Generating multi-language social network user profiles by translation

US9747281B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9747281-B2
Application numberUS-201514961266-A
CountryUS
Kind codeB2
Filing dateDec 7, 2015
Priority dateDec 7, 2015
Publication dateAug 29, 2017
Grant dateAug 29, 2017

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.

Techniques are provided to allow users of a social network to have multilingual profiles (or profiles in second languages that are different than the users' native, or original, profile languages). In one technique, a translation model is applied to one or more data items (in a first language) in a user's profile to generate translated data items in a second language. The translated data items are displayed to the user (or an online social “friend” of the user) and the user is allowed to select one of the translated data items to include in the user's “second language” profile. The selection may then be used to improve the translation model.

First claim

Opening claim text (preview).

What is claimed is: 1. A method comprising: storing a plurality of profiles, wherein each profile of the plurality of profiles comprises multiple data items about a different user of a plurality of users; identifying a first profile of a first user in the plurality of users, wherein the first profile is in the plurality of profiles, is in a first language, and comprises a plurality of data items about the first user; translating a first data item in the plurality of data items into a plurality of translated data items that are in a second language that is different than the first language; for each translated data item in the plurality of translated data items, determining how often said each translated data item appears with the first data item in the plurality of profiles; selecting, based on a number of user profiles that contain at least one of plurality of translated data items and the first data item, a first translated data item from among the plurality of translated data items; storing the first translated first data item in a second language profile of the first user; causing the second language profile to be displayed to a second user that is different than the first user; wherein the method is performed by one or more computing devices. 2. The method of claim 1 , wherein: translating the first data item comprises translating each data item in the plurality of data items into a different translated data item of a translated plurality of data items that are in the second language; causing the second language profile to be displayed comprises causing the plurality of translated data items to be displayed concurrently. 3. The method of claim 1 , further comprising, prior to causing the second language profile to be displayed to the second user: receiving, from the computing device associated with the first user, a request to view the first profile; after receiving the request, causing the first profile and the first translated data item to be displayed to the first user. 4. The method of claim 3 , further comprising, prior to causing the second language profile to be displayed to the second user: receiving, from the computing device associated with the first user, first input that indicates whether to retain the first translated data item as a data item in the second language profile. 5. The method of claim 1 , wherein: the plurality of profiles includes a second profile that is different than the first profile, the second profile is about a third user in the plurality of users, the second profile includes a second plurality of data items that includes a particular data item, the second plurality of data items are in the first language; the method further comprising: translating the particular data item into a second plurality of translated data items that includes a particular translated data item and a second translated data item that is different than the particular translated data item; causing the second plurality of translated data items to be displayed concurrently; receiving first input that selects the particular translated data item from among the second plurality of translated data items; in response to receiving the first input, including the particular translated data item in a second language profile for the third user. 6. The method of claim 5 , wherein causing the second plurality of translated data items to be displayed concurrently comprises: for the particular translated data item, causing an identification of a first source of the particular translated data item to be displayed; for the second translated data item, causing an identification of a second source of the second translated data item to be displayed, wherein the first source is different than the second source. 7. The method of claim 5 , further comprising: for each translated data item in the second plurality of translated data items, generating a confidence score; determining an order of the second plurality of translated data items based on confidence scores associated with the second plurality of translated data items; wherein causing the second plurality of translated data items to be displayed concurrently comprises causing the second plurality of translated data items to be displayed according to the order. 8. The method of claim 5 , further comprising: receiving second input that classifies a translated data item in the second plurality of translated data items as a type of translation that is incorrect; updating a machine translation model or a classifier based on the second input. 9. The method of claim 1 , wherein the first data item and the first translated data item correspond to a job title of the first user, a name of an employer of the first user, a headline of the first user, a skill of the first user, a work summary of the first user, or an interest or hobby of the first user. 10. The method of claim 1 , wherein the first user provided particular input that specified each data item in the plurality of data items. 11. The method of claim 1 , wherein: the plurality of profiles includes a second profile that is different than the first profile, the second profile is about a third user in the plurality of users, the second profile includes a second plurality of data items that includes a first particular data item, the second plurality of data items are in the first language, the method further comprising: receiving, from a fourth user that is connected to the third user in a social network, first input that indicates a particular translated data item that corresponds to the first particular data item and that is in a third language that is different than the first language; after receiving the first input, causing the first particular translated data item to be displayed to the third user; receiving, from the third user, second input that accepts the first particular translated data item; in response to receiving the second input, storing the first particular translated data item in a particular language profile that is in the third language. 12. The method of claim 11 , further comprising, prior to receiving the first input: using a machine translation model to determine the first particular translated data item; causing the first particular translated data item to be displayed to the fourth user; wherein the first input is a selection, by the fourth user, of the first particular translated data item. 13. The method of claim 11 , wherein the fourth user specifies the first particular translated data item through text input or voice input. 14. The method of claim 11 , further comprising, prior to receiving the first input: determining, based on one or more criteria, the fourth user from among a plurality of users who are connected to the third user in the social network; causing, to be displayed to the fourth user, a message that indicates that the third user has a profile that can be translated based on input from the fourth user. 15. The method of claim 11 , further comprising, prior to receiving the first input: receiving third input that the third user specifies and that indicates the fourth user; in response to receiving the third input, causing, to be displayed to the fourth user, a message that indicates that the third user has a profile that can be translated based on input from the fourth user. 16. The method of claim 1 , wherein the plurality of profiles includes a second profile that is different than the first profile, is about a third user in the plurality of users, and includes a second plurality of data item

Assignees

Inventors

Classifications

  • G06Q10/40Primary

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

  • Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

  • G06F40/42Primary

    Data-driven translation · CPC title

  • Physics · mapped topic

  • Physics · mapped topic

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 US9747281B2 cover?
Techniques are provided to allow users of a social network to have multilingual profiles (or profiles in second languages that are different than the users' native, or original, profile languages). In one technique, a translation model is applied to one or more data items (in a first language) in a user's profile to generate translated data items in a second language. The translated data items …
Who is the assignee on this patent?
Linkedin Corp
What technology area does this patent fall under?
Primary CPC classification G06Q10/40. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Aug 29 2017 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 3 related publications on this page (citations in our corpus or others sharing the same primary CPC).