Automated social message stream population

US9996575B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9996575-B2
Application numberUS-201514621203-A
CountryUS
Kind codeB2
Filing dateFeb 12, 2015
Priority dateOct 30, 2014
Publication dateJun 12, 2018
Grant dateJun 12, 2018

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A messaging system automatically populates a stream of messages using only a seed selected by the requesting account holder. In one embodiment, the seed includes the streams of one or more of the “top” accounts of the messaging system. Here, “top” is according to any one of a number of different metrics stored in the messaging system. With knowledge of the seed, the messaging system automatically populates a stream for the requesting account holder, without requiring any other input. As a result, an account holder is provided with a fully functioning stream with very little effort or knowledge required on their part.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-executed method comprising: providing, by a computer server, a list of a set of accounts of a messaging system to a client device, the set of accounts determined according to a metric; receiving, at the computer server from a client operating the client device, a request for a stream of messages, the request comprising a seed specifying at least one of the set of accounts, computing a vector matrix representing a measure of relevance between each account of the set of accounts; storing the vector matrix in a first database; determining a relevance of the seed to each account of the set of accounts using the vectors stored in the vector matrix and the seed; selecting a subset of accounts of the set of accounts based on the determined relevances; storing the subset of accounts in a second database distinct from the first database; accessing a plurality of messages authored by the stored subset of accounts; ranking the plurality of messages to determine messages to include in the message stream based on a relevance of the messages to the client and, providing the stream to the client device by the computer server. 2. The computer-executed method of claim 1 wherein the messaging system hosts messages authored by the accounts, the messages visible to other accounts. 3. The computer-executed method of claim 1 further comprising: ranking a plurality of accounts of the messaging system according to a metric; and selecting the list of the set of accounts based on the rank. 4. The computer-executed method of claim 3 wherein the metric is a number of other accounts of the plurality of accounts of the messaging system that have formed unidirectional connections to the account being ranked. 5. The computer-executed method of claim 1 wherein the seed comprises a plurality of the accounts of the set of accounts. 6. The computer-executed method of claim 1 wherein determining the relevance of the seed to each of the set of accounts comprises: generating a seed vector based on the seed and the vector matrix; and for each account in the set of accounts: combining the seed vector and a feature vector for the account from the vector matrix to determine the relevance of the seed to the account. 7. The computer-executed method of claim 1 wherein computing the vector matrix further comprises: performing singular value decomposition to generate at least two matrices: a diagonal matrix S comprising A×A dimensions, and a follow matrix V comprising A×Y dimensions where Y is a number of accounts of the messaging system in the list of the set of accounts; and combining the S and the V matrices to generate the vector matrix. 8. The computer-executed method of claim 1 wherein ranking one of the messages comprises: determining a likelihood of engagement with the message based on engagement data stored by the messaging system, the engagement data comprising previous engagements by accounts of the messaging system with the message; and ranking the message based on the likelihood of engagement. 9. The computer-executed method of claim 1 wherein ranking one of the messages comprises: determining a time decay value based on an amount of time that has elapsed since the message was authored; and ranking the message based on the time decay value. 10. The method of claim 1 wherein the first database is a high-density file system database and the second database is a fast access database. 11. A messaging system comprising: a plurality of messaging databases associated with a plurality of messaging server instances, the messaging databases configured to store: a plurality of accounts of the messaging system; a plurality of messages authored by accounts of the messaging system; a plurality of connections between the accounts of the messaging system; a ranking computer server communicatively coupled to the plurality of databases, the ranking computer server configured to: providing a set of accounts of the plurality of accounts of the messaging system to a client device, the set of accounts being determined according to a metric; receive a request for a stream of messages from a front end server, the request comprising a seed specifying at least one of the set of accounts; compute a vector matrix representing a measure of relevance between each account of the set of accounts; store the vector matrix in a first database; determine a relevance of the seed to each account of the set of accounts using the vectors stored in the vector matrix and the seed; select a subset of accounts of the set of accounts based on the determined relevances; store the subset of accounts in a second database distinct from the first database; access a plurality of messages authored by the stored subset of accounts; provide at least one of the messages to the front end server to send to the client device. 12. The messaging system of claim 11 , wherein to provide at least one of the messages to the client device, the ranking computer server is configured to: rank the plurality of messages authored by the stored subset of accounts to determine messages to include in a message stream based on a relevance of the messages to the client; provide the message stream to the front end server to send to the client device. 13. The messaging system of claim 11 wherein the messaging server instances are physically located at two geographically dissimilar locations. 14. The messaging system of claim 11 wherein to determine the top accounts of a messaging system according to a metric, the ranking computer server is further configured to: rank the plurality of accounts of the messaging system according to a metric; and select the list of the set of accounts based on the rank. 15. The messaging system of claim 14 wherein the metric is a number of other accounts of the plurality of accounts of the messaging system that have formed unidirectional connections to the account being ranked. 16. The messaging system of claim 11 wherein the seed comprises a plurality of the accounts of the set of accounts. 17. The messaging system of claim 11 wherein to compute the vector matrix the ranking computer server is configured to: perform singular value decomposition to generate at least two matrices; a diagonal matrix S comprising A×A dimensions, and a follow matrix V comprising A×Y dimensions where Y is a number of accounts of the messaging system in the list of the set of accounts; and combine the S and the V matrices to generate the vector matrix. 18. The messaging system of claim 11 wherein the messaging databases store engagement data, and wherein to rank one of the messages, the ranking computer server is further configured to: access the engagement data stored in the messaging databases; determine a likelihood of engagement with the message based on engagement data stored by the messaging system, the engagement data comprising previous engagements by accounts of the messaging system with the message; and rank the message based on the likelihood of engagement. 19. The messaging system of claim 11 wherein ranking one of the messages comprises: determining a time decay value based on an amount of time that has elapsed since the message was authored; and ranking the message based on the time decay value. 20. The messaging system of claim 11 wherein the ranking computer server is further configured to: receive a second request for a second stream of messages from the front end s

Assignees

Inventors

Classifications

  • using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

  • Office automation; Time management · CPC title

  • Interaction with lists of selectable items, e.g. menus · CPC title

  • Business processes related to social networking or social networking services · CPC title

  • Updating · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9996575B2 cover?
A messaging system automatically populates a stream of messages using only a seed selected by the requesting account holder. In one embodiment, the seed includes the streams of one or more of the “top” accounts of the messaging system. Here, “top” is according to any one of a number of different metrics stored in the messaging system. With knowledge of the seed, the messaging system automatical…
Who is the assignee on this patent?
Twitter Inc
What technology area does this patent fall under?
Primary CPC classification H04L51/52. Mapped technology areas include Electricity.
When was this patent published?
Publication date Tue Jun 12 2018 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).