first output comprising the processed image output.

13 . The method of claim 11 , wherein the at least a processor is configured to utilize a first application programming interface, wherein the application programming interface is configured to:

authenticate user credentials associated with the user profile;

access, using the authenticated user credentials, a data repository;

retrieve the multimodal data comprising a plurality of electronic records from the data repository; and

transmit the plurality of electronic records to the chatbot, wherein the chatbot is configured to generate the at least a first output.

14 . The method of claim 13 , wherein the at least a processor is configured to utilize a second application programming interface, wherein the application programming interface is configured to:

identify, using a node protocol, an optimal node of an edge system;

establish a connection to the optimal node of the edge system;

process, using the optimal node, the multimodal data;

generate, using the optimal node, the plurality of outputs; and

transmit the plurality of outputs to the downstream device.

15 . The method of claim 14 , wherein the node protocols comprise choosing the optimal node as a function of geolocation data.

16 . The method of claim 14 , wherein the at least a processor is configured to utilize a third application programming interface, wherein the application programming interface is configured to:

establish a cloud computing connection to a remote data center;

receive multimodal data from the remote data center as a function of the first query; and

transmit processed data to the chatbot from the remote data center.

17 . The method of claim 11 , wherein the chatbot comprises a machine learning model, wherein the machine learning model is iteratively trained on the chatbot training dataset.

18 . The method of claim 11 , wherein the chatbot further comprises a large language model, wherein the large language model is configured to:

receive the multimodal data;

processes the multimodal data using a trained neural network, wherein processing comprises:

extracting, using embedding techniques, at least an attribute from the multimodal data;

identifying, using the at least an attribute, at least a pattern from the multimodal data; and

generating, using the at least a pattern, return data;

generate, using the return data, the at least a first output of the plurality of outputs.

19 . The method of claim 11 , further comprising:

identifying, using the evaluation model, recalibration data comprising a variance from target output, wherein the variance is derived from the score; and

retraining, the evaluation model, using the recalibration data.

20 . The method of claim 11 , wherein the at least a first output of the plurality of outputs comprises at least a resource.

Assignments (1)

References Cited (11)