# US 2020/0403955 A1 · Systems and methods to prioritize chat rooms using machine learning

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

- Number: US 2020/0403955 A1
- Document ID: US20200403955A1
- Status: Published application
- Kind: A1
- Application number: 16/448,257
- Filed: 2019-06-21
- Published: 2020-12-24
- Earliest claimed: 2019-06-21
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Eric CHEN; Keith GRIFFIN
- Web page: https://patentgrep.com/patent/US20200403955A1

## CPC

- H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L 51/52: for supporting social networking services
- G06N 20/00: Machine learning
- H04L 51/214: using selective forwarding
- H04L 67/306: User profiles
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Chat room content classification, in an online communication environment, where higher applicable chat rooms are prioritized for a user, is provided. First, an chat room service receives chat room content for at least a first chat room and a second chat room. A chat room analyzer can then analyze a characteristic(s) associated with the first chat room and/or the second chat room. Based on the characteristic, the chat room determines that the first chat room is more applicable to the user. Then, a user interface may be presented to the user where the first chat room is prioritized (or ranked) over the second chat room.

## Claims

### Claim 1

A method comprising:
receiving content for at least a first chat room and a second chat room;
analyzing a characteristic, associated with the first chat room and the second chat room, against a user profile, the user profile comprising a plurality of characteristics and an associated weight assigned to each of the plurality of characteristics;
determining that the first chat room is more applicable to the user than the second chat room, wherein determining that the first chat room is more applicable to the user than the second chat room comprises:
determining a score for each of the first chat room and the second chat room based on the characteristic associated with the first chat room and the second chat room and the plurality of characteristics and the associated weight assigned to each of the plurality of characteristics for the user profile, and
determining that the first room is more applicable to the user based on the score; and
based on determining that the first chat room is more applicable than the second chat room, providing a user interface to the user where the first chat room is prioritized over the second chat room.

### Claim 2 (depends on 1)

The method of claim 1, wherein the characteristic is one of a mention of the user, a frequency of recent posts, a uploaded file, a number of participants, an amount of time between posts, a relationship between the user and a poster, and/or a presence of a keyword.

### Claim 3 (depends on 1)

The method of claim 1, wherein the user profile determines a likelihood that the user will post a message to the chat room.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
waiting a period of time; and
after the period of time, reanalyzing the characteristic.

### Claim at position 5

-6. (canceled)

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
providing, on the user interface, a view of the user profile;
receiving an input associated with the user interface; and
based on the input, eliminating one of the plurality of characteristics.

### Claim 8 (depends on 1)

The method of claim 1, wherein the user profile is associated with a machine learning model, wherein developing the machine learning model comprises:
for each chat room, parse the content associated with the chat room into two or more instances;
for each instance, extract the characteristic;
determine if a user posted a message during a first instance;
if a user posted a message during the first instance, indicate user interest in the first instance; and
based on the user interest in the first instance, weight the characteristic associated with the first instance.

### Claim 9 (depends on 8)

The method of claim 8, wherein the two or more instances are parsed based on a read event of the user.

### Claim 10 (depends on 9)

The method of claim 9, further comprising updating the machine learning model periodically based on new content in the two or more chat rooms.

### Claim 11

A non-transitory computer readable medium having stored thereon instructions which when executed by a processor, cause the processor to perform a method, the method comprising:
receiving content for at least a first chat room and a second chat room;
for each chat room, parsing the content associated with the first chat room and the second chat room into two or more instances;
for each instance, extracting two or more characteristics describing the instance;
determining if a user posted a message during a first instance;
if a user posted a message during the first instance, indicating user interest in the first instance;
based on the user interest in the first instance, creating a user profile comprising a plurality of characteristics of the two or more characteristics, wherein the user profile further comprises an associated weight for each of the plurality of characteristics;
determining that the first chat room is more applicable to the user than the first chat room; and
providing, based on determining that the first chat room is more applicable to the user than the second chat room, a user interface to the user where the first chat room is prioritized over the second chat room.

### Claim 12 (depends on 11)

The non-transitory computer readable medium of claim 11, further comprising:
at a later time, analyzing a first characteristic, associated with the first chat room and the second chat room, against the user profile.

### Claim 13 (depends on 11)

The non-transitory computer readable medium of claim 11, wherein the two or more instances are parsed based on a post event of the user.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, further comprising updating the machine learning model periodically based on new content in the two or more chat rooms.

### Claim 15 (depends on 14)

The non-transitory computer readable medium of claim 14, further comprising:
providing, on a user interface, a view of the user profile;
receiving an input associated with the user interface; and
based on the input, eliminating one of the plurality of characteristics.

### Claim 16

A system comprising:
a display that provides a user interface;
a memory storage;
a processing unit coupled to the memory storage and the display, wherein the processing unit is operative to:
provide, on the user interface, a prioritization of a first chat room over a second chat room, wherein the prioritization is based on a contemporaneous comparison of a characteristic, associated with the first chat room, to a user profile comprising a plurality of characteristics and an associated weight assigned to each of the plurality of characteristics, wherein the processing unit being operative to provide the prioritization of the first chat room over the second chat room comprises the processing unit being operative to:
determine a score for each of the first chat room and the second chat room on the characteristic associated with the first chat room and the second chat room and the plurality of characteristics and the associated weight assigned to each of the plurality of characteristics for the user profile, and
determine that the first room is more applicable to the user over the second chat room based on the score;
receiving an input associated with the user interface to select the first chat room; and
based on the input, providing content from the first chat room.

### Claim 17 (depends on 16)

The system of claim 16, wherein the processing unit is further configured to:
provide, on the user interface, a view of the user profile;
receiving an input associated with the user interface; and
based on the input, eliminating one of the plurality of characteristics.

### Claim 18 (depends on 17)

The system of claim 17, wherein the characteristic is one of a mention of the user, a frequency of recent posts, a uploaded file, a number of participants, an amount of time between posts, a relationship between the user and a poster, and/or a presence of a keyword.

### Claim 19 (depends on 17)

The system of claim 17, wherein the input is received into a user-selectable device.

### Claim 20 (depends on 19)

The system of claim 19, wherein the input is sent from the system to a chat room service to change the user profile.

### Claim 21 (depends on 19)

The system of claim 19, wherein the processing unit is further operative to:
wait a period of time; and
after the period of time, reanalyze the characteristic.

### Claim 22 (depends on 16)

The system of claim 16, wherein the associated weight is determined based on statistical analysis of historical data associated with the first chat room and the second chat room.
