Dynamic link preview generation
By identifying communication platforms and generating customized data through the content provider system, the lack of control over link preview generation in existing technologies is solved, enabling dynamic link previews customized according to platform characteristics, thereby increasing user interaction and conversion opportunities.
Patent Information
- Application Number
- CN201980076114.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2018-12-31
- Filing Date
- 2019-10-09
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2039-10-09
AI Technical Summary
Existing link preview generation technologies lack the control capabilities of content provider systems, making it impossible to customize the content and format of link previews according to the characteristics of different communication platforms, resulting in insufficient richness and interactivity of link previews.
The system supports link preview generation through the content provider system, identifies the communication platform and finds customized data, and generates link previews of appropriate size and format according to platform characteristics, including time, geography and user interaction considerations, to achieve dynamic control over link previews.
It enables customized link previews based on the differences between different communication platforms, increasing user interactivity and conversion opportunities, and enhancing the richness and control of link previews.
Smart Images

Figure CN113056735B_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims priority to U.S. Application No. 16 / 237,541, filed on December 31, 2018, and entitled “Dynamic Link Preview Generation,” the entire disclosure of which is incorporated herein by reference. Background Art
[0003] A large amount of digital content can be accessed by users of computing devices via network addresses that are part of the Internet. For example, there are millions of websites, each with a large number of web pages that can be used to access digital images, animations, audio content, multimedia content, etc. Initially, in order to share access or knowledge of the digital content, a user of a computing device copied the network address and sent the network address as text to another user of another computing device. However, these network addresses are often difficult to resolve and accurately copy, causing user frustration and computing inefficiencies caused by repeated attempts.
[0004] Therefore, subsequent technologies have been developed to share network addresses using link previews. However, these technologies lack richness and are implemented locally at the user's device or through the communication platform through which the link is shared. As a result, control of link generation is borne by the user's device or communication platform and is not configured to handle a wide range of digital content that can be accessed via a large number of web pages. In a conventional example, a user may wish to share a link to a web page with another user via a messaging communication platform. In response, the messaging communication platform typically selects the first image and the title of the page that can be accessed via the web page as a link preview. Therefore, the generation of the link preview is controlled by the messaging communication platform rather than the content provider of the web page.
[0005] Although conventional techniques involving Open Graph (OG) metadata have been developed, these techniques support limited capabilities of content providers to indicate which content is accessible via web pages, and still do not support the ability to control how content is used to generate link previews. Thus, conventional link preview generation techniques do not support the ability of content providers to control the generation of link previews delivered by other devices. This limits the ability of these systems to control their digital content, and misses the opportunity to expand the richness of content when it is shared as part of a link preview by devices "external" to the content provider system. Summary of the invention
[0006] Dynamic link preview generation techniques are described that overcome challenges of conventional techniques by supporting link preview generation by a content provider system that presents digital content via a corresponding network address. In one example, the content provider system identifies a communication platform of the service provider system to be used to transmit a shared link based on a request received from a service provider system. This can be performed in a variety of ways, including based on a network domain from which a content request is received, as part of an open graph protocol request, etc.
[0007] After identifying the communication platform, the content provider system finds the customization data that describes how to generate the link preview for the communication platform. The customization data may specify which parts of the digital content are to be included in the link preview, the size and / or aspect ratio of the digital image, resolution, color, etc.
[0008] In response, the content provider system presents the digital content accessible via the network address at an appropriate size (e.g., aspect ratio, resolution, etc.). The presented digital content can then be cached and transmitted to the service provider system, for example, via a communication platform, for use as a link preview between a first client device and a second client device. In this way, the link preview can be customized to address how the link preview is transmitted via the communication platform and also control "what" is included in the link, and thus provide a degree of control over exposing the digital content to the content provider system that is not achievable using conventional techniques. Further discussion of these and other examples is included in the following sections and is shown in the corresponding figures.
[0009] This summary introduces some concepts in a simplified form, which will be further described in the following detailed description. As such, this summary is neither intended to indicate essential features of the claimed subject matter nor to be used as an aid in determining the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The detailed description is described with reference to the accompanying drawings. Entities represented in the drawings may refer to one or more entities, and thus singular or plural entities may be referred to interchangeably in the discussion.
[0011] Figure 1 is an illustration of an environment in an example implementation operable to employ the dynamic link preview generation techniques described herein.
[0012] Figure 2 Depicted in more detail shows Figure 1 A system in an example implementation of the operation of a preview generation module in generating link previews.
[0013] Figure 3is a flow diagram depicting a procedure in an example implementation in which a link preview is generated based on customized data found for a particular platform from which a request was initiated.
[0014] Figure 4 and Figure 5 Respective examples of link previews generated for different communication platforms are depicted.
[0015] Figure 6 An example implementation is depicted in which a link preview is configured to encourage a user to take an action, such as converting a good or service associated with digital content accessible via a network address to digital marketing content.
[0016] Figure 7 Depicted are systems in an example implementation in which a customization data module generates a model for controlling customizations applied to link previews.
[0017] Figure 8 is a flow diagram depicting a procedure in an example implementation in which a model describing user interactions with link previews is generated to customize generation of subsequent link previews.
[0018] Fig. 9 An example system is shown that includes various components of an example device that can be implemented as described with reference to Figures 1 to 8 Any type of computing device described and / or utilized to implement implementations of the techniques described herein. DETAILED DESCRIPTION
[0019] Overview
[0020] Conventional link preview generation techniques do not support the ability of a content provider system that makes digital content accessible via a network address (e.g., a URL) to control how link previews are generated to share awareness and access to the digital content. This limits the ability of content provider systems to use conventional techniques to extend the richness of link previews, including what digital content to include in a link preview and how to display the digital content as part of a link preview.
[0021] Thus, dynamic link preview generation techniques are described that overcome challenges of conventional techniques by supporting link preview generation by a content provider system that presents digital content via a corresponding network address. In one example, a user of a first client device may wish to share a network address (e.g., a link) with a user of a second client device via a communication platform of a service provider system. The communication platform can be configured in a variety of ways, such as to support instant messaging, social network communications (e.g., "shares" or posts), electronic messages, emails, etc. Examples of communication platforms include And also as included It is supported as part of a social networking system such as .
[0022] Thus, in this example, the service provider system receives input from a first client device to share a network address with a second client device. In response, the service provider system generates a content request to a content provider system to enable digital content to be accessed via a network address, such as a URL. The content provider system, based on the request, identifies a communication platform of the service provider system for transmitting a sharing link. This can be performed in a variety of ways, including based on the domain from which the content request was received, as part of an open graph protocol request, etc.
[0023] After identifying the communication platform, the content provider system looks up customization data that describes how to generate a link preview for the communication platform. The customization data may specify which portions of the digital content are to be included in the link preview, the size and / or aspect ratio of the digital image, resolution, color, etc. In this way, the customization data may be used to account for the nuances of the communication platform. The customization data may, for example, indicate an appropriate size to be used as part of the link preview.
[0024] In response, the content provider system renders the digital content accessible via the network address at an appropriate size (e.g., aspect ratio, resolution, etc.). The rendered digital content may then be cached and transmitted to the service provider system, e.g., via a communication platform, for use as a link preview between the first client device and the second client device. The link preview may be selected by the second client device to support navigation to the digital content accessible via the network address, and also provide information indicating what digital content is accessible via the network address.
[0025] In the above example, for example, the link preview can be customized to address how the link preview is transmitted via the communication platform, such as the size of the link preview, the orientation of the user interface to be used to display the link preview, the colors used by the user interface of the communication platform, etc. Custom data can also be used to specify which parts of the digital content are to be included in the link preview, which may be different based on the communication platform to be used to transmit the link preview. For example, a first communication platform can support the communication of link previews with digital image sizes or orientations that are smaller than those supported by another communication platform. Therefore, the content provider system can utilize customized data to support the generation of link previews that take into account these differences in display characteristics. As a result, link previews can be generated in various different ways based on the communication platform to be used to transmit the link preview.
[0026] Other considerations not involving the communication platform used to transmit the preview are also contemplated, for example, temporal considerations (i.e., time), such as holidays or the time of day when the request is received, geographic considerations, demographic data corresponding to users of the first client device and / or the second client device, etc. In addition, the link can be configured to be interactive to support user interaction before being used to initiate navigation to the corresponding network address. For example, the link can output an animation in response to detecting a "hover" (e.g., a gesture, a cursor) on the link, can provide a digital video, can include a game or question-and-answer function, etc.
[0027] In one example, the preview can be personalized based on the user who initiated the generation of the link for sharing and / or for the user who is to receive the generated link. For example, the content provider system can also use customization data to increase the likelihood of a user action being initiated by a user of a client device that receives a link preview. For example, the content provider system can generate a model based on monitored user interactions with past link previews, such as whether the link preview was used to navigate to a network address, whether the navigation resulted in a conversion of a good or service associated with the digital content (e.g., to digital marketing content), was adopted as part of an A / B test, etc. This can be based on the user who initiated the generation of the link and / or the user who is to receive the link, and therefore both users can be processed as part of dynamically generating the link.
[0028] The model can then be used to select specific portions of the digital content to include in subsequent link previews, select how the portion of the digital content is to be displayed, select the configuration of display characteristics (e.g., color) of the link preview itself, etc. For example, a link can be dynamically generated based on user interaction with an advertisement included within the link. Various other customizations are also contemplated. In this manner, the content provider system can achieve various advantages by controlling the generation of link previews that are not possible using conventional link preview generation techniques that are implemented only "outside" the content provider system.
[0029] In one implementation, a content request is received from a service provider system to attempt to crawl digital content associated with a network address to generate previews. However, in this implementation, at least one network address is presented as a digital content asset (e.g., a digital image as part of the Open Graph metadata, such as "https:contentprovidersystem.comimage.jpeg"), but the generation of link previews is actually initiated by the content provider system as described above. As a result, even for a service provider system that attempts to generate link previews on its own, link previews can still be generated based on the content provider system. Further discussion of these and other examples is included in the following sections and is shown in the corresponding figures.
[0030] In the following discussion, an example environment in which the techniques described herein may be employed is first described. Example procedures that may be performed in the example environment as well as other environments are then described. Thus, execution of the example procedures is not limited to the example environment, and the example environment is not limited to execution of the example procedures.
[0031] Example Environment
[0032] Figure 1 1 is an illustration of a digital media environment 100 in an example implementation operable to employ the dynamic link preview generation techniques described herein. The illustrated environment 100 includes a first client device 102, a second client device 104, a content provider system 106, and a service provider system 108 communicatively coupled to each other via a network 110. The computing devices implementing these devices and systems may be configured in a variety of ways.
[0033] For example, the computing device can be configured as a desktop computer, a laptop computer, a mobile device (e.g., assuming a handheld configuration, such as a tablet computer or mobile phone as shown for the first client device and the second client device), etc. Thus, the computing device can range from a full-resource device with large amounts of memory and processor resources (e.g., a personal computer, a game console) to a low-resource device with limited memory and / or processing resources (e.g., a mobile device). In addition, although a single computing device is depicted and described in some cases, the computing device can represent multiple different devices, such as those used by an enterprise to perform "cloud" operations for the content provider system 106 and the service provider system 108, as well as for example, as described with respect to Fig. 9 A plurality of servers are further described.
[0034] The first client device 102 and the second client device 104 are communicatively coupled via the network 110 using respective communication modules 112, 114 to communicate using the service provider system 108 as an intermediary. For example, the illustrated service provider system 108 represents one of several different service provider systems that are configured to support communications between the devices using a platform manager module 116 and a communication platform 118. The platform manager module 116 represents functionality to support such communications via the network 110 using the communication platform 118.
[0035] The communication supported by the communication platform 118 between the first client device 102 and the second client device 104 may be configured in a variety of ways. Examples of configurations for communication include instant messaging, postings, emails, text messages, etc., which may be communicated via various communication platforms 118. Examples of communication platforms 118 include Messages, Instant messages and posts, Images and direct messages, Posts and messages, Instant messaging, Tweets, Photo sharing and bookmarking, Videos and comments and many other communication platforms. In this way, the communications sent and received via the multiple communication platforms 118 available to the first client device 102 and the second client device 104 can support different quantities, orientations and arrangements of digital content from each other.
[0036] In some cases as described above, users may wish to share information about digital content they have found that can be accessed via the network 110. Assume that a user of the first client device 102 interacts with the communication module 112 to access digital content 120 stored in a storage device 124 of the content provider system 106 and managed by a content manager module 122. The digital content 120 can be configured in a variety of ways, such as web pages, digital images, digital audio, digital video and multimedia content, documents, etc., which can be accessed by the content manager module 122 via a network address (e.g., a uniform resource locator).
[0037] In the example shown, the digital content 120 is configured as a web page that includes various different parts, including a search bar, a row of tags, automatically scrolling dynamic digital images, subheadings, etc. A user of the first client device 102 viewing the web page may then wish to make the user of the second client device 104 aware of the web page by sharing a link to the network address of the web page via the communication platform 118.
[0038] As previously described, conventional techniques for generating link previews are performed at a client device or service provider system 108 and are not supported at a content provider system 106. In one conventional example, structured metadata (e.g., "og:title" for titles and "og:image" for images) (e.g., in accordance with the Open Graph protocol) is added to a header portion of a web page to identify digital content items that can be accessed via the web page. The service provider system that is to generate link previews in this conventional example then generates link previews as needed based on the identified digital content items. As a result, no degree of control is given to the content provider system regarding how the service provider system shares digital content as link previews.
[0039] However, in the techniques described herein, even in cases where the service provider system 108 is also configured to generate link previews, the content provider system 106 employs the preview generation module 126 to generate link previews 128, which are then shared by the service provider system 108. Continuing with the previous example, for example, the service provider system 108 may request titles and images based on Open Graph tags (e.g., "og:title" for titles and "og:image" for images). However, in this example, the network address of the "og:image" tag for the digital image causes the preview generation module 126 to generate link previews 128 if the link previews 128 have not yet been generated and are not available via the cache. As a result, link previews 128 may be generated by the content provider system 106 even for service provider systems 108 that attempt to generate link previews themselves, thereby maintaining control of these previews at the content provider system 106.
[0040] The link preview 128 may be customized in a variety of different ways by the preview generation module 126. Examples of customization include customization based on the communication platform 118 via which the link preview 128 is transmitted and viewed. For example, this may be used to account for available resolutions, theme colors, image sizes, and output options of the communication platform 118. This may also be used to select portions of the digital content 120, for example to increase the likelihood of a user interaction initiating a conversion, such as a good or service associated with the digital content 120.
[0041] Other customization examples are also contemplated, such as to address time considerations such as holidays. For example, the link preview 128 can be configured to be interactive to support user interaction before being used to initiate navigation to the corresponding network address as part of initiating the navigation, etc. The link preview 128 can, for example, output an animation in response to detecting a "hover" (e.g., gesture, cursor) on a link, can output a digital video, can include a game or question-and-answer function, etc. In another example, the link preview 128 includes a dynamic display function that can be used in conjunction with the selection of the link preview 128 - for example, as an animation that dynamically expands on digital content that can be accessed via a link, the ability to play digital media including audio and video through interaction with the link preview 128, etc. - to initiate navigation to the network address. In this way, the content provider system 106 can customize the generation of the link preview 128 as needed, including further discussion of it in the following section.
[0042] In general, the functions, features, and concepts described with respect to the examples above and below can be employed in the context of the example processes described in this section. In addition, the functions, features, and concepts described with respect to the different figures and examples in this document can be interchangeable with each other and are not limited to implementation in the context of a particular figure or process. In addition, the boxes associated with the different representative processes and corresponding figures in this document can be applied and / or combined together in different ways. Therefore, the various functions, features, and concepts described with respect to the different example environments, devices, components, figures, and processes in this document can be used in any suitable combination and are not limited to the specific combinations represented by the examples listed in this specification.
[0043] Dynamic link preview generation
[0044] Figure 2 Depicted in more detail shows Figure 1 The system 200 in an example implementation of the operation of the preview generation module 126 in generating the link preview 128. Figure 3 A procedure 300 is depicted in an example implementation in which a link preview is generated based on customized data looked up for the particular platform from which the request originated.
[0045] The following discussion describes techniques that can be implemented using the previously described systems and devices. Aspects of each process can be implemented in hardware, firmware, software, or a combination thereof. The processes are shown as a set of blocks that specify operations performed by one or more devices and are not necessarily limited to the order shown for performing the operations by the respective blocks. In portions of the following discussion, reference will be made to Figures 1 to 6 .
[0046] First, in this example, a first client device 102 interacts with a service provider system 108. The service provider system 108 includes a platform manager module 116 that supports a communication platform 118 through which the first client device 102 can communicate with a second client device 104 via a network 110. The communication platform 118 can support a variety of communications delivered via the network 110 in a variety of ways. Examples of these communications are instant messaging, social network communications (e.g., "shares" or posts), electronic messages, etc. Examples of communication platforms include And also as mentioned above including etc. is supported as part of a social networking system.
[0047] The first client device 102 initiates a link sharing request 202 via the communication module 112 (e.g., a browser, a web-implemented application, etc.), which is transmitted to the service provider system 108. The first client device 102 may, for example, navigate to a network address via a browser or a dedicated application, and wish to "share" digital content accessible at the network address, such as a web page, digital media, etc., via the communication platform 118.
[0048] A user of the first client device 102 may, for example, navigate to a web page and select a "share" feature via the user interface. Selection of the share feature causes the communication module 112 to output a selection of a communication platform 118 through which the user wishes to share a link to the web page, such as via an instant message, a post in a social media service, etc. In response, the communication module 112 transmits a link sharing request 202 to the service provider system 108 that implements the selected communication platform 118.
[0049] The receipt of the link share request 202 by the service provider system 108 causes the platform manager module 116 to access the network address associated with the link share request 202 in order to generate a link preview. For example, the service provider system 108 can be configured to support open graph tags, such as "og:title" for titles and "og:image" for images. The title and image received by the service provider system 108 in response to the request are then used by the service provider system 108 itself in an OG tagging scenario to generate a link preview. However, in this example, the content provider system 106 itself generates the link preview 128, which is then passed to the service provider system 108 for use as a digital image by the client device. As a result, the content provider system 106 controls how the service provider system 108 presents the digital content as part of the link preview 128.
[0050] For example, the content provider system 106 receives, via the network 110, a content request 204 for digital content that can be accessed via a network address (block 302). The content request 204 can, for example, follow the Open Graph tags (e.g., "og:title" for a title and "og:image" for an image) and request a title and an image associated with the network address. For example, the link preview 128 can be obtained by the content provider system 106 using the content request 204 for an image "og:image" rather than simply providing the digital image from a web page. Thus, as further described below, even in the case where the service provider system 108 is configured to generate a link preview, the content provider system 106 can instead generate the preview and pass the preview to the service provider system 108. This gives the content provider system 106 a degree of control in generating the link preview 128 that is not possible using conventional techniques. In another example, the content request 204 requests digital content that can generally be accessed via a network address (e.g., an entire web page).
[0051] Then, the communication platform 118 corresponding to the service provider system 108 that initiated the request is identified (block 304). In the example shown, the content provider system 106 includes a platform identification module 206 that is configured to identify a platform ID 208 based on the content request 204. For example, the content request 204 may include a header that specifies a network domain from which the request originated. Based on the network domain, the platform identification module 206 may determine the communication platform 118 that the service provider system 108 uses to support communications between client devices.
[0052] Then, in the example shown, the platform ID 208 is passed as input from the platform identification module 206 to the custom data module 210. The custom data module 210 represents functionality for looking up custom data 212 from the storage device 214 that corresponds to the identified communication platform 118 of the service provider system 108 (block 306). The custom data 212 may describe, for example, display characteristics, color themes, resolutions, aspect ratios, types of digital content supported, etc. as used by the communication platform 118. As further described below, the custom data 212 may also describe digital content that has successfully initiated a user action via the identified communication platform 118, such as a conversion to a good or service associated with the digital content accessible via a network address and thus serve as digital marketing content (e.g., an advertisement).
[0053] The customization data 212 is passed as input from the customization data module 210 to the preview generation module 126. The preview generation module 126 then generates a link preview 128 of the digital content that can be accessed via the network address based on the customization data 212. The link preview can be selected to cause navigation to the network address to access the digital content (block 308). Continuing with the above example, the content request 204 can include open graph tags (e.g., "og:title" for a title and "og:image" for a digital image) to request a title and image associated with the network address, which are then used by the service provider system 108 itself to generate the link preview 128.
[0054] However, in the illustrated example, the OG tag for the digital image (or title) causes the content provider system 106 to generate a link preview 128 instead, and pass the link preview back to the service provider system 108 as a digital image, which is used by the service provider system 108 to generate the link. To this end, in one example, the digital content lookup module 216 is used to look up the digital content accessible via a network address, such as from a storage device 218. The preview generation module 126 then renders the digital content in a headless browser (e.g., as an HTML page) and captures a screenshot to generate a digital image, such as having the size, resolution, aspect ratio, etc. specified by the customization data 212.
[0055] The captured screenshot is then used by the preview generation module 126 as a link preview 128, which is transmitted by the content provider system 106 via the network 110 for receipt by the service provider system 108 (block 310). In this way, the preview generation module 126 of the content provider system 106 can control how digital content originating from the content provider system 106 is represented as part of the link preview 128 used by the service provider system 108. The link preview 128 can then be delivered by the service provider system 108 to the second client device 104, which can then be received by the second client device 104 in a manner such as Figure 1 A link preview 128 is presented in the illustrated user interface and can be selected to cause the communication module 114 to navigate to the network address and obtain digital content accessible via the network address.
[0056] The above-described dynamic link preview generation technique may be performed in real time upon receiving a content request 204. As a result, this functionality may be available to millions of web pages without the need to generate and store link previews 128 offline. However, in implementations, link previews 128 are cached in a storage device for use in subsequent requests, such as within a limited amount of time, based on past usage, etc. Link previews may also be generated "offline," such as before receiving a content request 204.
[0057] Figure 4 and Figure 5 Respective examples of link previews 400 , 500 generated for different communication platforms 118 are depicted. Figure 4 The link preview 400 is configured for use as a post in a news feed as part of a social networking system. This includes being formatted to be displayed in a generally landscape orientation and selecting a plurality of digital images. However, Figure 5 The link preview 500 is configured to utilize a limited display area to output as an instant message in a vertical orientation. In this way, link previews 400, 500 for the same digital content accessible from the same network address can be generated differently to address the communication platform 118, via which the link preview is transmitted.
[0058] Figure 6 An example implementation 600 is depicted in which a link preview is configured to encourage a user to take an action, such as converting a good or service associated with digital content accessible via a network address to digital marketing content. In this example, the preview generation module 126 is configured to generate the link preview 128 based on a variety of factors to increase the likelihood that a user will take an action when viewing the link preview 128, such as a conversion such as "clicking" on the link, subsequently purchasing a good or service associated with the network address for which the link preview 128 was generated, etc.
[0059] For example, the preview generation module 126 may generate a link preview 602 that includes an offer of "free shipping" and another link preview 604 for "10% off" for the same communication platform 118. As part of an A / B test, the preview generation module 126 may then learn which options perform best in achieving the desired results. As a result, the link previews 128 may support increased functionality and revenue opportunities that are not available using conventional techniques.
[0060] Figure 7 Depicted is system 700 in an example implementation in which a customization data module generates a model for controlling customizations applied to link previews. Figure 8Depicted is a procedure 800 in an example implementation in which a model describing user interactions with a link preview is generated to customize the generation of subsequent link previews. The customization can be based on the user initiating the generation of the link, the user to receive the link, etc.
[0061] The following discussion describes techniques that can be implemented using the previously described systems and devices. Aspects of each process can be implemented in hardware, firmware, software, or a combination thereof. The processes are shown as a set of blocks that specify operations performed by one or more devices and are not necessarily limited to the order shown for performing the operations by the respective blocks. In portions of the following discussion, reference will be made to Figure 7 and Figure 8 .
[0062] First, in this example, user interaction data 702 is received by the customization data module 210, the user interaction data describing user interactions with a link preview and characteristics of the link preview. The link preview is generated based on usage by a corresponding communication platform for previewing digital content accessible via a corresponding network address (block 802). For example, the user interaction data 702 may describe a communication platform 704 for which the link preview was generated, link preview characteristics 706 (e.g., the type of digital image, color, content included in the link preview, etc.), user characteristics 708 (e.g., demographic information such as age, gender, geographic location) of a user interacting with the link preview (e.g., initiating the link preview 128 and / or receiving the link preview 128), an indication 710 of performance of a user action (e.g., whether the link preview resulted in a conversion), etc.
[0063] The user interaction data is then received as input by the model training module 712 to generate a model 714 describing the user interaction with the link preview (block 804). A variety of techniques can be performed. In a first example, the model training module 712 uses the regression analysis module 718 to generate the model 714 using regression analysis. Regression analysis is a statistical technique for estimating the relationship between variables in the user interaction data 702.
[0064] In a second example, the machine learning module 716 is used to train a model using a machine learning technique, in which the user interaction data 702 is used to train the model 714 using a loss function. Models trained using machine learning may include decision trees, support vector machines, linear regression, logistic regression, Bayesian networks, random forest learning, dimensionality reduction algorithms, boosting algorithms, artificial neural networks, deep learning, etc. Therefore, the model 714 trained using machine learning is configured to perform high-level abstraction on data by generating data-driven predictions or decisions based on known input data.
[0065] Once the model 714 is trained, it is passed to the model usage module 720 to generate customization data 212 based on subsequent user interaction data 722 to customize subsequent link previews (box 806). Subsequent user interaction data 722 can, for example, describe the communication platform, link preview characteristics, user characteristics (e.g., sender or receiver), and / or instructions 710 for the performance of user actions. Based on this information, customization data 212 is generated to describe the characteristics of successfully achieving a desired result, such as a conversion of a good or service. In this way, link previews 128 can be configured to increase the richness of link previews 128 using digital marketing techniques, which is not possible in conventional techniques. Customization data 212 can, for example, be based on previous user interactions and then used to customize the generation of subsequent links, such as to increase the likelihood of conversion.
[0066] Example Systems and Devices
[0067] Fig. 9 An example system is shown generally at 900 including an example computing device 902, which represents one or more computing systems and / or devices that may implement the various techniques described herein. This is illustrated by the inclusion of a preview generation module 126. The computing device 902 may be, for example, a server of a service provider, a device associated with a client (e.g., a client device), a system on a chip, and / or any other suitable computing device or computing system.
[0068] The illustrated example computing device 902 includes a processing system 904, one or more computer-readable media 906, and one or more I / O interfaces 908 that are communicatively coupled to one another. Although not shown, the computing device 902 may also include a system bus or other data and command transmission system that couples the various components to one another. The system bus may include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any of a variety of bus architectures. A variety of other examples are also contemplated, such as control lines and data lines.
[0069] Processing system 904 represents the function of performing one or more operations using hardware. Therefore, processing system 904 is shown as including hardware elements 910, which can be configured as processors, functional blocks, etc. This can include other logic devices implemented in hardware as application-specific integrated circuits or formed using one or more semiconductors. Hardware elements 910 are not limited by the materials from which they are formed or the processing mechanisms used therein. For example, a processor may include semiconductors and / or transistors (e.g., electronic integrated circuits (ICs)). In this case, the processor executable instructions may be electronic executable instructions.
[0070] Computer-readable storage media 906 is shown to include memory / storage 912. Memory / storage 912 represents memory / storage capacity associated with one or more computer-readable media. Memory / storage component 912 may include volatile media (e.g., random access memory (RAM)) and / or non-volatile media (e.g., read-only memory (ROM), flash memory, optical disk, magnetic disk, etc.). Memory / storage component 912 may include fixed media (e.g., RAM, ROM, fixed hard disk drive, etc.) and removable media (e.g., flash memory, removable hard disk drive, optical disk, etc.). As further described below, computer-readable media 906 may be configured in a variety of other ways.
[0071] The input / output interface 908 represents functionality that allows a user to input commands and information to the computing device 902, and also allows information to be presented to the user and / or other components or devices using various input / output devices. Examples of input devices include a keyboard, a cursor control device (e.g., a mouse), a microphone, a scanner, a touch function (e.g., a capacitive sensor or other sensor configured to detect physical touch), a camera (e.g., which may employ visible wavelengths or invisible wavelengths such as infrared frequencies to identify movement as gestures that do not involve touch), etc. Examples of output devices include a display device (e.g., a monitor or projector), a speaker, a printer, a network card, a tactile response device, etc. Thus, the computing device 902 may be configured in various ways as further described below to support user interaction.
[0072] Herein, various techniques may be described in the general context of software, hardware elements, or program modules. Typically, such modules include routines, programs, objects, elements, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The terms "module," "function," and "component" as used herein generally represent software, firmware, hardware, or a combination thereof. The features of the techniques described herein are platform-independent, which means that the techniques may be implemented on a variety of commercial computing platforms with a variety of processors.
[0073] An implementation of the described modules and techniques may be stored on or transmitted over some form of computer-readable media. Computer-readable media may include a variety of media that may be accessed by computing device 902. By way of example and not limitation, computer-readable media may include “computer-readable storage media” and “computer-readable signal media”.
[0074] "Computer-readable storage media" may refer to media and / or devices that are capable of storing information persistently and / or non-transiently, as compared to mere signal transmission, carrier waves, or the signal itself. Therefore, computer-readable storage media refers to non-signal bearing media. Computer-readable storage media include the following hardware: volatile and non-volatile, removable and non-removable media and / or storage devices implemented in methods or technologies suitable for storage of information such as computer-readable instructions, data structures, program modules, logic elements / circuits, or other data. Examples of computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage device, hard disk, cassette, magnetic tape, magnetic disk storage device or other magnetic storage device or other storage device, tangible media or an article of manufacture suitable for storing the desired information and accessible by a computer.
[0075] "Computer-readable signal media" may refer to signal-bearing media that is configured to transmit instructions to the hardware of the computing device 902, such as via a network. Signal media may typically present computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, a data signal, or other transport mechanism. Signal media also include any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in a manner that encodes information in the signal. By way of example and not limitation, communication media include wired media such as a wired network or direct wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media.
[0076] As previously described, hardware elements 910 and computer-readable media 906 represent modules, programmable device logic, and / or fixed device logic implemented in hardware that can be employed in some embodiments to implement at least some aspects of the technology described herein (e.g., execute one or more instructions). Hardware can include components of integrated circuits or systems on a chip, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), and other implementations in silicon or other hardware. In this context, hardware can operate as a processing device that performs program tasks defined by the following instructions and / or logic: instructions and / or logic presented by the hardware and hardware for storing execution instructions (e.g., the computer-readable storage medium described previously).
[0077] The aforementioned combination may also be used to implement the various techniques described herein. Therefore, software, hardware or executable modules may be implemented as one or more instructions and / or logic presented on some form of computer-readable storage media and / or presented by one or more hardware elements 910. Computing device 902 may be configured to implement specific instructions and / or functions corresponding to software modules and / or hardware modules. Therefore, the implementation of a module that can be executed as software by computing device 902 may be implemented at least partially in hardware, for example, by using hardware elements 910 and / or computer-readable storage media of processing system 904. Instructions and / or functions may be executed / operated by one or more articles (e.g., one or more computing devices 902 and / or processing system 904) to implement the techniques, modules and examples described herein.
[0078] The technology described herein can be supported by various configurations of computing device 902 and is not limited to the specific examples of the technology described herein. As described below, the functionality can also be implemented in whole or in part on the "cloud" 914 by using a distributed system, for example, via platform 916.
[0079] The cloud 914 includes and / or represents a platform 916 for resources 918. The platform 916 abstracts the underlying functionality of the hardware resources (e.g., servers) and software resources of the cloud 914. The resources 918 may include applications and / or data that may be utilized when performing computer processing on a server remote from the computing device 902. The resources 918 may also include services provided over the Internet and / or through a subscriber network (e.g., a cellular network or a Wi-Fi network).
[0080] The platform 916 may abstract resources and functionality to connect the computing device 902 with other computing devices. The platform 916 may also be used to abstract the scaling of resources to provide corresponding scaling levels to the demand encountered for resources 918 implemented via the platform 916. Thus, in an interconnected device implementation, the implementation of the functionality described herein may be distributed throughout the system 900. For example, the functionality may be implemented in part on the computing device 902 and may be implemented via the platform 916 that abstracts the functionality of the cloud 914.
[0081] in conclusion
[0082] Although the invention has been described in language specific to structural features and / or methodological acts, it should be understood that the invention defined in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as example forms of implementing the claimed invention.
Claims
1. A method implemented by at least one computing device of a content provider system, the content provider system comprising a storage device storing digital content accessible via a network address, the method comprising: receiving, by the at least one computing device via a network, a request for the digital content from a service provider system including a communication platform; identifying, by the at least one computing device, the communications platform of the service provider system that initiated the request; searching, by the at least one computing device, for customization data corresponding to the communication platform of the service provider system based on the identified communication platform; generating, by the at least one computing device, a link preview of the digital content accessible via the network address based on the found customization data; as well as The link preview is transmitted by the at least one computing device via the network for receipt by the service provider system, the link preview being selectable to cause navigation to the network address to access the digital content.
2. The method according to claim 1, wherein: The request is initiated by the service provider system in response to input received by the service provider system from a first client device to share the network address in communications with a second client device via the communications platform.
3. The method according to claim 1, wherein: The identification is based on an identifier of a network domain from which the request originated.
4. The method according to claim 1, wherein: The customization data describes the dimensions to be used to generate the link preview.
5. The method according to claim 1, wherein: The customization data describes which digital images of a plurality of digital images included as part of the digital content are to be included in the link preview.
6. The method according to claim 1, wherein: The digital content is a web page, and the service provider system implements a social network via which the link preview is shared.
7. The method according to claim 1, wherein: The network address is presented as a digital image included as part of a web page.
8. The method according to claim 1, wherein: The customization data for the identified communication platform identifies a portion of the digital content for inclusion in the link preview based on a likelihood of causing selection of the link preview to result in navigation to the network address.
9. The method according to claim 1, wherein: The customization data for the identified communication platform identifies a portion of the digital content for inclusion in the link preview based on a likelihood of resulting in a conversion for a good or service associated with the digital content.
10. The method according to claim 1, wherein: The customized data for the identified communication platform is based on machine learning, using a model trained based on previous link previews generated for the identified communication platform to identify a portion of the digital content for inclusion in the link preview.
11. The method according to claim 1, wherein: The generating of the link preview includes rendering the digital content having a size based on the customization data.
12. The method according to claim 1, wherein: The network address is configured as a uniform resource locator (URL).
13. The method according to claim 1, wherein: The customization data causes a link preview generated for a first said identified communications platform to differ from a link preview generated for a second said identified communications platform.
14. A method implemented by at least one computing device of a content provider system, the method comprising: receiving, by the at least one computing device, data describing user interactions with a link preview and characteristics of the link preview, the link preview generated based on usage of a communication platform of a corresponding service provider system for previewing digital content accessible via a corresponding network address; generating, by the at least one computing device, a model describing user interactions with the link preview; as well as customizing, by the at least one computing device, generation of subsequent link previews based on the generated model; wherein the data describes conversions of goods or services associated with the digital content, and the model is used to customize the generation of subsequent link previews to increase the likelihood of conversions.
15. The method according to claim 14, wherein: The generation of the model is performed using machine learning.
16. The method according to claim 14, wherein: The generation of the model was performed using regression analysis.
17. A content provider system, comprising: Processing systems; as well as A computer-readable storage medium having a plurality of digital contents accessible via corresponding network addresses and having stored thereon instructions that, in response to execution by the processing system, cause the processing system to perform operations comprising: receiving, via a network, a request from a service provider system including a communication platform for a digital content item from the plurality of digital content items, the digital content item being accessible via a corresponding said network address; generating a link preview of the digital content item accessible via the corresponding network address using customization data, the customization data being based on a model configured to associate conversion of a good or service associated with digital content with the digital content item; and The generated link preview is transmitted via the network for receipt by an originator of the request, the link preview being selectable to cause navigation to the network address to access the digital content.
18. The content provider system according to claim 17, wherein: The customized data is based on demographic data of a user initiating the request.
19. The content provider system according to claim 17, further comprising: a communications platform of the service provider system identifying an originator of the request; as well as The customization data is looked up based on the identified communication platform.
