Search

US-20260127447-A1 - SYSTEM AND METHOD FOR AUTOMATED CATALOGING AND BUILDING MACHINE LEARNING MODELS

US20260127447A1US 20260127447 A1US20260127447 A1US 20260127447A1US-20260127447-A1

Abstract

Aspects of the subject disclosure may include, for example, a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including: selecting a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models; selecting a second bbDNA having a second weight from the catalog, wherein the second bbDNA is associated with at least one ML model in the plurality of ML models; and creating a new ML model based on a combination of the first bbDNA and the second bbDNA. Other embodiments are disclosed.

Inventors

  • Mukundan Sarukkai
  • Eshrat Huda

Assignees

  • AT&T INTELLECTUAL PROPERTY I, L.P.

Dates

Publication Date
20260507
Application Date
20260102

Claims (20)

  1. 1 . A device, comprising: a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising: selecting building block pattern functions (bbDNAs) having different weights from a catalog, wherein a first bbDNA of the bbDNAs is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the bbDNAs are associated with machine learning (ML) models, and wherein the weights are based on a performance factor, a usage factor or a combination thereof; and creating a new ML model based on a combination of the bbDNAs.
  2. 2 . The device of claim 1 , wherein the bbDNAs are selected based on having a description that indicates usefulness to solve a problem.
  3. 3 . The device of claim 2 , wherein the bbDNAs are selected based on the weights being greater than weights of other bbDNAs in the catalog.
  4. 4 . The device of claim 3 , wherein the performance factor is a first ratio of an actual response time to an expected response time of an ML model incorporating a respective bbDNA.
  5. 5 . The device of claim 3 , wherein the usage factor is a second ratio of a frequency of usage of the respective bbDNA to a total frequency of usage of all bbDNAs in the catalog.
  6. 6 . The device of claim 3 , wherein the weights are each a product of the performance factor and the usage factor, respectively.
  7. 7 . The device of claim 1 , wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
  8. 8 . A non-transitory, machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising: selecting building block pattern functions (bbDNAs) having different weights from a catalog, wherein a first bbDNA of the bbDNAs is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the bbDNAs are associated with machine learning (ML) models, and wherein the weights are based on a performance factor, a usage factor or a combination thereof; and creating a new ML model based on a combination of the bbDNAs.
  9. 9 . The non-transitory, machine-readable medium of claim 8 , wherein the bbDNAs are selected based on having a description that indicates usefulness to solve respective problems.
  10. 10 . The non-transitory, machine-readable medium of claim 9 , wherein the weights are greater than weights of other bbDNAs in the catalog.
  11. 11 . The non-transitory, machine-readable medium of claim 10 , wherein the performance factor is a first ratio of an actual response time to an expected response time of an ML model incorporating a respective bbDNA.
  12. 12 . The non-transitory, machine-readable medium of claim 10 , wherein the usage factor is a second ratio of a frequency of usage of the respective bbDNA to a total frequency of usage of all bbDNAs in the catalog.
  13. 13 . The non-transitory, machine-readable medium of claim 10 , wherein the weights are a product of the performance factor and the usage factor, respectively.
  14. 14 . The non-transitory, machine-readable medium of claim 10 , wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
  15. 15 . A method, comprising: selecting, by a processing system comprising a processor, building block pattern functions (bbDNAs) having different weights from a catalog, wherein a first bbDNA of the bbDNAs is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the bbDNAs are associated with machine learning (ML) models, and wherein the weights are based on a performance factor, a usage factor or a combination thereof; and creating, by the processing system, a new ML model based on a combination of the bbDNAs.
  16. 16 . The method of claim 15 , wherein the performance factor is a first ratio of an actual response time to an expected response time of an ML model incorporating a respective bbDNA.
  17. 17 . The method of claim 16 , wherein the usage factor is a second ratio of a frequency of usage of the respective bbDNA to a total frequency of usage of all bbDNAs in the catalog.
  18. 18 . The method of claim 17 , wherein the bbDNAs are selected based on having a description that indicates a usefulness to solve respective problems.
  19. 19 . The method of claim 17 , wherein the weights are greater than weights of other bbDNAs in the catalog.
  20. 20 . The method of claim 17 , wherein the weights are each a product of the performance factor and the usage factor, respectively.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 17/752,203 filed on May 24, 2022. All sections of the aforementioned application are incorporated herein by reference in their entirety. FIELD OF THE DISCLOSURE The subject disclosure relates to a system and method for automated cataloging and building machine learning models. BACKGROUND Machine learning (ML) models continuously evolve, learn and adapt to vast repositories of data and provide better answers to user queries. BRIEF DESCRIPTION OF THE DRAWINGS Reference will now be made to the accompanying drawings, which are not necessarily drawn to scale, and wherein: FIG. 1 is a block diagram illustrating an exemplary, non-limiting embodiment of a communications network in accordance with various aspects described herein. FIG. 2A illustrates an exemplary self-learning data flow for a system functioning within the communication network of FIG. 1 in accordance with various aspects described herein. FIG. 2B is a block diagram illustrating an example, non-limiting embodiment of an evolution of a machine-learning model in accordance with various aspects described herein. FIG. 2C is a block diagram illustrating an example, non-limiting embodiment of a process of building a new machine-learning model in accordance with various aspects described herein. FIG. 2D is a block diagram illustrating an example, non-limiting embodiment of evaluating and publishing bbDNAs of machine-learning models in accordance with various aspects described herein. FIG. 3 is a block diagram illustrating an example, non-limiting embodiment of a virtualized communication network in accordance with various aspects described herein. FIG. 4 is a block diagram of an example, non-limiting embodiment of a computing environment in accordance with various aspects described herein. FIG. 5 is a block diagram of an example, non-limiting embodiment of a mobile network platform in accordance with various aspects described herein. FIG. 6 is a block diagram of an example, non-limiting embodiment of a communication device in accordance with various aspects described herein. DETAILED DESCRIPTION The subject disclosure describes, among other things, illustrative embodiments for a system and method for automated cataloging and building ML models from inherited building block pattern functions. Other embodiments are described in the subject disclosure. One or more aspects of the subject disclosure include a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including: selecting a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models; selecting a second bbDNA having a second weight from the catalog, wherein the second bbDNA is associated with at least one ML model in the plurality of ML models; and creating a new ML model based on a combination of the first bbDNA and the second bbDNA. One or more aspects of the subject disclosure include a non-transitory, machine-readable medium, with executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, including: selecting a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models, and wherein the first bbDNA is selected based on the first weight and a first description of the first bbDNA; selecting a second bbDNA having a second weight from the catalog, wherein the second bbDNA is associated with at least one ML model in the plurality of ML models, and wherein the second bbDNA is selected based on the second weight and a second description of the second bbDNA; and creating a new ML model based on a combination of the first bbDNA and the second bbDNA. One or more aspects of the subject disclosure include a method of selecting, by a processing system including a processor, a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models, and wherein the first bbDNA is selected based on the first weight and a first description of the first bbDNA indicating usefulness of solving a problem; selecting, by the processing system, a second bbDNA having a second weight from the catalog, wherein the second bb