# US 2016/0255037 A1 · System and method for personalization of message streams via machine learning

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

- Number: US 2016/0255037 A1
- Document ID: US20160255037A1
- Status: Published application
- Kind: A1
- Application number: 15/143,028
- Filed: 2016-04-29
- Published: 2016-09-01
- Earliest claimed: 2012-02-23
- Assignees: Bottlenose, Inc.
- Applicants: Bottlenose, Inc.
- Inventors: Nova Spivack; Dominiek ter Heide
- Web page: https://patentgrep.com/patent/US20160255037A1

## CPC

- G06N 20/00: Machine learning
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06N 5/04: Inference or reasoning models
- G06N 5/046: Forward inferencing; Production systems
- G06Q 10/10: Office automation; Time management
- G06Q 10/42: Determination of affinities or common interests between users
- G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics
- G06Q 10/46: Determination of level of influence of users within social networking services
- H04L 43/16: Threshold monitoring
- H04L 51/212: using filtering or selective blocking
- H04L 51/52: for supporting social networking services
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L 67/306: User profiles
- H04L 67/53: using third party service providers
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods for analyzing messages in a network or across networks are disclosed. In one aspect, embodiments of the present disclosure include a system for processing incoming messages from multiple web-based services. The system can include, a processing unit, a memory unit having stored thereon instructions which when executed by the processing unit causes the processing unit to perform a method which can, perform an action on an incoming message in accordance with a rule set to process the incoming messages. The rule set can be determined as a result of machine learning. in one embodiment, the action is performed by an independent service, the independent service being independent from the multiple web-based services.

## Claims

### Claim 1

A system for processing incoming messages from multiple web-based services, the system, comprising:
a processing unit;
a memory unit having stored thereon instructions which when executed by processing unit, cause the processing unit to:
perform an action on an incoming message in accordance with a rule set to process the incoming messages;
wherein the rule set is determined as a result of machine learning;
wherein the action is performed by an independent service, the independent service being independent from the multiple web-based services.

### Claim 2 (depends on 1)

The system of claim 1, wherein, the action includes generating a personalized data stream for a user in accordance with the rule set to filter and prioritize incoming messages for the user.

### Claim 3 (depends on 2)

The system of claim 2, wherein, the personalized data stream includes a likestream comprised of messages implicitly or explicitly liked by the user as defined by the rule set.

### Claim 4 (depends on 3)

The system of claim 3, wherein, the action performed on likestream includes: categorizing the messages contained therein by message type; visually presenting the messages in the likestream by category to the user in a user interface provided by the independent service.

### Claim 5 (depends on 3)

The system of claim 3, wherein, the messages in the likestream are visually presented in user interface of the independent service in chronological order or based on degree to which they are liked.

### Claim 6 (depends on 3)

The system of claim 3, wherein, other users are able to subscribe to the likestream of the user.

### Claim 7 (depends on 1)

The system of claim 1, wherein the rule set is specified by the user, via a user interface provided by the service which is independent of the multiple web-based services.

### Claim 8 (depends on 1)

The system of claim 1, wherein the result of machine learning includes machine learning from observance of user behavior and tracking user preferences.

### Claim 9 (depends on 1)

The system of claim 1, wherein, the rule set includes, type of interaction with a message, including one or more of, posted, replied to, reposted, received, liked, disliked, annotated, read, saved, favorited, and tagged.

### Claim 10 (depends on 1)

The system of claim 1, wherein, the rule set includes, people parameters of people who interacted with a message, including, specific people, connected people, followed people, following people, people who follow specified other people, people with a certain social influence level, geographical parameters of the people, membership or group affiliation.

### Claim 11 (depends on 10)

The system of claim 10, wherein, the people parameters further include, screen name of an author, author follower count, author following count, author average messages per day.

### Claim 12 (depends on 1)

The system of claim 1, wherein, the rule set includes, message parameters including, one or more of message type, topics of a message, words in a message, message importance, relevance of message source, repost score, popularity, influence of author.

### Claim 13 (depends on 1)

The system of claim 1, wherein, the rule set further includes, number of reposts.

### Claim 14 (depends on 1)

The system of claim 1, wherein, the rule set includes, timing or geographical parameters of a message.

### Claim 15 (depends on 1)

The system of claim 1, wherein the action is specified by the user, via a user interface provided by the service which is independent of the multiple web-based services.

### Claim 16 (depends on 1)

The system of claim 1, wherein the action is determined using the result of machine learning.

### Claim 17 (depends on 1)

The system of claim 1, wherein, the action includes adjusting a user interface experience of the incoming message including one or more of adjusting visibility or audibility of the message.

### Claim 18 (depends on 1)

The system of claim 1, wherein, the action includes one or more of, annotate or tag the message, repost the message, delete the message, hide the message, file the message, reply to the message.

### Claim 19 (depends on 1)

The system of claim 1, wherein, the action includes one or more of save the message, add the message to my interests, add the author of the message to my interests, share the message.

### Claim 20 (depends on 1)

The system of claim 1, wherein, the action includes, one or more of, launch a plug-in or another application, call a function, send the message to another application, export the message as data or export the message into another format, view the message in a specific viewer.

### Claim 21 (depends on 1)

The system of claim 1, wherein, the action includes one or more of, translate the message, change the personalization score of the message.

### Claim 22 (depends on 1)

The system of claim 1, wherein, instructions which when executed by the processing unit, further cause the processing unit to:
identify the interests of the user from online activity or online relationships of the user;
increase visibility of those incoming messages which are more interesting to the user among other incoming messages in the personalized data stream for presentation, in a user interface provided by the independent service.

### Claim 23 (depends on 1)

The system of claim 1, wherein, the online activity of the user is automatically detected from those activities of the user on or via the multiple web-based services.

### Claim 24 (depends on 1)

The system of claim 1, wherein, the online activity of the user is automatically detected from those activities of the user with online content.

### Claim 25 (depends on 1)

The system of claim 1, wherein, the online activity of the user is automatically detected from interactions or relationships of the user with other users in any of the multiple web-based services.

### Claim 26 (depends on 1)

The system of claim 1, wherein, the user interface is a part of a platform which is independent of any of the web-based services.

### Claim 27 (depends on 1)

The system of claim 1, wherein, the rule set includes, tags in a message, and/or labels in a message.

### Claim 28 (depends on 1)

The system of claim 1, wherein, the rule set includes, level of interest of message to the user.
