Authenticated customization of machine-learning models

Patent metadata

Field	Value
Publication number	US-2025094804-A1
Application number	US-202418883407-A
Country	US
Kind code	A1
Filing date	Sep 12, 2024
Priority date	Sep 15, 2023
Publication date	Mar 20, 2025
Grant date	—

Abstract

Techniques are disclosed for providing an authenticated model customization for a machine-learning model. A cloud service provider platform accesses a message including, at least, timestamp data and user identification data. A training group of data entities is identified based on the data in the message. A training dataset is determined based on the training group of data entities. A machine-learning model is modified based on the training dataset. The modified machine-learning model is provided during an authenticated network session associated with the user identification data. In some embodiments, the modification of the machine-learning model is removed based on a determination that the authenticated network session had ended.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
accessing a message that includes timestamp data and user identification data; identifying a training group of data entities including patient information, wherein each data entity in the training group:
(i) is included in an appointment dataset associated with the user identification data, and
(ii) includes appointment time data within a time window that is based on the timestamp data;
determining, based on the training group of the data entities, at least one training dataset; modifying at least one pre-trained machine-learning model based on the at least one training dataset; and providing, during an authenticated network session associated with the user identification data, the at least one modified pre-trained machine-learning model.

2 . The computer-implemented method of claim 1 , further comprising:
accessing an additional message indicating an end of the authenticated network session associated with the user identification data; and removing, from the at least one pre-trained machine-learning model, the modification that is based on the at least one training dataset.

3 . The computer-implemented method of claim 1 , wherein the training group of the data entities comprises secured data entities, and the authenticated network session grants access, to a client device that is authenticated via the user identification data, to the patient information included in the secured data entities.

4 . The computer-implemented method of claim 1 , wherein the message is generated in response to a client application executing on a client device associated with the user identification data, the message indicating that the client application is granted access to a computing resource.

5 . The computer-implemented method of claim 1 , wherein the time window includes one or more of:
(a) a forward time window including a first period of time subsequent to the timestamp data, (b) a backwards time window including a second period of time prior to the timestamp data, or (c) an extended time window in which a most recent appointment time data item is included.

6 . The computer-implemented method of claim 1 , further comprising:
during the authenticated network session, accessing an additional message that includes the user identification data and modified timestamp data; determining an additional training dataset that is based on at least one additional data entity, the additional data entity (i) being included in the appointment dataset associated with the user identification data, and (ii) including additional appointment time data that is within an additional time window based on the additional timestamp data; further modifying the at least one pre-trained machine-learning model based on the additional training dataset; and providing, during the authenticated network session associated with the user identification data, the at least one further modified pre-trained machine-learning model.

7 . The computer-implemented method of claim 6 , wherein further modifying the at least one pre-trained machine-learning model further comprises removing, from the at least one pre-trained machine-learning model, the modification that is based on the at least one training dataset.

8 . The computer-implemented method of claim 1 , wherein identifying the training group of data entities further comprises:
determining a group of data entities associated with the user identification data; determining a first subset of the group of data entities, wherein each data entity included in the first subset is included in the appointment dataset associated with the user identification data; determining a second subset of the group of data entities, wherein each data entity included in the second subset includes the appointment time data within the time window; and selecting, from the group of data entities associated with the user identification data, a third subset of the group of data entities, wherein each data entity in the third subset is included in the first subset and the second subset, wherein the training group of the data entities includes each data entity included in the third subset.

9 . The computer-implemented method of claim 1 , wherein:
the at least one pre-trained machine-learning model comprises a speech recognition pre-trained machine-learning model; the at least one training dataset comprises a speech recognition training dataset; determining the speech recognition training dataset comprises:
extracting, from the training group of the data entities, text data associated with the patient information included in the training group of the data entities, and
generating a customization recognition vocabulary that includes the extracted text data, wherein the speech recognition training dataset includes the customization recognition vocabulary; and
the modifying the at least one pre-trained machine-learning model based on the at least one training dataset comprises modifying the speech recognition pre-trained machine-learning model based on the speech recognition training dataset

10 . The computer-implemented method of claim 9 , further comprising:
accessing an additional message indicating an end of the authenticated network session associated with the user identification data; and removing, from the speech recognition pre-trained machine-learning model, the speech recognition training dataset that includes the customization recognition vocabulary.

11 . The computer-implemented method of claim 1 , wherein:
the at least one pre-trained machine-learning model comprises a language pre-trained machine-learning model; the at least one training dataset comprises a language training dataset; determining the language training dataset comprises:
identifying, in the training group of the data entities, a group of data objects associated with the patient information included in the training group of the data entities; and
modifying, for each particular data object in the group of data objects, a respective searchable data entity to include the particular data object, wherein the language training dataset includes the respective searchable data entity for each particular data object in the group of data objects; and
the modifying the at least one pre-trained machine-learning model based on the at least one training dataset comprises modifying the language pre-trained machine-learning model based on the language training dataset.

12 . The computer-implemented method of claim 11 , further comprising:
accessing an additional message indicating an end of the authenticated network session associated with the user identification data; and removing, from the language pre-trained machine-learning model, the language training dataset that includes the respective searchable data entity for each particular data object in the group of data objects.

13 . A system comprising:
one or more processing systems; and one or more computer-readable media storing instructions which, when executed by the one or more processing systems, cause the system to perform operations comprising:
accessing a message that includes timestamp data and user identification data;
identifying a training group of secured data entities including patient information, wherein each secured data entity in the training group:
(i) is included in an appointment dataset associated with the user identification data, and
(ii) includes appointment time data within a time window that is based on the timestamp data;

determining, based on the training group of the secured data entities, at least on

Assignees

• Oracle Int Corp

Inventors

• Suravarapu Shashi Prasad
• Saikia Amitabh
• Gadde Srinivasa Phani Kumar
• Barra Diego Andres Cornejo
• Maheu Cody Nicholas
• Wu Yuanxu
• Mujumdar Laukik Satish
• Carter Daniel Bruce
• Medeck Zachary Jon-Christian
• Manakkattil Jobinesh Purushothaman
• Dahal Sangeet
• Gupta Shweta Shyamsunder

Classifications

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• H04L2463/121

  Timestamp · CPC title

• G06N3/082 Primary

  modifying the architecture, e.g. adding, deleting or silencing nodes or connections · CPC title

• G06F21/6245 Primary

  Protecting personal data, e.g. for financial or medical purposes · CPC title