Matching video content with podcast episodes

Abstract

A system and method are provided for matching videos and podcast episodes. A data store comprising podcast episode identifiers is accessed. The podcast episode identifiers are associated with one or more podcast episode attributes. A video content item is identified. The video content item includes one or more video content item attributes. A matching podcast episode identifier that matches the video content item is determined based on the one or more podcast episode attributes and the one or more video content item attributes. A ranking of one of the video content items or the matching podcast episode identifiers is adjusted to reflect a correspondence between the video content item and the matching podcast episode identifier. Information associated with the matching podcast episode identifier is provided to a first user device.

Description

[Technical Field]

[0001] Aspects and implementations of the present disclosure relate to matching video content with podcast episodes. [Background technology]

[0002] Various platforms allow users to listen to audio content, such as podcast episodes. For example, users may search for and find audio content using search engines or through content sharing platforms. Additionally, podcast publishers may use podcast manager platforms to track analytics information about their podcasts. The analytics information may include the number of times a podcast episode has been started, the average length of time users have listened to a particular podcast episode, and demographics about podcast listeners. Summary of the Invention [Means for solving the problem]

[0003] The following is a simplified summary of the disclosure to provide a basic understanding of some aspects of the disclosure. This summary is not an extensive overview of the disclosure. It is not intended to identify key or critical elements of the disclosure, nor is it intended to delineate the scope or claims of particular embodiments of the disclosure. Its sole purpose is to present some concepts of the disclosure in a simplified form as a prelude to the more detailed description that is presented later.

[0004] In some implementations, systems and methods for matching video content items and podcast episodes are disclosed to enhance content sharing platforms. In one implementation, a data store is accessed that includes one or more podcast episode identifiers and one or more video content item identifiers. The podcast episode identifiers of the one or more podcast episode identifiers can be associated with one or more podcast episode attributes, and the video content item identifiers of the one or more video content item identifiers can be associated with one or more video content item attributes. For matching podcast episode identifiers of the one or more podcast episode identifiers, a matching video content item identifier is determined based on the one or more podcast episode attributes associated with the matching podcast episode identifier. A ranking of at least one of the matching video content item identifiers or the matching podcast episode identifiers is adjusted to reflect a correspondence between the matching video content item identifiers and the matching podcast episode identifiers. Information associated with the matching podcast episode identifiers is provided to a first user device.

[0005] In some implementations, another system and method for matching video content items and podcast episodes is disclosed to enhance a search engine platform. In one implementation, a data store is accessed that includes one or more podcast episode identifiers and one or more video content item identifiers. The podcast episode identifiers of the one or more podcast episode identifiers can be associated with one or more podcast episode attributes, and the video content item identifiers of the one or more video content item identifiers can be associated with one or more video content item attributes. For matching podcast episode identifiers of the one or more podcast episode identifiers, a matching video content item identifier is determined based on the one or more podcast episode attributes associated with the matching podcast episode identifier. A ranking of at least one of the matching video content item identifiers or the matching podcast episode identifiers is adjusted to reflect a correspondence between the matching video content item identifiers and the matching podcast episode identifiers. Information associated with the matching podcast episode identifiers and the matching video content item identifiers is provided to a user device.

[0006] In some implementations, another system and method for matching video content items with podcast episodes is disclosed to enhance a podcast manager platform. In one implementation, a request for podcast analytics information for a podcast is received. The podcast can be associated with one or more podcast episodes. An identification of a source comprising one or more video content items is received. Further, one or more podcast episode attributes are identified for the one or more podcast episodes, and one or more video content item attributes are identified for the one or more video content items. A matching video content item is determined that matches a matching podcast episode of the one or more podcast episodes based on the one or more podcast episode attributes and the one or more video content item attributes. Analytics information associated with the matching video content item is determined. A response to the request is provided. The response includes the analytics information associated with the matching video content item and the podcast analytics information.

[0007] Aspects and implementations of the present disclosure will be more fully understood from the following detailed description and the accompanying drawings of various aspects and implementations of the present disclosure, which should not be construed as limiting the disclosure to any particular aspect or implementation, but are for purposes of illustration and understanding only. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an exemplary system architecture according to one implementation of the present disclosure. [Figure 2] FIG. 2 illustrates an example of a matching subsystem according to one implementation of the present disclosure. [Figure 3]1 illustrates an exemplary graphical user interface (GUI) on a client device, showing an exemplary podcast destination page on a content sharing platform, according to one implementation of the present disclosure. [Figure 4] 1 illustrates an exemplary GUI on a client device according to one implementation of the present disclosure, showing an example of a content sharing platform that includes both podcast episodes and video content items. [Figure 5] FIG. 1 illustrates an exemplary GUI of a content sharing platform optimized for audio content, according to one implementation of the present disclosure. [Figure 6] FIG. 1 illustrates an exemplary GUI of a content sharing platform enhanced for episodic content, according to one implementation of the present disclosure. [Figure 7] FIG. 1 illustrates an exemplary GUI of a lock screen of a user device showing media controls optimized for listening to audio content, according to one implementation of the present disclosure. [Figure 8] FIG. 1 illustrates an exemplary GUI of a search engine platform optimized in accordance with an aspect of the present disclosure. [Figure 9] FIG. 1 illustrates an exemplary GUI of a podcast manager platform optimized according to aspects of the present disclosure. [Figure 10] FIG. 1 illustrates an exemplary GUI of a podcast manager platform optimized according to aspects of the present disclosure. [Figure 11] 1 is a flow diagram of a method for enhancing a content sharing platform by matching video content items to podcast episodes, according to one implementation of the present disclosure. [Figure 12] 1 is a flow diagram of a method for enhancing a search engine platform by matching video content items to podcast episodes, according to one implementation of the present disclosure. [Figure 13]1 is a flow diagram of a method for enhancing a podcast manager platform by matching video content items to podcast episodes, according to one implementation of the present disclosure. [Figure 14] FIG. 1 is a block diagram of a computer system that operates in accordance with an implementation of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] These drawings may be better understood when viewed in conjunction with the following detailed description.

[0010] Aspects of the present disclosure relate to matching video content with podcast episodes. Podcast creators and / or publishers can publish podcast episodes in both audio and video formats. For example, a podcast publisher may publish an episode as an audio file through a podcast publishing service and a video of the episode through a video hosting service. The video may include a video recording of the podcast host recording the episode and / or may include slides or images related to the episode content.

[0011] In many cases, the content of the video differs from the content of the audio format of the podcast episode. For example, a video of a podcast episode may include a visual intro and outro, and the intro / outro of the audio format of the podcast episode may be optimized for listening (e.g., a video outro may include printed credits, while the audio outro may include spoken credits). In some cases, the breaks or summaries included in the audio and video formats may differ. For example, the audio version of a podcast episode may include breaks every set number of minutes (e.g., every 15 minutes) to accommodate the publisher's platform (e.g., a radio station) and may include a summary after the break. However, the video format of the podcast episode may exclude breaks and summaries or may include breaks and summaries at different time intervals. Furthermore, the video and audio formats may not be released on the same day. For example, a podcast episode may be released initially in audio format and only released as a video once the audio version has reached a certain number of plays.

[0012] Existing content sharing platforms, search engines, and / or podcast managers all operate independently, and when a user needs to find matching podcast episodes on these different platforms, they must switch between multiple applications. This switching consumes significant time and computing resources. Aspects and implementations of the present disclosure address the above and other deficiencies or problems by providing techniques for matching video content to podcast episodes across multiple platforms / systems (e.g., content sharing platforms, search engines, and / or podcast managers). Furthermore, aspects and implementations of the present disclosure provide tools that can combine performance metrics, analytical data, and information across multiple platforms / systems and that can cover both audio and video episode formats.

[0013] In some implementations, to match video content items to podcast episodes (and vice versa), a matching system operating according to aspects of the present disclosure may identify attributes associated with the video content items and attributes associated with the podcast episodes. Attributes may include audio transcripts of the video content items and / or podcast episodes, durations, titles, descriptions, and / or publication dates of the video content items and / or podcast episodes. Additional attributes not listed herein may be identified. The matching system may compare attributes to generate a matching score for each episode-video pair. The episode-video pair with the highest matching score may be determined to be a match.

[0014] Based on the matching, a platform optimization system operating according to aspects of the present disclosure may improve the experience of podcast publishers by providing comprehensive analytical information including data from both the audio and video formats of the episodes. The platform optimization system may also improve the experience of users of search engine platforms and / or users of content sharing platforms by providing search results that include both the audio and video formats of the episodes, including optimized versions for each format. Furthermore, rankings used to generate search results in either the search engine platform or the content sharing platform may be enhanced based on matching content items with podcast episodes.

[0015] More specifically, by matching the video format of a podcast episode with the audio format of the podcast episode, a podcast analytics provider can provide analytics information associated with both the video and audio formats, rather than just the audio format. For example, a podcast analytics provider can display combined data regarding the overall play counts of an episode across both audio and video, thus providing a more complete picture to podcast publishers. Furthermore, by matching the video format of a podcast episode with the audio format of a podcast episode, search engines can enhance their ranking signals by combining performance metrics for each format, such as play counts. Furthermore, search engine ranking signals are enhanced by combining information associated with both the audio and video formats. For example, a video of a podcast episode may not include host information, while the audio format of the same podcast episode may include host information. By determining that the two match, the combined information can adjust the ranking of both formats. Search engines can be further enhanced by presenting search results that combine audio and video items, rather than displaying separate experiences for audio and video formats.

[0016] Additionally, content sharing platforms can benefit from matching the video format of a podcast episode to the audio format. Similar to search engines, content sharing platforms can adjust the ranking of both formats by combining performance metrics for the video format with performance metrics for the audio format. They can also adjust the ranking by combining information from both formats (e.g., host information). Furthermore, the user experience of a content sharing platform can be enhanced by providing a “listen-only” experience for viewers watching video content items that match podcast episodes. When a content sharing platform displays a video that matches a podcast episode, it can provide an optimized listen-only experience. The listen-only experience can include, but is not limited to, information about the matching podcast and / or host, previous / next episode controls, autoplay of another listen-only video when the video ends, the ability to subscribe to the podcast, and the ability to donate / contribute to the podcast publisher. Furthermore, when a video matches a podcast episode, the content sharing platform can enhance the advertising presented during the video. Rather than embedding generic video ads, the content sharing platform can provide ads designed to be listened to.

[0017] Aspects of the present disclosure provide several technical advantages, including, for example, a mechanism that allows matching of podcast episodes across different content sharing platforms, search engines, and / or podcast managers, thereby creating deeper integration between these platforms / systems and reducing the time and computing resources consumed by repetitive manual switching (e.g., switching between platforms / systems, applications, or interfaces) that would otherwise be performed by a user. Another technical advantage is improved and expanded functionality of search engine platforms, content sharing platforms, and podcast manager platforms. In particular, aspects of the present disclosure combine ranking signals associated with matched podcast episodes and video content items to provide improved search results. For example, combining performance metrics for a podcast episode with performance metrics for a matched video content item can provide more accurate ranking signals for both the podcast episode and the video content item. By providing more accurate ranking signals, the content sharing platform and / or search engine platform can provide more accurate results to users, thus avoiding wasting computing resources by providing less accurate search results. Additionally, the content sharing platform experience can be optimized to provide greater control related to the listening-only experience when a user is viewing a video that matches a podcast episode, thus improving the operation of the content sharing platform.

[0018] Various aspects of the above-referenced methods and systems are described in detail herein below by way of example and not limitation.

[0019] 1 illustrates an exemplary system architecture 100 according to one implementation of the present disclosure. System architecture 100 (also referred to herein as the “system”) includes end-user devices 102A-N, a data store 110, a content sharing platform 120, a search engine platform 130, a podcast manager platform 150, a server machine 140, and a third-party platform 165, each connected to a network 104.

[0020] In implementations, the network 104 may include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN) or a wide area network (WAN)), a wired network (e.g., an Ethernet network), a wireless network (e.g., an 802.11 network or a Wi-Fi network), a cellular network (e.g., a Long Term Evolution (LTE) network), a router, a hub, a switch, a server computer, and / or combinations thereof.

[0021] Each of the end user devices 102A-N may include a computing device such as a personal computer (PC), laptop, mobile phone, smartphone, tablet computer, netbook computer, network-connected television, etc. In some implementations, the end user devices 102A-N may also be referred to as a “user device” or a “client device.” Each end user device may include a content viewer. In some implementations, the content viewer may be an application that provides a user interface (UI) for a user to view or upload content such as images, video items, podcast episodes, web pages, documents, etc. For example, the content viewer may be a web browser through which content provided by a web server (e.g., web pages such as Hypertext Markup Language (HTML) pages, digital media items, etc.) can be accessed, retrieved, presented, and / or navigated. The content viewer may render, display, and / or present the content to the user. The content viewer may also include an embedded media player (e.g., a Flash player or an HTML5 player) embedded in a web page (e.g., a web page that may provide information about products sold by an online retailer). In another example, the content viewer may be a standalone application (e.g., a mobile application or app) that allows a user to view digital media items (e.g., digital video items, digital podcast episodes, digital images, e-books, etc.).

[0022] According to aspects of the present disclosure, the content viewer may be a content sharing platform application through which a user records, edits, and / or uploads content for sharing on the content sharing platform 120. Thus, the content viewer may be provided to the end user devices 102A-N by the content sharing platform 120. For example, the content viewer may be an embedded media player embedded in a web page provided by the content sharing platform 120. The content viewer may be a search platform application through which a user searches for content using the search engine platform 130. Additionally or alternatively, the content viewer may be a podcast manager application that allows a user to manage podcasts on the podcast manager platform 150.

[0023] Media items 121 may be consumed over the Internet or through a mobile device application, such as a content viewer on end-user devices 102A-N. Requested media items 121 may be requested by a user of the content sharing platform 120 for presentation to the user. As used herein, “media,” “media item,” “online media item,” “digital media,” “digital media item,” “content,” and “content item” may include electronic files that can be executed or loaded using software, firmware, or hardware configured to present digital media items to an entity. In one implementation, the content sharing platform 120 may use the data store 110 to store the media items 121. In another implementation, the content sharing platform 120 may use the data store 110 to store the media items 121 or fingerprints as electronic files in one or more formats. The media items 121 may be provided to a user, and providing the media items 121 may include granting access to the media items 121, transmitting the media items 121, and / or presenting or allowing the presentation of the media items 121.

[0024] In some implementations, a media item 121 may be a video item. A video item is a set of consecutive video frames (e.g., image frames) representing a moving scene. For example, a series of consecutive video frames may be continuously captured or later reconstructed to create an animation. A video item may be provided in a variety of formats, including, but not limited to, analog, digital, two-dimensional, and three-dimensional video. Furthermore, a video item may include a movie, a video clip, or any set of animated images displayed sequentially. Furthermore, a video item may be stored as a video file that includes a video component and an audio component. A video component may refer to video data in a video coding format or an image coding format (e.g., H.264 (MPEG-4 AVC), H.264 MPEG-4 Part 2, Graphic Interchange Format (GIF), WebP, etc.). An audio component may refer to audio data in an audio coding format (e.g., Advanced Audio Coding (AAC), MP3, etc.). Note that GIF may be stored as an image file (e.g., a .gif file) or as a series of images in an animated GIF (e.g., GIF89a format). Note that H.264 may be, for example, a video coding format that is a block-oriented, motion compensation-based video compression standard for recording, compressing, or distributing video content.

[0025] In some implementations, a media item 121 may be an audio file, such as a podcast episode. A media item 121 that is a video item may be a video version of a podcast episode. For example, the video version of a podcast episode may be a video of a host creating the podcast episode, or an image or series of images related to the topic of the podcast episode combined with the audio of the podcast episode.

[0026] In some implementations, data store 110 is persistent storage capable of storing media items 121 as well as data structures for tagging, organizing, and indexing media items 121. Data store 110 may be hosted by one or more storage devices, such as main memory, magnetic or optical storage-based disks, tapes or hard drives, NAS, SAN, etc. In some implementations, data store 110 may be a network-attached file server, while in other implementations, data store 110 may be some other type of persistent storage, such as an object-oriented database, a relational database, etc., that may be hosted by content sharing platform 120 or one or more different machines coupled to server content sharing platform 120 via network 104.

[0027] In one implementation, the content sharing platform 120, the search engine platform 130, the podcast manager platform 150, or the server machine 140 may be one or more computing devices (such as a rack-mounted server, a router computer, a server computer, a personal computer, a mainframe computer, a laptop computer, a tablet computer, a desktop computer, etc.), data stores (e.g., hard disks, memory, databases), networks, software components, and / or hardware components that may be used to provide users with access to media items 121 and / or to provide media items 121 to users. For example, the content sharing platform 120 may enable users to consume, upload, search, approve ("like"), disapprove ("dislike"), or comment on media items 121. The content sharing platform 120 may also include websites (e.g., web pages) or application backend software that may be used to provide users with access to media items 121. As another example, the search engine platform 130 may enable users to perform internet searches, which may include searching for media items 121. Search engine platform 130 may include websites (e.g., web pages) or application backend software that may be used to provide users with access to the internet, including media items 121. As another example, podcast manager platform 150 may provide podcast analytics information to users. For example, users may be podcast publishers. Podcast manager platform 150 may allow podcast publishers to view a list of published podcasts and episodes, and may include performance data for each podcast episode (e.g., number of plays, play date, average play time, etc.), as well as listener demographic information.

[0028] In some implementations, content sharing platform 120, search engine platform 130, and / or podcast manager platform 150 may each be combined into a single platform. In some implementations, server machine 140 or any of its components (e.g., podcast episode fetcher 144, video content item fetcher 143, and / or matching subsystem 142) may be combined with platforms 120, 130, 150. Each platform 120, 130, 150 may include a platform optimizer 170A-C. Platform optimizers 170A-C may use results from matching subsystem 142 to optimize platform operation.

[0029] In implementations of the present disclosure, a "user" may be represented as a single individual. However, other implementations of the present disclosure encompass a "user" that is a set of users and / or an entity controlled by an automated source. For example, a set of individual users federated as a community in a social network may be considered a "user." In another example, an automated consumer may be an automated ingestion pipeline, such as a topic channel of the content sharing platform 120.

[0030] The content sharing platform 120 may include multiple channels (e.g., channels A through X). A channel may include one or more media items 121 available from a common source or having a common topic, theme, or content. The media items 121 may be digital content selected by a user, made available by a user, uploaded by a user, selected by a content provider, selected by a broadcaster, etc. A channel may be associated with an owner, who is a user who can perform actions on the channel. Various activities may be associated with a channel based on the owner's actions, such as the owner making digital content available on the channel, the owner selecting (e.g., "liking") digital content to be associated with another channel, or the owner commenting on digital content associated with another channel. The activities associated with a channel may be collected in the channel's activity feed. Users other than the channel owner may subscribe to one or more channels of interest. The concept of "subscribing" may also be referred to as "liking," "following," "becoming a friend," etc.

[0031] The third-party platform 165 may be used to provide video and / or audio advertisements. Alternatively, the third-party platform 165 may provide other services. For example, the third-party platform 165 may be a video streaming service provider that generates a media streaming service via a communication application for users to play videos, television programs, video clips, audio, audio clips, and movies on end-user devices 102A-N via the third-party platform 165. In some implementations, a content provider may upload or provide (e.g., via the third-party platform 165) media items 121 to the content sharing platform 120 for presentation to one or more users.

[0032] In some implementations, the server machine 140 may include a podcast episode fetcher 144, a video content item fetcher 143, and a matching subsystem 142. In some implementations, the podcast episode fetcher 144 may identify podcast episodes uploaded to the web. For example, the podcast episode fetcher 144 may have a web crawler that crawls the Internet in a systematic and automated manner to find podcast episodes. In some implementations, the podcast episode fetcher 144 may identify podcast episodes uploaded via the content sharing platform 120 and / or the podcast manager platform 150. Upon finding and / or identifying a podcast episode, the podcast episode fetcher 144 may store a podcast episode identifier in the data store 110. The podcast episode identifier may be a URL of the podcast episode and / or an identifier that links to a URL of the podcast episode. In some implementations, the podcast episode fetcher 144 may further extract certain metadata from the identified podcast episode and store the extracted metadata as attributes in the data store 110.

[0033] The video content item fetcher 143 can function similarly. That is, the video content item fetcher 143 can have a web crawler that crawls the Internet in a systematic and automated manner to find video content items. In some implementations, the video content item fetcher 143 can identify video content items uploaded via the content sharing platform 120 and / or the podcast manager platform 150. Upon finding and / or identifying a video content item, the video content item fetcher 143 can store a video content item identifier in the data store 110. The video content item identifier can be a URL for the video content item and / or an identifier that links to a URL for the video content item. In some implementations, the video content item fetcher 143 can extract metadata from the identified video content item and store the extracted metadata as attributes in the data store 110.

[0034] The matching subsystem 142 can identify matching video content items and podcast episodes. In some implementations, the matching subsystem 142 can use extracted metadata and / or other information about the podcast episode identifiers and video content item identifiers stored in the data store 110 to match the podcast episodes with the video content items. The matching subsystem 142 can store the matched podcast episode identifiers and matched video content item identifiers in the data store 110. The matching subsystem 142 and the data store 110 are further described with respect to FIG. 2.

[0035] In some implementations, the matching subsystem 142 is a machine learning module trained to assign matching scores to pairs of podcast episode identifiers and video content item identifiers based on the attributes of each media item. In some implementations, the machine learning model can be trained using a labeled set of input training data. The set of input training data can include a subset of podcast episode identifiers associated with episode attributes (e.g., audio, transcript, duration, publication date, title, description, etc.) paired with matching video content item identifiers associated with the video content item attributes (e.g., audio, transcript, duration, publication date, title, description, etc.). The set of input training data can also include a subset of podcast episode identifiers associated with episode attributes paired with non-matching video content item identifiers associated with the video content item attributes. Using the input training data for training, the supervised machine learning model can be trained to provide a high score when a video content item matches a podcast episode and a low score when a video content item does not match a podcast episode.

[0036] In some implementations, the platform optimizer 170A-C can use the results of the matching system 142 to optimize the platform. In some implementations, the platform optimizer 170A can be used to optimize the content sharing platform 120 and / or to improve the user experience of the content sharing platform 120. In some implementations, to optimize the content sharing platform 120, the platform optimizer 170A can adjust the rankings of the matched video content item identifiers and / or the matched podcast episode identifiers to reflect the correspondence between the matched video content item identifiers and the matched podcast episode identifiers. That is, the content sharing platform 120 can rank the video content items and / or podcast episodes based on certain metrics. These metrics can include popularity indicators, such as, for example, the number of recommendations made for the video content item and / or podcast episode, the number of likes for the video content item and / or podcast episode, the number of views for the video content item and / or podcast episode, the number of shares for the video content item and / or podcast episode, etc. In some implementations, the video content items and / or podcast episode identifiers can be further ranked based on the subject matter of the items.

[0037] Once the video content item identifiers and podcast episode identifiers are matched by the matching subsystem 142, the platform optimizer 170A can combine rankings of the matched video content item identifiers and the matched podcast episode identifiers, for example, by combining popularity metrics for each item. The content sharing platform 120 can use these combined rankings to provide a more accurate representation of the podcast episodes and / or video content items within the content sharing platform 120. The platform optimizer 170A can also cause the content sharing platform 120 to provide information associated with both the matched podcast episode identifiers and the matched video content item identifiers to a user. For example, a user may use the content sharing platform 120 to search for videos related to a particular topic. The content sharing platform 120 can use the combined rankings generated by the platform optimizer 170A to identify one or more video content items related to the particular topic. For example, a video content item that would not have ranked highly based on popularity metrics alone may be ranked highly based on the popularity metrics of the matching podcast episodes.

[0038] Furthermore, in response to a user's search request, the content sharing platform 120 can provide the user with both video content items and matching podcast episodes related to the searched topic. When providing matching podcast episodes, the content sharing platform 120 can include audio-specific features and / or podcast-specific information. For example, audio-specific features can include a “listen only” option. An example of a “listen only” feature can include optimized advertisements or promotional items that are more suitable for listening, rather than advertisements or promotional items that are more suitable for viewing. For example, a user may be using the content sharing platform 120 to watch a video content item that has matching podcast episodes. The content sharing platform 120 can present the video content item with a “listen only” option and / or present the video content item optimized for a listening experience. Promotional items presented within the video content item can be optimized for a listening experience. As another example, the podcast-specific information can include “next / previous episode” features and / or host information. FIGS. 3-7 illustrate graphical user interfaces of an exemplary content sharing platform 120 enhanced by the platform optimizer 170A.

[0039] In some implementations, the platform optimizer 170B can be used to optimize the search engine platform 130 and / or to improve the user experience of the search engine platform 130. In some implementations, similar to how the platform optimizer 170A optimizes the content sharing platform 120, the platform optimizer 170B can optimize the search engine platform 130 by adjusting the rankings of matched video content items and / or matched podcast episodes to reflect the correlation between the two. The search engine platform 130 can rank the podcast episode identifiers and / or video content item identifiers based on certain metrics, including the number of plays. The platform optimizer 170B can combine the number of plays of the matched video content item identifiers with the number of plays of the matched podcast episode identifiers. The number of plays can be the number of times a video content item associated with a video content identifier has started playing on the content sharing platform, the search engine platform, and / or another platform. The play count may be the number of times that a podcast episode associated with the podcast episode identifier has been initiated to play on a content sharing platform, a search engine platform, a podcast manager platform, and / or another platform.

[0040] The search engine platform 130 can use the combined play counts to rank both the matched video content items and the matched podcast episodes when determining whether to return either or both in response to a search. For example, a user can use the search engine platform 130 to search the Internet for a particular subject. The search engine platform 130 can determine that the results include a particular video content item. The search engine platform 130, via the platform optimizer 170B, can determine that a particular video content item has matching podcast episodes (as determined by the matching subsystem 142). The platform optimizer 170B can adjust the ranking of the video content items based on the combined metrics associated with both the video content items and the matched podcast episodes. The metrics can include, for example, play counts and / or popularity metrics.

[0041] The platform optimizer 170B can also be used to improve the user experience of the search engine platform 130. In some implementations, if the search results include a video content item with a matching podcast episode (or vice versa, a podcast episode with a matching video content item), the search engine platform 130 can display both the video content item and the podcast episode. An exemplary graphical user interface of the search engine platform 130 enhanced by the platform optimizer 170B is shown in FIG.

[0042] In some implementations, platform optimizer 170C can be used to optimize podcast manager platform 150 and / or improve the user experience of podcast manager platform 150. Podcast manager platform 150 can provide podcast analytics information, for example, to podcast publishers, including, for example, the number of times a podcast episode has been played, the number of plays in the past 30 days, and the average play duration. In some implementations, to optimize podcast manager platform 150, platform optimizer 170C can identify analytics information associated with both the matched podcast episode identifiers and the matched video content item identifiers. In some implementations, podcast manager platform 150 can use an API, for example, to fetch the analytics information associated with the matched video content item identifiers from content sharing platform 120.

[0043] In some implementations, a user of the podcast management platform 150 (e.g., a podcast publisher) can use the podcast management platform 150 to request analytical information for a podcast. The user can identify one or more channels A-X of the content sharing platform 120 that are associated with the user's podcast episodes. The podcast manager platform 150 can identify podcast episode identifiers associated with the user and can also identify video content item identifiers associated with the identified channels. The platform optimizer 170C can match the identified video content item identifiers with the identified podcast episode identifiers using the matching subsystem 142. The platform optimizer 170C can then determine analytical information associated with the matched podcast episode identifiers and the matched video content item identifiers and provide the analytical information to the user. Examples of graphical user interfaces of the podcast manager platform 150 enhanced by the platform optimizer 170C are shown in FIGS. 9-10 .

[0044] In addition to the above, users may be provided with selectable controls over whether and when the systems, programs, or functionality described herein enable the collection of user information (e.g., information about the user's social networks, social actions or activities, occupation, user preferences, or the user's current location) and whether content or communications are sent to the user from the server. Additionally, certain data may be processed in one or more ways before being stored or used so that personally identifiable information is removed. For example, a user's identity may be processed so that the user's personally identifiable information cannot be determined, and the user's geographic location may be generalized where the location information is obtained (e.g., at the city, zip code, or state level) so that the user's specific location cannot be determined. Thus, users may control what information is collected about them, how that information is used, and what information is provided to them.

[0045] 2 illustrates a matching subsystem according to one implementation of the present disclosure. The matching subsystem 142 can include an attribute extraction module 203, a comparison score generator 205, and a matching module 207.

[0046] The data store 110 can store podcast episodes 211, video content items 212, a matching score heap 213, a set of matched podcast episodes 214, and a set of matched video content items 215. The podcast episodes 211 can include a list of identified podcast episodes identified by the podcast episode fetcher 144 of FIG. 1. In some implementations, the podcast episodes 211 stores a list of podcast identifiers that reference podcast episodes stored in another data store (not shown). For example, the podcast episodes 211 can be an index of podcast episodes. Similarly, the video content items 212 can include a list of identified video content items identified by the video content item fetcher 143 of FIG. 1. In some implementations, the video content items 212 store a list of video content items that reference video content items stored in another data store (not shown). For example, the video content items 212 can be an index of video content items.

[0047] The attribute extraction module 203 can extract attributes from podcast episodes and / or video content items. The attributes can include, but are not limited to, audio transcripts, audio content, titles, descriptions, durations, and / or publication dates. Some of the attributes, such as titles and descriptions, can be stored in the metadata of podcast episodes and / or video content items. Thus, the attribute extraction module 203 can read the metadata and extract relevant attributes. The attribute extraction module 203 can store the extracted attributes in the data store 110. Other attributes may not be stored in the metadata of the associated media items, in which case the attribute extraction module 203 can use other techniques to identify and extract relevant attributes. For example, the attribute extraction module 203 can generate transcripts of the media items using various transcription techniques. In some implementations, the podcast episodes 211 can be a table that stores podcast episode identifiers with associated podcast episode attributes, and the video content items 212 can be a table that stores video content item identifiers with associated video content item attributes.

[0048] The comparison score generator 205 can generate a comparison score for each media item (i.e., for each podcast episode referenced in the podcast episode 211 and / or for each video content item referenced in the video content item 212). In some implementations, the comparison score generator 205 can identify a first podcast episode identifier in the podcast episode 211. The first podcast episode identifier may be one that does not have a matching video content item. That is, the first podcast episode identifier may not be included in the matched episodes 215 of the data store 110.

[0049] The comparison score generator 205 may compare the extracted attributes of the first podcast episode identifier with the extracted attributes of the video content item 212. Based on the comparison of the attributes, the comparison score generator 205 may generate a matching score. If the matching score exceeds a threshold score, the first podcast episode identifier and the matched video content item may be added to a matching score heap 213. The matching score heap 213 may store a list of episode identifiers, video content item identifiers, and their matching scores. The matching score heap 213 may be ordered by matching score value, with the highest matching score value at the top of the heap.

[0050] In some implementations, the comparison score generator 205 can first compare the transcript attributes of the first podcast episode identifier with the transcript attributes of the video content item 212. In some implementations, the transcript may be the best way to match the video content item and the podcast episode. If the matching score based on the transcript meets the matching criteria (i.e., exceeds the matching score threshold), the comparison score generator 205 can stop there. In some implementations, the matching score generator 205 can compare the remaining attributes to generate a more comprehensive matching score.

[0051] In some implementations, the matching module 207 can determine a matching value for each attribute. The matching score can then be a weighted average of the attribute matching values. For example, the matching module 207 can compare a transcript associated with a podcast episode identifier to a transcript associated with a video content item identifier. If the transcripts match or substantially match (e.g., more than a certain percentage of the transcripts match, e.g., 70% match), the matching module 207 can store a matching value for the transcript attribute. In some implementations, the matching value for each attribute can be "1" if there is a match and "0" if there is no match. Similarly, the matching module 207 can compare a title attribute associated with a podcast episode identifier to a title associated with a video content item identifier. If the titles match or substantially match (e.g., more than a certain percentage of the titles match, e.g., 90% match), the matching module 207 can store a matching value (e.g., "1") for the title attribute. If the titles do not match, the matching module 207 can store a no-match value (e.g., "0") for the title attribute. The matching module 207 can perform a similar comparison for each attribute associated with the podcast episode identifier and the video content item identifier.

[0052] To determine the matching score, in some implementations, the matching module 207 can sum the attribute matching values. If the matching score exceeds a certain threshold, the matching module 207 can determine that the podcast episode identifier and the video content item identifier match. In some implementations, the matching module 207 can determine the matching score using an average or weighted average of the attribute matching values. For example, because a match in the transcript indicates a higher likelihood that the podcast episode identifier and the video content item identifier match, the matching module 207 can give a higher weight to the transcript. As another example, because the podcast episode and the podcast episode's video content item may be published on different dates, the matching module 207 can give a lower weight to the publication date. The matching module 207 can use other techniques to determine the matching score for each podcast episode identifier and video content item identifier pair.

[0053] The matching module 207 can determine when the matching score heap 213 is not empty. If the matching score heap 213 is not empty, the matching module 207 can select the first entry in the matching score heap 213 (i.e., the matched podcast episode identifier and video content item identifier with the highest matching score). In some implementations, the matching module 207 can determine whether the podcast episode identifier and / or video content item identifier in the first entry of the matching score heap 213 are already matched by checking whether any of the podcast episode identifier and / or video content item identifier are listed in the matched episodes 215 list or the matched videos list 217, respectively. If they are not matched, the matching module 207 can add the podcast episode identifier and video content item identifier in the first entry of the matching score heap 213 to the matched episodes 215 list or the matched videos list 217, respectively.

[0054] Figures 3-10 show exemplary graphical user interfaces (GUIs) on client devices according to implementations of the present disclosure. Figures 3-7 show exemplary GUIs on user devices showing content provided by a content sharing platform, such as content sharing platform 120 of Figure 1. Figure 8 shows an exemplary GUI on a user device showing search results provided by a search platform, such as search engine platform 130 of Figure 1. Figures 9 and 10 show exemplary GUIs on user devices showing content provided by a podcast manager platform, such as podcast manager platform 150 of Figure 1.

[0055] FIG. 3 illustrates an exemplary podcast destination page 300 on a content sharing platform on a user device according to one implementation of the present disclosure. In some implementations, the platform optimizer 170A of FIG. 1 can enhance the content sharing platform 120 by providing a podcast destination page, as shown in FIG. 3. The podcast destination page can include podcasts in which the user has expressed interest (e.g., podcasts that the user typically listens to or has listened to, or podcasts to which the user has subscribed or liked). The podcast destination page can include podcasts related to topics in which the user has expressed interest. In some implementations, the podcast destination page can include links to podcasts and / or podcast episodes with rankings enhanced by the platform optimizer 170A. For example, the podcast 302 shown in FIG. 3 can have a matched video content item. A combined popularity metric associated with the podcast 302 and the matched video content item can list the podcast 302 on the user's podcast destination page. The podcast destination page can group podcasts based on topic and / or style, for example, “inspirational talk” and “talk show,” as shown in FIG. 3.

[0056] 4 illustrates an exemplary GUI 400, showing an example of a content sharing platform that includes both podcast episodes and video content items, according to one implementation of the present disclosure. A "Good for listening" section 401 is included in the home screen shown in FIG. 4. In some implementations, the platform optimizer 170A of FIG. 1 can enhance the content sharing platform 120 to include links to video content items that are matched to podcast episodes. The video content items listed in the "Good for listening" section 401 can be ranked according to a combined popularity metric of the matched video content items and the matched podcast episodes.

[0057] FIG. 5 illustrates an exemplary GUI 500 of a content sharing platform optimized for audio content, such as a video content item, matched to a podcast episode, according to one implementation of the present disclosure. In one example, a user can select a podcast episode from the “Suitable for Listening” section 401 shown in FIG. 4 , and the podcast episode can be presented to the user as shown in FIG. 5 . The GUI 500 can include information provided by both the matched podcast episode identifier and the matched video content item. For example, the GUI 500 can include the video content item at the top of the screen and information extracted from the matched podcast episode at the bottom of the screen. For example, host information can be extracted from metadata of the matched podcast episode. The video content item matched to the podcast episode can be provided to the user via a content sharing platform using the listening-optimized GUI 500, and rather than displaying the video content item full-screen, the video content item can occupy less than half of the screen, allowing the listening control 502 to be more prominent on the screen.

[0058] FIG. 6 illustrates an example GUI 600 of a content sharing platform enhanced for episodic content, according to one implementation of the present disclosure. As shown in FIG. 6, GUI 600 includes a link to a podcast 602, as well as a video of the podcast episode displayed in the main portion of the screen. By matching the video of the podcast episode with the podcast series associated with the podcast episode, GUI 600 can display additional information associated with the matched podcast. In the example shown in FIG. 6, a link 601 to "Continue Watching Season 2" for the podcast series can be added to GUI 600. Without matching the video of the podcast episode with the podcast episode identifier (and thus the podcast series), the content sharing platform may not have enough information to include links to other podcast episodes in the series in GUI 600.

[0059] 7 illustrates an exemplary GUI 700 of a lock screen showing media controls optimized for listening to audio content, such as podcast episodes, according to one implementation of the present disclosure. The lock screen may be displayed on a mobile device when the mobile device is playing a video matching the podcast episode using a content sharing platform. Because the video matches the podcast episode, the GUI 700 may display an optimized lock screen showing media controls more suited to audio content. That is, rather than providing media controls traditionally used for viewing video content items (e.g., a "skip" control), the GUI 700 may provide media controls traditionally used for audio content, such as a ±10 second seek control 701.

[0060] FIG. 8 illustrates an example GUI 800 of a search engine platform optimized according to aspects of the present disclosure. In this example, the search engine results combine search results for audio episodes and search results for video content. As shown in FIG. 8, the search results may be presented in a carousel showing mixed content, such as some audio content items (e.g., podcasts or podcast episodes) and some video content items. More specifically, the search results include a carousel 803 that includes links to podcast episodes 801 and video content items 802. A traditional search engine platform may present two carousels, one for podcasts and one for videos, which takes up more space on the screen and can be particularly problematic on smaller mobile device screens.

[0061] FIG. 9 illustrates an example GUI 900 of a podcast manager platform optimized according to aspects of the present disclosure. As indicated by header 902, analytical information provided to a user (e.g., a podcast publisher) via a podcast manager platform (e.g., podcast manager platform 150 of FIG. 1 ) includes analytical information from both the podcast publisher and the content sharing platform. In one example, a platform optimizer (e.g., platform optimizer 170C of FIG. 1 ) identified video content items matching the podcast episodes listed in FIG. 9 and combined analytical information associated with both the podcast episodes and the matched video content items. Hovering over metrics can display additional details. For example, as shown in FIG. 9 , the mouse is hovering over the number of plays for Ep 114. Box 904 displays a breakdown of the number of plays for Ep 114, including 48 plays on the podcast publisher platform and 128 plays on the content sharing platform.

[0062] 10 illustrates an exemplary GUI 1000 that provides additional details regarding the analytics information provided to a user, according to aspects of the present disclosure. For example, GUI 1000 includes additional details regarding the number of plays for Ep 144 of FIG. 9. The total number of plays for the podcast episode and the matching video content item was 176, of which 48 were audio plays and 128 were video plays. The play time is the sum of the total play times for both the video content item and the podcast episode. A graph shows the total number of plays on a timeline.

[0063] 11, 12, and 13 show flow diagrams of methods 1100, 1200, and 1300 performed according to some implementations of the present disclosure. Methods 1100, 1200, and 1300 can be performed by processing logic that can include hardware (circuitry, dedicated logic, etc.), software (e.g., instructions executing on a processing device), or a combination thereof. In one implementation, some or all of the operations of methods 1100, 1200, and 1300 can be performed by one or more components of system 100 of FIG.

[0064] For ease of explanation, methods 1100, 1200, and 1300 of the present disclosure are illustrated and described as a series of acts. However, acts according to the present disclosure can be performed in various orders and / or simultaneously, as well as with other acts not shown and described herein. Moreover, not all illustrated acts are required to implement methods 400 and 500 in accordance with the disclosed subject matter. Furthermore, those skilled in the art will understand and appreciate that methods 1100, 1200, and 1300 can also be represented as a series of interrelated states via a state diagram or events. Furthermore, it should be appreciated that methods 1100, 1200, and 1300 disclosed herein can be stored on an article of manufacture to facilitate transport and transfer of such methods to a computing device. As used herein, the term "article of manufacture" is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0065] 11 is a flow diagram of a method 1100 for enhancing a content sharing platform by matching video content items to podcast episodes, according to some implementations of the present disclosure. At block 1110, processing logic may access a data store that stores a plurality of podcast episode identifiers. A podcast episode identifier from the plurality of podcast identifiers may be associated with one or more podcast episode attributes.

[0066] The podcast episode attributes and / or video content item attributes may include at least one of an audio transcript, audio content, title, description, duration, or publication date. Processing logic may identify the attributes by reading metadata associated with the respective podcast episode identifier and / or video content item identifier. For example, the publication date of the podcast episode may be stored in the metadata associated with the podcast episode identifier. In some implementations, processing logic may determine or generate the attributes. For example, processing logic may use transcription techniques to generate a transcript of the podcast episode associated with the podcast episode identifier. Attributes may similarly be obtained from the video content item and / or from video content item metadata associated with the video content item identifier.

[0067] At block 1120, processing logic may identify a video content item. The video content item may include or be associated with one or more video content item attributes. In some implementations, processing logic may receive identification of the video content item from a user device. For example, a user using a content sharing platform may upload a video content item to the content sharing platform. The processing logic may identify the video as a video content item and may extract or identify one or more video content item attributes. In some implementations, processing logic may identify a video content item that has already been uploaded to the content sharing platform.

[0068] At block 1130, processing logic may determine a matching podcast episode among a plurality of podcast episode identifiers that match the video content item based on one or more podcast episode attributes and one or more video content item attributes.

[0069] In some implementations, to determine matching podcast episodes, processing logic may compare one or more video content item attributes with one or more podcast episode attributes of each of a plurality of podcast episode identifiers. In some implementations, processing logic may compare the podcast episode attributes with the video content item attributes for each podcast episode identifier. For example, processing logic may compare a transcript associated with each podcast episode identifier with a transcript associated with the video content item identifier. Processing logic may assign a matching value for each compared attribute. For example, if the transcripts match, processing logic may assign a matching value of “1” to the transcript attribute, and if the titles do not match, processing logic may assign a matching value of “0” to the title attribute. Determining whether attributes match may include substantial matching. That is, processing logic may determine that the transcripts match if a certain percentage (e.g., 70%) of the transcripts match, or processing logic may determine that the descriptions match if a certain percentage (e.g., 90%) of the descriptions match.

[0070] The processing logic may determine a matching score for each of the one or more podcast episode identifiers based on the comparison. In some implementations, the matching score may be the sum of the matching values ​​for each attribute being compared. In some implementations, the matching score may be the average (or weighted average) of the matching values ​​for each attribute being compared. For example, the processing logic may assign a higher weight to the transcript and a lower weight to the title. The processing logic may identify the matching podcast episode identifier with the highest matching score that meets the matching criteria. The highest matching score may meet the matching criteria by exceeding a minimum matching score threshold.

[0071] In some implementations, to determine matching podcast episodes, the processing logic may provide one or more video content item attributes as input to a machine learning model, which may be trained to identify matching podcast episodes based on the one or more podcast episode attributes and the video content item attributes.

[0072] At block 1140, the processing logic may adjust a ranking of at least one of the video content items or the matching podcast episodes to reflect the correspondence between the video content items and the matching podcast episodes. In some implementations, the ranking of the video content items or the ranking of the matching podcast episodes is based on a popularity metric. Adjusting the ranking of the video content items or the matching podcast episodes to reflect the correspondence between the video content items and the matching podcast episodes may include combining a popularity metric associated with the video content items with a popularity metric associated with the matching podcast episodes.

[0073] At block 1150, the processing logic can provide information associated with the matching podcast episodes to the first user device. In some implementations, the information associated with the matching podcast episodes is provided in response to receiving a search query from the user device. The results of the search query can include video content items. Additionally, the results of the search query can include podcast analytics information associated with the matching podcast episodes. In some implementations, the information associated with the matching podcast episodes includes host information, previous / next podcast episode controls, and / or listening-only options.

[0074] FIG. 12 illustrates a flow diagram of a method 1200 for enhancing a search engine platform by matching video content items to podcast episodes, according to some implementations of the present disclosure.

[0075] At block 1210, processing logic may access a data store comprising one or more podcast episode identifiers and one or more video content item identifiers, wherein the podcast episode identifiers of the one or more podcast episode identifiers may be associated with one or more podcast episode attributes, and wherein the video content item identifiers of the one or more video content item identifiers may be associated with one or more video content item attributes.

[0076] The podcast episode attributes and / or video content item attributes may include at least one of an audio transcript, audio content, title, description, duration, or publication date. Processing logic may identify the attributes by reading metadata associated with the respective podcast episode identifier and / or video content item identifier. For example, the publication date of the podcast episode may be stored in the metadata associated with the podcast episode identifier. In some implementations, processing logic may determine or generate the attributes. For example, processing logic may use transcription techniques to generate a transcript of the podcast episode associated with the podcast episode identifier. Attributes may similarly be obtained from the video content item and / or from video content item metadata associated with the video content item identifier.

[0077] The processing logic may also periodically identify additional podcast episodes and / or additional video content items and store the associated additional podcast episode identifiers and / or additional video content item identifiers in the data store. In some implementations, the processing logic may crawl the Internet to identify additional podcast episodes and video content items. In some implementations, the processing logic may receive the additional podcast episodes and / or video content items. For example, a user may upload a podcast episode and / or video content item to the platform, and the processing logic may store the newly uploaded podcast episode identifiers and / or video content item identifiers in the data store.

[0078] At block 1220, processing logic may determine, for a matching podcast episode identifier among the one or more podcast episode identifiers, a matching video content item identifier based on one or more podcast episode attributes associated with the matching podcast episode identifier. In some implementations, processing logic may select one of the multiple podcast episode identifiers from the data store as a matching podcast episode identifier for finding a matching video content item. In some implementations, the data store includes an identifier indicating whether each podcast episode identifier in the data store has a matching video content item identifier. The processing logic may select the matching podcast episode identifier as the first podcast episode identifier in the data store that does not have a matching video content item. In some implementations, processing logic may select the matching podcast episode identifier based on a popularity metric. That is, processing logic may identify a podcast episode identifier that does not have a matching video content item but has a high popularity metric (e.g., a number of plays or likes above a respective threshold) as a matching podcast episode identifier.

[0079] In some implementations, to determine matching video content item identifiers, processing logic may compare one or more podcast episode attributes associated with the matching podcast episode identifiers with one or more video content item attributes associated with the one or more video content item identifiers. In some implementations, processing logic may compare, for each video content item identifier, the podcast episode attributes associated with the matching podcast episode identifiers with the video content item attributes. For example, processing logic may compare transcripts associated with the matching podcast episode identifiers with transcripts associated with each video content item identifier. Processing logic may assign a matching value for each compared attribute. For example, if the transcripts match, processing logic may assign a matching value of "1" to the transcript attribute, and if the titles do not match, processing logic may assign a matching value of "0" to the title attribute. Determining whether attributes match may include substantial matching. That is, processing logic may determine that the transcripts match if a certain percentage (e.g., 70%) of the transcripts match, or processing logic may determine that the descriptions match if a certain percentage (e.g., 90%) of the descriptions match.

[0080] The processing logic may determine a matching score for each of the one or more video content item identifiers based on the comparison. In some implementations, the matching score may be the sum of the matching values ​​for each attribute being compared. In some implementations, the matching score may be the average (or weighted average) of the matching values ​​for each attribute being compared. For example, the processing logic may assign a higher weight to the transcript and a lower weight to the title. The processing logic may identify the matching video content item identifier with the highest matching score that meets the matching criteria. The highest matching score may meet the matching criteria by exceeding a minimum matching score threshold.

[0081] In some implementations, to determine matching video content item identifiers, the processing logic may provide one or more video content item attributes as input to a machine learning model, which may be trained to identify matching video content item identifiers based on one or more matching podcast episode attributes and video content item attributes.

[0082] At block 1230, the processing logic may adjust a ranking of at least one of the matching video content item identifiers or the matching podcast episode identifiers to reflect a correspondence between the matching video content item identifiers and the matching podcast episode identifiers. In some implementations, the ranking of the matching video content items or the ranking of the matching podcast episodes is based on a popularity index. Adjusting the ranking of the video content items or the matching podcast episodes to reflect the correspondence between the video content items and the matching podcast episodes may include combining a popularity index associated with the matching video content item identifiers with a popularity index associated with the matching podcast episode identifiers.

[0083] At block 1240, the processing logic may provide information associated with the matching podcast episode identifiers and video content item identifiers to the user device. In some implementations, the information associated with the matching podcast episode identifiers and video content item identifiers may be provided in response to receiving a search query from the user device. The results of the search query may include at least one of matching video content items or matching podcast episode identifiers. For example, search results including a particular video content item provided to a user through a platform not enhanced by aspects of the present disclosure would include only the video content item and information associated with the video content item. However, by matching video content items to podcast episodes in accordance with aspects of the present disclosure, the search platform may enhance the search results by providing both the video content item and the matched podcast episode, along with associated information, to the user device. Thus, information that may be associated only with the podcast episode (e.g., host information) is added to the search results.

[0084] 13 shows a flow diagram of a method 1300 for enhancing a podcast manager platform by matching video content items to podcast episodes according to one implementation of the present disclosure. At block 1310, processing logic may receive a request for podcast analytics information for a podcast, the podcast associated with one or more podcast episodes. In some implementations, the processing logic may receive the request from a user device implementing the podcast manager platform. A user may request podcast analytics information associated with a particular podcast.

[0085] At block 1320, the processing logic may receive an identification of a source comprising one or more video content items. In some implementations, a podcast may be associated with a particular channel on a content sharing platform. In other implementations, a user may provide a source containing one or more video content items to be associated with a podcast to the podcast manager platform.

[0086] At block 1330, processing logic may identify one or more podcast episode attributes of one or more podcast episodes. At block 1340, processing logic may identify one or more video content item attributes of one or more video content items. The podcast episode attributes and / or video content item attributes may include at least one of an audio transcript, audio content, title, description, duration, or publication date. The processing logic may identify the attributes by reading metadata associated with the respective podcast episode identifier and / or video content item identifier. For example, the publication date of the podcast episode may be stored in the metadata associated with the podcast episode identifier. In some implementations, the processing logic may determine or generate the attributes. For example, the processing logic may use transcription techniques to generate a transcript of the podcast episode associated with the podcast episode identifier. The attributes may similarly be obtained from the video content item and / or from video content item metadata associated with the video content item identifier. In some implementations, the processing logic may receive the attributes from a user device (e.g., a user may provide the attributes).

[0087] At block 1350, processing logic may determine a matching video content item that matches a matching podcast episode of the one or more podcast episodes based on one or more podcast episode attributes and one or more video content item attributes. In some implementations, the processing may first identify a matching podcast episode from the one or more podcast episodes to identify a matching video content item. The processing logic may identify a podcast episode as a matching podcast episode to identify a matching video content item based on a popularity index (i.e., identifying the video content items of the most popular podcast episodes) or systematically (i.e., selecting the first podcast episode in a list of podcast episodes). A podcast episode selected as a matching podcast episode may be one that does not already have a matching video content item. The processing logic may determine a matching video content item for each podcast episode associated with the identified podcast.

[0088] To determine matching video content items, processing logic may determine matching scores for one or more video content items by comparing the respective video content item attributes with one or more podcast episode attributes associated with the matching podcast episodes. The matching scores may be determined as described above with respect to FIGS. 11 and 12 by comparing the attributes of the matching podcast episodes with the attributes of each video content item. Processing logic may identify the matching video content item as the video content item with the highest matching score. In some implementations, the matching score meets the matching criteria by exceeding a matching value threshold. For example, if the best-matching video content item has a matching score below the matching value threshold, processing logic may not identify it as a match.

[0089] In some implementations, to determine matching video content item identifiers, the processing logic may provide one or more video content item attributes and matching podcast episode attributes as inputs to a machine learning model, which may be trained to identify matching video content item identifiers based on the one or more matching podcast episode attributes and video content item attributes.

[0090] At block 1360, processing logic may determine analytical information associated with the matching video content items. At block 1370, processing logic may provide a response to the request, the response comprising analytical information associated with the matching video content items and podcast analytical information. In some implementations, the analytical information provided in response to the request may include a combined number of plays associated with each podcast episode and the matching video content items, as shown in the example GUIs in FIGS. 9 and 10. The analytical information provided in response to the request may also include additional combined information, such as, for example, a combined average play length or a combined number of plays in the first 30 days. The analytical information may also include demographics about podcast listeners and viewers of the video content items.

[0091] FIG. 14 is a block diagram illustrating an exemplary computer system 1400 according to an implementation of the present disclosure. The computer system 1400 may correspond to the server machine 140, the content sharing platform 120, and / or the end-user devices 102A-N described with respect to FIG. 1. The computer system 1400 may operate in the capacity of a server or endpoint machine in an end-point server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a television, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a web appliance, a server, a network router, a switch, or a bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Furthermore, while only a single machine is illustrated, the term “machine” shall be interpreted to include any collection of machines that individually or jointly execute a set (or sets) of instructions to perform any one or more of the methodologies described herein.

[0092] The exemplary computer system 1400 includes a processing device (processor) 1402, a main memory 1404 (e.g., read only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), double data rate (DDR SDRAM, or DRAM (RDRAM)), etc.), a static memory 1406 (e.g., flash memory, static random access memory (SRAM), etc.), and a data storage device 1418, which communicate with each other via a bus 1440.

[0093] Processor (processing device) 1402 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, or the like. More specifically, processor 1402 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing other instruction sets or combinations of instruction sets. Processor 1402 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. Processor 1402 is configured to execute instructions 1426 for performing the operations described herein (e.g., instructions for identifying matching video content items and podcast episodes).

[0094] The computer system 1400 may further include a network interface device 1408. The computer system 1400 may also include a video display unit 1410 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), input devices 1412 (e.g., a keyboard and alphanumeric keyboard, a motion-sensitive input device, a touch screen), a cursor control device 1414 (e.g., a mouse), and a signal generation device 1420 (e.g., a speaker).

[0095] The data storage device 1418 may include a non-transitory machine-readable storage medium 1424 (also a computer-readable storage medium) on which is stored a set of one or more instructions 1426 (e.g., for optimizing a platform using identified matched pairs of video content items and podcast episodes) and embodying any one or more of the methods or functions described herein. The instructions may also reside, completely or at least partially, within the main memory 1404 and / or within the processor 1402 during execution by the computer system 1400, with the main memory 1404 and the processor 1402 also constituting machine-readable storage media. The instructions may further be transmitted or received over a network 1430 via the network interface device 1408.

[0096] In one implementation, instructions 1426 include instructions for identifying matching pairs of podcast episode identifiers and video content item identifiers and optimizing the platform based on the identified matching pairs. While computer-readable storage medium 1424 (machine-readable storage medium) is shown to be a single medium in the exemplary implementation, the terms “computer-readable storage medium” and “machine-readable storage medium” should be considered to include a single medium or multiple media (e.g., centralized or distributed databases and / or associated caches and servers) that store one or more sets of instructions. The terms “computer-readable storage medium” and “machine-readable storage medium” should also be considered to include any medium that can store, encode, or carry a set of instructions for execution by a machine, causing the machine to perform any one or more of the methods of this disclosure. Accordingly, the terms “computer-readable storage medium” and “machine-readable storage medium” should be considered to include, but are not limited to, solid-state memory, optical media, and magnetic media.

[0097] References throughout this specification to "one implementation" or "an implementation" mean that particular features, structures, or characteristics described in connection with that implementation are included in at least one implementation. Thus, the appearances of the phrases "in one implementation" or "in an implementation" in various places throughout this specification may, but do not necessarily, refer to the same implementation, depending on the context. Furthermore, particular features, structures, or characteristics may be combined in any suitable manner in one or more implementations.

[0098] To the extent that the terms "includes," "including," "has," "contains," variations thereof, and other similar terms are used in either the detailed description or the claims, these terms are intended to be inclusive in the same manner as the term "comprising" as an open transition word, without excluding additional or other elements.

[0099] As used herein, terms such as “component,” “module,” and “system” are generally intended to refer to computer-related entities, such as hardware (e.g., circuitry), software, a combination of hardware and software, or an entity associated with an operational machine having one or more specific functions. For example, a component may be, but is not limited to, a process running on a processor (e.g., a digital signal processor), a processor, an object, an executable file, a thread of execution, a program, and / or a computer. By way of example, both an application running on a controller and the controller can be a component. One or more components can reside within a process and / or thread of execution, and components may be localized on one computer or distributed among two or more computers. Furthermore, a “device” may be provided in the form of specially designed hardware, general-purpose hardware specialized by the execution of software that enables the hardware to perform specific functions (e.g., generating features and / or descriptors), software on a computer-readable medium, or a combination thereof.

[0100] The aforementioned systems, circuits, modules, etc. have been described with respect to interactions between several components and / or blocks. It will be recognized that such systems, circuits, components, blocks, etc. can include those components or designated subcomponents, portions of the designated components or subcomponents, and / or additional components, according to various permutations and combinations of the foregoing. Subcomponents can also be implemented as components communicatively coupled to other components rather than being included within a parent component (hierarchy). Furthermore, it should be noted that one or more components can be combined into a single component providing aggregate functionality or divided into several individual subcomponents, and that optionally one or more intermediate layers, such as a management layer, can be provided to communicatively couple such subcomponents to provide integrated functionality. Any component described herein can also interact with one or more other components not specifically described herein but known to those skilled in the art.

[0101] Furthermore, the words "example" or "exemplary" are used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" should not necessarily be construed as preferred or advantageous over other aspects or designs. Rather, use of the word "example" or "exemplary" is intended to present concepts in a concrete manner. The term "or," as used in this application, is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, the term "X uses A or B" is intended to mean any of the natural inclusive permutations. That is, if X uses A, if X uses B, or if X uses both A and B, then "X uses A or B" is satisfied in any of the foregoing cases. Furthermore, the articles "a" and "an," as used in this application and the appended claims, should be construed generally to mean "one or more" unless otherwise specified or clear from the context to refer to the singular form.

[0102] Finally, implementations described herein include the collection of data describing users and / or user activities. In one implementation, such data is collected only if the user consents to the collection of this data. In some implementations, the user is asked to explicitly authorize data collection. Additionally, the user can opt in or out of participating in such data collection activities. In one implementation, the collected data is anonymized before performing analysis to obtain statistical patterns so that the user's identity cannot be determined from the collected data. [Explanation of symbols]

[0103] 100 System Architecture 102A~N End-user devices 104 Network 110 Datastore 120 Content Sharing Platform 121 Media Items 130 Search Engine Platforms 140 Server Machine 142 Matching Subsystem 143 Video Content Item Fetcher 144 Podcast Episodes Fetcha 150 Podcast Manager Platforms 165 Third-Party Platforms 170A Platform Optimizer 170B Platform Optimizer 170C Platform Optimizer 203 Attribute Extraction Module 205 Comparison Score Generator 207 Matching Module 211 podcast episodes 212 Video Content Items 213 Matching Score Heap 214 Matched Podcast Episode Sets 215 Matched Sets of Video Content Items 215 Matched Episodes 217 Matching Video List 300 Podcast Destination Pages 302 Podcasts 400 GUI 400 ways 401 "Good for Listening" Section 500 GUI 500 ways 502 Listening Control 600 GUI 601 Links 602 Podcasts 700 GUI 701 Seek Control 800 GUI 801 Podcast Episodes 802 Video Content Items 803 Carousel 900 GUI 902 Header 904 Box 1000 GUI 1100 methods 1200 methods 1300 methods 1400 Computer Systems 1402 Processing device (processor) 1404 main memory 1406 Static Memory 1408 Network Interface Device 1410 Video Display Unit 1412 Input Devices 1414 Cursor Control Device 1418 Data Storage Devices 1420 Signal Generating Device 1424 Non-transitory machine-readable storage medium 1424 computer-readable storage medium 1426 command 1430 Network 1440 Bus

Claims

1. accessing a data store comprising a plurality of podcast episode identifiers, wherein podcast episode identifiers of the plurality of podcast episode identifiers are associated with one or more podcast episode attributes; identifying a video content item, the video content item comprising one or more video content item attributes; determining a matching podcast episode identifier from the plurality of podcast episode identifiers that matches the video content item based on the one or more podcast episode attributes and the one or more video content item attributes; adjusting a ranking of at least one of the video content item or the matching podcast episode identifier to reflect a correspondence between the video content item and the matching podcast episode identifier, wherein the ranking of the video content item is based on a popularity index associated with the video content item and the ranking of the matching podcast episode identifier is based on a popularity index associated with the matching podcast episode identifier, and adjusting comprises combining the popularity index associated with the video content item with the popularity index associated with the matching podcast episode identifier; providing information associated with the matching podcast episode identifiers having the adjusted rankings to a first user device, the information comprising host information, previous / next podcast episode controls, or listen-only options; A computer-implemented method comprising:

2. 10. The method of claim 1, wherein the one or more podcast episode attributes comprise at least one of an audio transcript, audio content, title, description, duration, or publication date, and the one or more video content item attributes comprise at least one of an audio transcript, audio content, title, description, duration, or publication date.

3. The method of claim 1 , wherein the video content item is received from a second user device.

4. determining the matching podcast episode identifiers from the plurality of podcast episode identifiers that match the video content item, comparing the one or more video content item attributes with the one or more podcast episode attributes associated with each of the plurality of podcast episode identifiers; determining a matching score for each of the plurality of podcast episode identifiers based on the comparison; identifying the matching podcast episode identifier with the highest matching score, wherein the matching score meets a matching criterion; The method of claim 1 , comprising:

5. determining the matching podcast episode identifiers from the plurality of podcast episode identifiers that match the video content item, 10. The method of claim 1, comprising providing the one or more video content item attributes as input to a machine learning model trained to identify the matching podcast episode identifiers based on the one or more podcast episode attributes.

6. 10. The method of claim 1, wherein the information associated with the matching podcast episode identifier is provided in response to receiving a search query from the first user device, and a result of the search query comprises the video content item.

7. The method of claim 6 , wherein the results of the search query comprise podcast analytics information associated with the matching podcast episode identifiers.

8. A memory; a processing device communicatively coupled to the memory; and wherein the processing device: accessing a data store comprising one or more podcast episode identifiers and one or more video content item identifiers, wherein the podcast episode identifiers of the one or more podcast episode identifiers are associated with one or more podcast episode attributes and the video content item identifiers of the one or more video content item identifiers are associated with one or more video content item attributes; For a matching podcast episode identifier of the one or more podcast episode identifiers, determining a matching video content item identifier based on the one or more podcast episode attributes associated with the matching podcast episode identifier; adjusting a ranking of at least one of the matching video content item identifiers or the matching podcast episode identifiers to reflect a correspondence between the matching video content item identifiers and the matching podcast episode identifiers, wherein the ranking of the matching video content item identifiers or the ranking of the matching podcast episode identifiers is based on a popularity index, and wherein to effect the adjustment, the processing device is further configured to combine a popularity index associated with the matching video content item identifiers with a popularity index associated with the matching podcast episode identifiers; providing information associated with the matching podcast episode identifiers with the adjusted rankings and the matching video content item identifiers to a user device, the information comprising host information, previous / next podcast episode controls, or listen-only options; A system configured to:

9. 9. The system of claim 8, wherein the one or more podcast episode attributes comprise at least one of a transcript, audio content, title, description, duration, or publication date, and the one or more video content item attributes comprise at least one of a transcript, audio content, title, description, duration, or publication date.

10. the processing device: periodically identifying additional podcast episode identifiers and additional video content item identifiers; storing the additional podcast episode identifier and the additional video content item identifier in the data store; The system of claim 8 , further configured to:

11. 9. The system of claim 8, wherein the information associated with the matching podcast episode identifier and the matching video content item identifier is provided in response to receiving a search query from the user device, and results of the search query comprise one of the matching video content item identifier or the matching podcast episode identifier.

12. The processing device, for the matching podcast identifier of the one or more podcast episode identifiers, for determining the matching video content item identifier based on the one or more podcast episode attributes associated with the matching podcast episode identifier: comparing the one or more podcast episode attributes associated with the matching podcast episode identifiers with the one or more video content item attributes associated with the one or more video content item identifiers; determining a matching score for each of the one or more video content item identifiers based on the comparison; and identifying the matching video content item identifier having the highest matching score, wherein the matching score meets a matching criterion; and The system of claim 8 , further configured to:

13. To determine the matching video content item identifier, the processing device:

10. The system of claim 8, further configured to provide the one or more video content item attributes and the one or more matching podcast episode attributes as inputs to a machine learning model trained to identify the matching video content identifier based on the one or more matching podcast episode attributes.

Images