Search

US-20260127087-A1 - METHOD AND APPARATUS FOR IMPLEMENTING A SELECTOR MECHANISM TO DETERMINE A GENERATIVE AI ENTITY BASED ON SPECIFIC TASK REQUIREMENTS

US20260127087A1US 20260127087 A1US20260127087 A1US 20260127087A1US-20260127087-A1

Abstract

A non-transitory computer-readable storage medium, comprising instructions which, when executed by one or more processors, configure the one or more processors to implement a Generative AI entity selector mechanism including, an input configured for receiving a user request intended for a Generative AI entity to elicit an output from the Generative AI entity, selection logic configured for processing the user request to select a Generative AI entity from the set of Generative AI entities for servicing the user request and an output for generating a selection signal, which conveys an identification of the Generative AI entity selected by the selection logic.

Inventors

  • Vik PANT
  • Bahar SATELI

Assignees

  • PRICEWATERHOUSECOOPERS LLP

Dates

Publication Date
20260507
Application Date
20251031
Priority Date
20241101

Claims (20)

  1. 1 . A non-transitory computer-readable storage medium, comprising instructions which, when executed by one or more processors, configure the one or more processors to implement a Generative AI entity selector mechanism for selecting a Generative AI entity to service a user request, among a set of Generative AI entities, the selector mechanism including: a. an input configured for receiving the user request; b. selection logic configured for processing the user request and to generate as a result of the processing a selection signal, c. an output for releasing the selection signal.
  2. 2 . The non-transitory computer-readable storage medium as defined in claim 1 , wherein the selection logic is configured to derive at least in part from the request the selection signal, wherein the selection signal conveys an identification of the Generative AI entity selected among the set of Generative AI entities.
  3. 3 . The non-transitory computer-readable storage medium as defined in claim 1 , wherein the selection logic is configured to process a configuration signal that influences the selection of a Generative AI entity from the set of Generative AI entities.
  4. 4 . The non-transitory computer-readable storage medium as defined in claim 2 , wherein the request is associated with a particular user, the selector mechanism is configured to store an interaction history between the user and a particular one of the Generative AI entities.
  5. 5 . The non-transitory computer-readable storage medium as defined in claim 1 , wherein the selector mechanism includes routing logic responsive to the selection signal to route via a data network the user request to the Generative AI entity selected from the set of Generative AI entities.
  6. 6 . The non-transitory computer-readable storage medium as defined in claim 1 , wherein the selection logic conveys an association between the user request and a plurality of metrics.
  7. 7 . The non-transitory computer-readable storage medium as defined in claim 6 , wherein the plurality of metrics includes intrinsic metrics.
  8. 8 . The non-transitory computer-readable storage medium as defined in claim 7 , wherein the plurality of metrics includes extrinsic metrics.
  9. 9 . The non-transitory computer-readable storage medium as defined in claim 7 , wherein the selection logic is configured to process the user request to derive a ranking against one or more of the intrinsic metrics.
  10. 10 . The non-transitory computer-readable storage medium as defined in claim 9 , wherein the selection logic includes a neural network-based classifier to derive the ranking.
  11. 11 . A non-transitory computer-readable storage medium, comprising instructions which, when executed by one or more processors, configure the one or more processors to: a. implement a Generative AI entity selector mechanism, including: i. an input configured for receiving a user request intended for a Generative AI entity to elicit an output from the Generative AI entity; ii. selection logic configured for generating a selection signal conveying a selection of one or more Generative AI entities among a plurality of Generative AI entities for servicing the user request, and output the selection signal via an output b. implement a Generative AI entity selector monitor configured to output data conveying one or more characteristics of an operation of the Generative AI entity selector.
  12. 12 . The non-transitory computer-readable storage medium as defined in claim 11 , wherein the data conveying the one or more characteristics defines a usage profile of the use of the plurality of Generative AI entities wherein the usage profile establishes comparative frequency of utilization metrics among the plurality of Generative AI entities.
  13. 13 . The non-transitory computer-readable storage medium as defined in claim 12 wherein the data conveying the one or more characteristics conveys information about cost incurred for using one or more of the Generative AI entities.
  14. 14 . The non-transitory computer-readable storage medium as defined in claim 12 , the data conveying the one or more characteristics establishes comparative cost metrics of utilization among the plurality of Generative AI entities.
  15. 15 . The non-transitory computer-readable storage medium as defined in claim 12 , wherein the data representative of the one or more characteristics establishes comparative latency metrics among the plurality of Generative AI entities.
  16. 16 . The non-transitory computer-readable storage medium as defined in claim 11 , implementing a dashboard application providing a dashboard interface for allowing a user to visualize the data conveying the one or more characteristics.
  17. 17 . A non-transitory computer-readable storage medium, comprising instructions which, when executed by one or more processors, configure the one or more processors to: a. implementing a GUI for allowing a user to control a behavior of a Generative AI entity selector mechanism; b. implementing on the GUI an input mechanism that provides a plurality of selection choices to modify an aspect of the behavior exhibited by the Generative AI entity selector; c. in response to user selection of a choice among the plurality of choices, deriving a configuration signal that influences a selection of a Generative AI entity among a plurality of Generative AI entities, by the Generative AI entity selector mechanism.
  18. 18 . The non-transitory computer-readable storage medium as defined in claim 17 , wherein the plurality of selection choices includes a selection choice configured to bias an operation of the Generative AI entity selector in favor of a lower cost of operation.
  19. 19 . The non-transitory computer-readable storage medium as defined in claim 17 , wherein the plurality of selection choices includes a selection choice configured to bias an operation of the Generative AI entity selector in favor of a lower latency.
  20. 20 . The non-transitory computer-readable storage medium as defined in claim 17 , wherein the GUI is configured to display a usage profile of the selector mechanism.

Description

CROSS-REFERENCE TO RELATED APPLICATION The present application claims the priority of Canadian Patent Application No. 3,256,853, filed on Nov. 1, 2025 and incorporated herein by reference. FIELD OF THE INVENTION The present invention relates to the field of Generative AI entities and to methods and systems for the management of such Generative AI entities. More specifically, the invention relates to a computer implemented selector mechanism configured to select a Generative AI entity among a plurality of Generative AI entities, and to optionally route a user request to the selected Generative AI entity for processing and output generation. Optionally, the invention integrates a dynamic feedback mechanism, enabling continuous learning and adaptation of the selector mechanism based on operational performance and user satisfaction metrics, thereby progressively enhancing the efficacy and precision of the Generative AI entity selection process over time. BACKGROUND OF THE INVENTION Generative AI entities offer numerous economic benefits that contribute to enhanced productivity, efficiency, and innovation across various industries. These entities can automate and optimize processes, leading to cost savings and increased output. For instance, in content creation and marketing, Generative AI can generate personalized advertisements, product descriptions, or social media content at scale, reducing the time and resources required for manual content production. In manufacturing, Generative AI can assist in designing and optimizing complex products, leading to improved efficiency and reduced material waste. Furthermore, Generative AI entities can facilitate data analysis and decision-making by quickly generating insights from vast amounts of information, enabling businesses to make data-driven decisions with greater speed and accuracy. Overall, the adoption of Generative AI entities has the potential to drive economic growth, foster innovation, and create new opportunities in diverse sectors. Generative AI entities exhibit a range of operational performances and associated usage costs, influenced by various technical and computational factors. Commonly, these entities adopt a revenue model that is predicated on a per-token charging basis. In this context, a token is defined as the fundamental unit of language processed by a Generative AI entity, representing a discrete element of input provided by the user. This unit can encompass an entire word, symbol, or a segment of a word within a given input sentence. The intricacy of a user's request has a direct correlation with the number of tokens required for processing. As such, more complex requests necessitate a greater token count, leading to an increment in the operational cost for that specific user interaction. This cost variability is integral to the system's design, ensuring that the pricing structure is reflective of the computational resources and processing time expended. In technical terms, the token-based billing model aligns the cost to the computational intensity and complexity of the language processing task. This approach allows for a flexible and scalable pricing strategy, accommodating a wide range of user needs from simple queries (e.g., closed-form questions) to more elaborate and demanding requests (e.g., question answering using contextual information). Consequently, users engaging with more advanced or extensive interactions with the Generative AI entity can expect a proportional increase in the cost, mirroring the higher level of resource utilization and processing time required by the system to fulfill such requests. A notable feature in many Generative AI entities is the incorporation of a dynamic feedback mechanism. This mechanism facilitates continuous learning and refinement of the system's Large Language Model (LLM) during usage. The evolving nature of the LLM, fostered by real-time user interactions and feedback, contributes to the progressive enhancement of the system's performance. However, this evolutionary aspect introduces a degree of unpredictability in the system's outputs. For instance, there is a potential for the development of biases within the LLM or impact their output through runtime attacks, necessitating monitoring and proactive intervention by the system operators to mitigate such tendencies. In contrast, there is also a category of Generative AI entities that include static variants, which do not employ a dynamic feedback loop. In these static systems, the LLM remains unchanged post-deployment. While the absence of ongoing learning capabilities limits the system's ability to adapt and improve over time, it also provides a higher degree of predictability in terms of output. Once a static Generative AI entity is commissioned and its operational characteristics, such as bias tendencies, are thoroughly understood, these traits remain consistent over its operational lifespan. This stability translates into reduced requirements f