Autonomous multifactor generative artificial intelligence framework
Various embodiments are directed to apparatuses, methods, computer-readable media, computer program products, and systems related to detecting a process trigger that identifies a target entity; identifying, entity data associated with the target entity; generating, using a machine learning based prediction model, a predictive asset output based at least in part on the entity data, wherein the predictive asset output comprises at least one predicted asset; generating, using a dynamic contextualization model, a multifactor contextualized asset representation for the at least one predicted asset based at least in part on the at least one predicted asset and the entity data; and transmitting the multifactor contextualized asset representation to one or more computing devices via one or more communication channels.
1 . A computer-implemented method comprising:
detecting, by one or more processors, a process trigger that identifies a target entity;
identifying, by the one or more processors, entity data associated with the target entity;
generating, by the one or more processors and using a machine learning based prediction model, a predictive asset output based at least in part on the entity data, wherein the predictive asset output comprises at least one predicted asset;
generating, by the one or more processors and using a dynamic contextualization model, a multifactor contextualized asset representation for the at least one predicted asset based at least in part on the at least one predicted asset, the entity data, and communication channel data, wherein the multifactor contextualized asset representation comprises natural language generative output that integrates one or more datum representative of the at least one predicted asset with one or more datum representative of contextually relevant asset features selected from asset features associated with the at least one predicted asset; and
transmitting, by the one or more processors, the multifactor contextualized asset representation to one or more computing devices via one or more communication channels.
2 . The computer-implemented method of claim 1 , wherein generating a predictive asset output comprises inputting the entity data to the machine learning based prediction model to cause the machine learning based prediction model to analyze the entity data and generate the predictive asset output based on the analysis of the entity data.
3 . The computer-implemented method of claim 1 , wherein the machine learning based prediction model is configured to generate the predictive asset output further based at least in part on one or more optimization parameters, and wherein the one or more optimization parameters comprise one or more predefined configuration metrics.
4 . The computer-implemented method of claim 1 , wherein the machine learning based prediction model is configured to generate the predictive asset output further by analyzing agent data for an agent associated with the target entity.
5 . The computer-implemented method of claim 1 , wherein the process trigger comprises an API request transmitted from a client computing device.
6 . The computer-implemented method of claim 1 , wherein generating the multifactor contextualized asset representation comprises:
predicting one or more contextually relevant asset features associated with the at least one predicted asset; and
modifying the predictive asset output to include the one or more contextually relevant asset features.
7 . The computer-implemented method of claim 1 , wherein the entity data comprises a plurality of entity data segments that comprise one or more of: (i) historical transactions data, (ii) demographic data, (iii) behavioral data, or (iv) interaction data.
8 . The computer-implemented method of claim 7 , wherein the interaction data comprises one or more of text data, audio data, or video data associated with the target entity.
9 . The computer-implemented method of claim 7 , wherein generating the predictive asset output based on the entity data comprises analyzing at least a first set of entity data segments from the plurality of entity data segments and generating the multifactor contextualized asset representation comprises analyzing a second set of entity data segments from the plurality of entity data segments.
10 . The computer-implemented method of claim 9 , wherein the first set of entity data segments and the second set of entity data segments are same.
11 . The computer-implemented method of claim 9 , wherein the first set of entity data segments comprise at least one entity data segment that is different from the second set of entity data segments.
12 . The computer-implemented method of claim 1 , wherein generating the multifactor contextualized asset representation comprises:
generating a prompt for the dynamic contextualization model; and
autonomously inputting the prompt to the dynamic contextualization model.
13 . The computer-implemented method of claim 1 , wherein generating the multifactor contextualized asset representation using the dynamic contextualization model further comprises generating the multifactor contextualized asset representation based at least in part by analyzing agent data for an agent associated with the target entity.
14 . The computer-implemented method of claim 1 , wherein the dynamic contextualization model is a large language model.
15 . The computer-implemented method of claim 1 , wherein the machine learning based prediction model comprises one or more of: (i) a decision tree machine learning or (ii) a deep learning neural network machine learning model.
16 . The computer-implemented method of claim 1 , further comprising storing the multifactor contextualized asset representation.
17 . The computer-implemented method of claim 1 , further comprising:
receiving, via a user interface, feedback data associated with the multifactor contextualized asset representation; and
providing the feedback data to the dynamic contextualization model.
18 . The computer-implemented method of claim 1 , wherein the machine learning based prediction model and the dynamic contextualization model are connected models, and wherein the predictive asset output is autonomously input to the dynamic contextualization model via a prompt.
19 . A system comprising one or more processors and at least one non-transitory memory comprising instructions that, with the one or more processors, cause the system to:
detect a process trigger that identifies a target entity;
identify, entity data associated with the target entity;
generate, using a machine learning based prediction model, a predictive asset output based at least in part on the entity data, wherein the predictive asset output comprises at least one predicted asset;
generate, using a dynamic contextualization model, a multifactor contextualized asset representation for the at least one predicted asset based at least in part on the at least one predicted asset, the entity data, and communication channel data, wherein the multifactor contextualized asset representation comprises natural language generative output that integrates one or more datum representative of the at least one predicted asset with one or more datum representative of contextually relevant asset features selected from asset features associated with the at least one predicted asset; and
transmit the multifactor contextualized asset representation to one or more computing devices via one or more communication channels.
20 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
detecting a process trigger that identifies a target entity;
identifying entity data associated with the target entity;
generating, using a machine learning based prediction model, a predictive asset output based at least in part on the entity data, wherein the predictive asset output comprises at least one predicted asset;
generating, using a dynamic contextualization model, a multifactor contextualized asset representation for the at least one predicted asset based at least in part on the at least one predicted asset, the entity data, and communication channel data, wherein the multifactor contextualized asset representation comprises natural language generative output that integrates one or more datum representative of the at least one predicted asset with one or more datum representative of contextually relevant asset features selected from asset features associated with the at least one predicted asset; and
transmitting the multifactor contextualized asset representation to one or more computing devices via one or more communication channels.