# US 2018/0322211 A1 · Prioritizing Items From Different Categories In A News Stream > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0322211 A1 - Document ID: US20180322211A1 - Status: Published application - Kind: A1 - Application number: 16/038,134 - Filed: 2018-07-17 - Published: 2018-11-08 - Earliest claimed: 2013-08-28 - Assignees: Oath Inc. - Applicants: Oath Inc. - Inventors: Xing Yi; Scott Gaffney - Web page: https://patentgrep.com/patent/US20180322211A1 ## CPC - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 16/30: of unstructured textual data (document management systems G06F16/93) - G06F 16/353: into predefined classes - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods, systems, and computer programs are presented for displaying a customized news stream. One method includes an operation for identifying dwell times spent by users while accessing a first plurality of items, each item belonging to one media type from a plurality of media types (e.g., news articles, videos, slide shows, etc.). In addition, the method includes operations for determining statistical parameters for each media type based on the identified dwell times, and for detecting a news corpus having a second plurality of items. A priority for each item in the news corpus is determined based on the media type of the item, the corresponding statistical parameters for the media type of the item, and the profile of a user. The news stream is sent to the user for presentation on a display, the news stream being sorted based on the priority of the items in the news corpus. ## Claims ### Claim 1 A method for sending a customized news stream to be displayed on a user device, the method comprising: identifying, by one or more servers, dwell times spent by a plurality of users while accessing a plurality of items, each item belonging to one media type from a plurality of media types, the plurality of media types having differing average dwell times; determining, by the one or more servers, a respective average dwell time for each media type; determining, at the one or more servers, a priority for each item of the plurality of items based on normalized dwell times of each item, the normalized dwell times of each item is a measurement of variance between the dwell time of the each item and the respective average dwell time of the media type of the each item; and sending, from the one or more servers, a news stream to the user device for presentation on a display associated with the user device, the news stream configured to be presented on the display associated with the user device in an order based on the priority of the items of the plurality of items, wherein the news stream includes items of two or more different media types, wherein operations of the method are executed by a processor. ### Claim 2 (depends on 1) The method of claim 1, wherein the normalized dwell times are a standardized measurement of the dwell times that enable comparison of engagement signals of items of different media types. ### Claim 3 (depends on 1) The method of claim 1, wherein a dwell time of an item is measured by identifying an average of the dwell times spent by the plurality of users while accessing the item. ### Claim 4 (depends on 3) The method of claim 3, wherein a normalized dwell time of the item is calculated based upon a quotient of a difference between the dwell time of the item and an average dwell time of items of a media type the item belongs to, and a standard deviation of dwell times for the media type. ### Claim 5 (depends on 1) The method as recited in claim 1, wherein determining the priority further includes: determining a first priority value for each item based on features within the item determined to be of interest to the user. ### Claim 6 (depends on 1) The method as recited in claim 1, wherein determining the priority further includes: determining a media-type priority value based on the media type of the item and the corresponding statistical parameters for the media type of the item; and determining the priority for the each item based on the media-type priority value of the each item. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein determining the priority further includes: determining a third priority value based on a popularity score of the item. ### Claim 8 (depends on 1) The method as recited in claim 1, wherein the dwell time of an item is based on an amount of time the item is displayed to a user. ### Claim 9 A non-transitory computer-readable storage medium storing a computer program for sending a customized news stream to be displayed on a user device, the computer-readable storage medium comprising: program instructions for identifying, by one or more servers, dwell times spent by a plurality of users while accessing a plurality of items, each item belonging to one media type from a plurality of media types, the plurality of media types having differing average dwell times; program instructions for determining, by the one or more servers, a respective average dwell time for each media type; program instructions for determining, at the one or more servers, a priority for each item of the plurality of items based on normalized dwell times of each item, the normalized dwell times of each item is a measurement of variance between the dwell time of the each item and the respective average dwell time of the media type of the each item; and program instructions for sending, from the one or more servers, a news stream to the user device for presentation on a display associated with the user device, the news stream being configured to be presented on the display associated with the user device in an order based on the priority of the items of the plurality of items, wherein the news stream includes items of two or more different media types. ### Claim 10 (depends on 9) The computer-readable storage medium as recited in claim 9, wherein the normalized dwell times are a standardized measurement of dwell times that enable comparison of engagement signals of items from different media types having differing average dwell times. ### Claim 11 (depends on 9) The computer-readable storage medium as recited in claim 9, wherein a dwell time of an item is measured by identifying an average of dwell times spent by the plurality of users while accessing the item. ### Claim 12 (depends on 11) The computer-readable storage medium as recited in claim 11, wherein a normalized dwell time of the item is calculated based upon a quotient of a difference between the dwell time of the item and an average dwell time for items of a media type the item belongs to, and a standard deviation of dwell times for the media type. ### Claim 13 (depends on 9) The computer-readable storage medium as recited in claim 9, wherein determining the priority further includes: determining a first priority value for each item based on features within the item determined to be of interest to the user. ### Claim 14 (depends on 9) The computer-readable storage medium as recited in claim 9, wherein determining the priority further includes: determining a media-type priority value based on the media type of the item and the corresponding statistical parameters for the media type of the item; and determining the priority for the each item based on the media-type priority value of the each item and the profile of the user. ### Claim 15 (depends on 9) The computer-readable storage medium as recited in claim 9, wherein determining the priority further includes: determining a third priority value based on a popularity score of the item. ### Claim 16 A method for displaying a customized news stream, the method comprising: identifying, by one or more servers, dwell times spent by a plurality of users while accessing a plurality of items, each item belonging to one media type from a plurality of media types, wherein the plurality of media types includes types selected from a group consisting of news articles, videos, photographs, short messages, slideshows, or blogs, the plurality of media types having differing average dwell times; for each media type, determining, by the one or more servers, a respective average dwell time for each media type; determining, at the one or more servers, a first priority for each item in the plurality of news items based on a normalized dwell time of each item, the normalized dwell time is a measurement of variance between the dwell time of the each item and the respective average dwell time of the media type of the each item; and determining, at the one or more servers, a second priority for each item in the plurality of news items based on the first priority and a profile of a user; and sending, from the one or more servers, a news stream to the user for presentation on a display associated with the user device, the news stream being configured to be presented on the display in an order based on the second priority of the items in the plurality of news items, wherein operations of the method are executed by a processor. ### Claim 17 (depends on 16) The method of claim 16, wherein the normalized dwell times are a standardized measurement of the dwell times that enable comparison of engagement signals of items of different media types. ### Claim 18 (depends on 16) The method of claim 16, wherein a dwell time of an item is measured by identifying an average of the dwell times spent by the plurality of users while accessing the item and wherein a normalized dwell time of the item is calculated based upon a quotient of a difference between the dwell time of the time of the item and the an average dwell time for items of a media type the item belongs to, and a standard deviation of dwell times for the media type. ### Claim 19 (depends on 16) The method as recited in claim 16, wherein the dwell time of an item is based on an amount of time that the item is displayed to a user. ### Claim 20 (depends on 16) The method as recited in claim 16, wherein the profile includes features of interest for the user based on items viewed by the user.