# US 2025/0219968 A1 · Generative machine learning model for personalized knowledge session content

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0219968 A1
- Document ID: US20250219968A1
- Status: Published application
- Kind: A1
- Application number: 18/400,503
- Filed: 2023-12-29
- Published: 2025-07-03
- Earliest claimed: 2023-12-29
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Qixu Gong; Benjamin L. Chang; Qihong Shao; David C. White, JR.
- Web page: https://patentgrep.com/patent/US20250219968A1

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06N 3/045: Combinations of networks
- G06N 20/00: Machine learning
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method, computer system, and computer program product are provided for generating personalized knowledge session content using a generative machine learning model. User profile data of a plurality of users and service description data that is descriptive of a service are processed to assign the plurality of users to a plurality of user groups. A personalized message is generated for each user group based on the user profile data and the service description data, wherein the personalized message is generated using one or more machine learning models. Each personalized message is provided to each user group and feedback data is collected based on the providing of each personalized message. Based on analyzing of the feedback data, one or more of: the user profile data, the one or more machine learning models, and the service description data are updated.

## Claims

### Claim 1

A computer-implemented method comprising:
processing user profile data of a plurality of users and service description data that is descriptive of a service to assign the plurality of users to a plurality of user groups;
generating a personalized message for each user group based on the user profile data and the service description data, wherein the personalized message is generated using one or more machine learning models;
providing each personalized message to each user group and collecting feedback data based on the providing of each personalized message; and
based on analyzing of the feedback data, updating one or more of: the user profile data, the one or more machine learning models, and the service description data.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein generating the personalized message comprises:
generating an initial message, based on the service description data, using a first machine learning model; and
generating the personalized message, using a second machine learning model, based on the initial message and the user profile data.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the second machine learning model comprises a text-to-text transformer that is updated using the feedback data.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein generating the personalized message comprises comparing the personalized message to the initial message to determine that the personalized message does not differ from the initial message by a threshold amount.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein each personalized message indicates particular features of the service that are selected based on the user profile data for each user group for which each personalized message is generated.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the user profile data includes historical user behavior, contracts and licenses associated with the plurality of users, and usage of particular services by the plurality of users.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the feedback data includes one or more of: explicit feedback data provided by one or more users of the plurality of users, and implicit feedback data that is collected based on interactions by one or more users of the plurality of users with the personalized message.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the implicit feedback data includes interaction data that is descriptive of interactions of one or more users of the plurality of users interacted with descriptions of particular features of the service.

### Claim 9

A system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising instructions to:
processing user profile data of a plurality of users and service description data that is descriptive of a service to assign the plurality of users to a plurality of user groups;
generating a personalized message for each user group based on the user profile data and the service description data, wherein the personalized message is generated using one or more machine learning models;
providing each personalized message to each user group and collecting feedback data based on the providing of each personalized message; and
based on analyzing of the feedback data, updating one or more of: the user profile data, the one or more machine learning models, and the service description data.

### Claim 10 (depends on 9)

The system of claim 9, wherein the instructions for generating the personalized message comprise instructions to:
generate an initial message, based on the service description data, using a first machine learning model; and
generate the personalized message, using a second machine learning model, based on the initial message and the user profile data.

### Claim 11 (depends on 10)

The system of claim 10, wherein the second machine learning model comprises a text-to-text transformer that is updated using the feedback data.

### Claim 12 (depends on 10)

The system of claim 10, wherein generating the personalized message comprises comparing the personalized message to the initial message to determine that the personalized message does not differ from the initial message by a threshold amount.

### Claim 13 (depends on 9)

The system of claim 9, wherein each personalized message indicates particular features of the service that are selected based on the user profile data for each user group for which each personalized message is generated.

### Claim 14 (depends on 9)

The system of claim 9, wherein the user profile data includes historical user behavior, contracts and licenses associated with the plurality of users, and usage of particular services by the plurality of users.

### Claim 15 (depends on 9)

The system of claim 9, wherein the feedback data includes one or more of: explicit feedback data provided by one or more users of the plurality of users, and implicit feedback data that is collected based on interactions by one or more users of the plurality of users with the personalized message.

### Claim 16 (depends on 15)

The system of claim 15, wherein the implicit feedback data includes interaction data that is descriptive of interactions of one or more users of the plurality of users interacted with descriptions of particular features of the service.

### Claim 17

One or more non-transitory computer readable storage media having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform operations including:
processing user profile data of a plurality of users and service description data that is descriptive of a service to assign the plurality of users to a plurality of user groups;
generating a personalized message for each user group based on the user profile data and the service description data, wherein the personalized message is generated using one or more machine learning models;
providing each personalized message to each user group and collecting feedback data based on the providing of each personalized message; and
based on analyzing of the feedback data, updating one or more of: the user profile data, the one or more machine learning models, and the service description data.

### Claim 18 (depends on 17)

The one or more non-transitory computer readable storage media of claim 17, wherein the program instructions for generating the personalized message further cause the computer to:
generate an initial message, based on the service description data, using a first machine learning model; and
generate the personalized message, using a second machine learning model, based on the initial message and the user profile data.

### Claim 19 (depends on 18)

The one or more non-transitory computer readable storage media of claim 18, wherein the second machine learning model comprises a text-to-text transformer that is updated using the feedback data.

### Claim 20 (depends on 18)

The one or more non-transitory computer readable storage media of claim 18, wherein generating the personalized message comprises comparing the personalized message to the initial message to determine that the personalized message does not differ from the initial message by a threshold amount.
