JP6505200B2 - Automated click type selection for content performance optimization - Google Patents

Description

  In computerized content distribution networks, content providers typically design content items (eg, advertisements) and provide them to content servers. A content server then delivers content items to various client devices via one or more content slots of the electronic resource. Content items often include images, videos, graphics, text, and / or other visual features. It can be difficult and challenging for content providers to generate effective and attractive content items.

  One implementation of the present disclosure is a method for optimizing the performance of content using click types. The method includes receiving, at processing circuitry, a request for a content item to be presented on a client device. The request includes an indication of the serving context for the content item. The method includes a click type performance model for the content item and a serving context to calculate, by the processing circuitry, a metric of the predicted performance of the content item for a plurality of different potential click types. The method further includes the step of using Each of the potential click types defines different criteria for triggering an event to be performed in response to the user's interaction with the content item when the defined criteria are met. The method further includes selecting one of the potential click types by the processing circuit based on the expected performance metric, and generating a content item having the selected click type. Content items are generated by processing circuitry in response to a request. The method further includes the step of providing the generated content item for presentation on the client device.

  In some implementations, the method collects and stores event data indicating user actions associated with content items having each of the potential click types and trains the click data type performance model And using as feedback for.

  In some implementations, the different criteria defined by the potential click type include different types of user interaction with the content item. In some implementations, each of the potential click types defines different criteria for calculating a performance metric.

  In some implementations, selecting one of the potential click types includes selecting a button click type. When the button click type is selected, the method causes the event as the user's interaction with the first part of the content item excluding the user's interaction with the second part of the content item distinct from the first part. The method may further include the steps of defining criteria for triggering and rendering a clickable button occupying only the first part of the content item.

  In some implementations, selecting one of the potential click types includes selecting an entire content item click type. When the entire content item click type is selected, the method defines the criteria for triggering the event as the user's interaction with any part of the content item, and the clickable element across the display area of the content item And R. as rendering.

  In some implementations, selecting one of the potential click types includes selecting a confirmation click type. When the confirmation click type is selected, the method displays a confirmation prompt in response to the first user interaction with the content item, and the confirmation prompt is displayed after the first user interaction And D. defining the criteria for triggering the event as a second user interaction with the content item occurring in between.

  In some implementations, the context of service provision includes at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association.

  In some implementations, selecting one of the potential click types includes selecting the click type associated with the extremum of the expected performance metric for the potential click type .

  In some implementations, the method further includes the step of comparing the predicted performance metric to a threshold. Selecting one of the potential click types comprises selecting the first of the potential click types if the predicted performance metric is below a threshold, and predicting Selecting a second click type of the potential click types if the performance metric being performed is greater than or equal to a threshold.

  Another implementation of the present disclosure is a system for optimizing content performance using click types. The system includes processing circuitry having a processor and a memory. The processing circuitry is configured to receive a request for a content item for presentation on a client device. The request includes an indication of the context of service provision for the content item. The processing circuitry is further configured to use the click type performance model and the serving context for the content item to calculate a metric of the predicted performance of the content item for a plurality of different potential click types. . Each of the potential click types defines different criteria for triggering an event to be performed in response to the user's interaction with the content item when the defined criteria are met. The processing circuitry selects one of the potential click types based on the expected performance metric, generates a content item having the selected click type in response to the request, and on the client device It is further configured to provide the generated content item for presentation.

  In some implementations, the processing circuitry collects and stores event data indicating user actions associated with content items having each of the potential click types, and trains the event data for click type performance models Configured to be used as feedback.

  In some implementations, the different criteria defined by the potential click type include different types of user interaction with the content item. In some implementations, each of the potential click types defines different criteria for calculating a performance metric.

  In some implementations, selecting one of the potential click types includes selecting a button click type. When the button click type is selected, the processing circuitry events the user interaction with the first portion of the content item excluding the user interaction with the second portion of the content item distinct from the first portion. And may be configured to render clickable buttons that occupy only a first portion of the content item.

  In some implementations, selecting one of the potential click types includes selecting an entire content item click type. When the entire content item click type is selected, the processing circuitry defines the criteria for triggering the event as user interaction with any part of the content item, as a clickable element across the content item display area It may be configured to render.

  In some implementations, selecting one of the potential click types includes selecting a confirmation click type. When the confirmation click type is selected, the processing circuitry configures the content item to cause the confirmation prompt to be displayed in response to the first user interaction with the content item, and after the first user interaction, the confirmation The criteria may be configured to trigger an event as a second user interaction with the content item that occurs while the prompt is displayed.

  In some implementations, the context of service provision includes at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association.

  In some implementations, selecting one of the potential click types includes the click type associated with the extremum of the expected performance metric for the potential click type.

  In some implementations, the processing circuit is configured to compare the predicted performance metric to a threshold. Selecting one of the potential click types involves selecting the first of the potential click types when the predicted performance metric is below the threshold, and predicting Selecting a second click type of the potential click types if the performance metric being performed is greater than or equal to a threshold.

  Another implementation of the present disclosure is a method for optimizing content performance using creative extensions. The method includes receiving, at processing circuitry, a request for a content item to be presented on a client device. The request includes an indication of the context of service provision for the content item. The method includes a creative extension performance model and a serving context for the content item to calculate, by the processing circuitry, a metric of the predicted performance of the content item with respect to a plurality of different potential creative extensions. The method further includes the step of using Each of the potential creative extensions defines different actions to be taken in response to the user's interaction with the content item. The method further includes selecting one of the potential creative extensions by the processing circuit based on the expected performance metric, and generating a content item having the selected creative extension. Content items are generated by processing circuitry in response to a request. The method further includes the step of providing the generated content item for presentation on the client device.

  In some implementations, the method collects and stores event data indicating user actions associated with content items having each of the potential creative extensions, and trains the event data into a creative extension performance model And using as feedback for.

  In some implementations, the method includes extracting data assets from at least one of a landing resource associated with the content item, a secondary resource associated with the landing resource, and a customer information database. The method may include using the extracted data asset to determine which of the potential creative extensions may be utilized for selection. In some implementations, using the extracted data assets to determine which of the potential creative extensions may be used for selection is required to generate the creative extensions In response to the steps of identifying data assets, determining whether the identified data assets have been extracted, and determining that the required data assets have not been extracted, the creative extension is used for selection Determining that it can not be done.

  In some implementations, selecting one of the potential creative extensions may use the serving context for the content item such that any of the potential creative extensions may be selected for selection Including the step of determining

  In some implementations, selecting one of the potential creative extensions includes selecting a click-to-call extension. When the click to call extension is selected, the method generates a creative extension configured to initiate communication with the subject associated with the content item using the extracted contact information; Rendering the rendered creative as a selectable element of the content item.

  In some implementations, selecting one of the potential creative extensions includes selecting a position extension. When the location extension is selected, the method uses the extracted location information to launch a map application or generate a creative extension configured to display the geographic location associated with the content item And rendering the generated creative extension as a selectable item of content item.

  In some implementations, selecting one of the potential creative extensions includes selecting a secondary resource extension. When the secondary resource extension is selected, the method uses the extracted secondary resource information to generate a creative extension configured to cause the client device to navigate to the secondary resource associated with the content item; Rendering the generated creative extension as a selectable item of content item.

  In some implementations, selecting one of the potential creative extensions includes selecting a creative extension that is associated with an extremum of the expected performance metric for the potential creative extension. .

  In some implementations, the context of service provision includes at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association.

  Another implementation of the present disclosure is a system for optimizing content performance using creative extensions. The system includes processing circuitry having a processor and a memory. The processing circuitry is configured to receive a request for a content item for presentation on a client device. The request includes an indication of the context of service provision for the content item. The processing circuitry is further configured to use the creative extension performance model and the serving context for the content item to calculate a metric of predicted performance of the content item for the plurality of different potential creative extensions . Each of the potential creative extensions defines different actions to be taken in response to the user's interaction with the content item. The processing circuitry selects one of the potential creative extensions based on the expected performance metric, generates a content item with the selected creative extension in response to the request, and on the client device It is further configured to provide the generated content item for presentation.

  In some implementations, the processing circuitry collects and stores event data indicative of user actions associated with content items having each of the potential creative extensions, and trains the event data into a creative extension performance model. Configured to be used as feedback.

  In some implementations, the processing circuitry is configured to extract data assets from at least one of a landing resource associated with the content item, a secondary resource associated with the landing resource, and a customer information database. Processing circuitry may use the extracted data assets to determine which of the potential creative extensions may be utilized for selection. In some implementations, using the extracted data assets to determine which of the potential creative extensions can be used for selection is required to generate the creative extensions In response to identifying the data asset, determining whether the identified data asset has been extracted, and determining that the required data asset has not been extracted, the creative extension is used for selection Determining that it can not be done.

  In some implementations, selecting one of the potential creative extensions may be used to select any of the potential creative extensions using the serving context for the content item. Including to determine.

  In some implementations, selecting one of the potential creative extensions includes selecting a click-to-call extension. When the click-to-call extension is selected, the processing circuitry generates and generates a creative extension configured to initiate communication with the subject associated with the content item using the extracted contact information. The creative extensions may be configured to render as selectable elements of the content item.

  In some implementations, selecting one of the potential creative extensions includes selecting a position extension. When the location extension is selected, the processing circuitry uses the extracted location information to launch a map application or to create a creative extension configured to display the geographic location associated with the content item. The generated and generated creative extensions may be configured to be rendered as selectable elements of the content item.

  In some implementations, selecting one of the potential creative extensions includes selecting a secondary resource extension. When the secondary resource extension is selected, the processing circuitry uses the extracted secondary resource information to generate and generate a creative extension configured to cause the client device to navigate to the secondary resource associated with the content item. The configured creative extensions may be configured to render as selectable elements of the content item.

  In some implementations, selecting one of the potential creative extensions includes selecting the creative extension that is associated with an extremum of the expected performance metric for the potential creative extension .

  In some implementations, the context of service provision includes at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association.

  The above is an overview, and therefore, includes simplifications, generalizations, and omissions of details, as appropriate. As a result, one of ordinary skill in the art will understand that the summary is merely exemplary and is in no way intended to be limiting. Other aspects of the device and / or process described herein, only as defined by the claims, inventive features and advantages are described in the present specification and will be interpreted in connection with the attached drawings. It will be clear in the explanation.

FIG. 10 is a block diagram of a computer system having a content generation system configured to optimize the performance of content using click types and creative extensions in accordance with the described implementations. FIG. 2 is a block diagram illustrating the content generation system of FIG. 1 training a predictive model for content performance optimization using feedback from client devices according to the described implementation. FIG. 6 is a block diagram illustrating some components of the content generation system of FIG. 1 including a content extractor, a creative selector, a click type selector, and a creative extension selector according to the described implementation. FIG. 5 is a block diagram illustrating the content extractor of FIG. 3 in more detail, according to the described implementation. FIG. 5 is a block diagram illustrating a creative generator that may be used by the creative selector of FIG. 3 to automatically generate a creative using extracted data assets, according to the described implementation. FIG. 5 is a block diagram illustrating the click type selector of FIG. 3 in more detail according to the described implementation. FIG. 5 is a block diagram illustrating the creative extension selector of FIG. 3 in more detail, according to the described implementation. 5 is a flow diagram of a process for optimizing the performance of content using a click type, according to the described implementation. 7 is a flow diagram of a process for optimizing content performance using creative extensions, according to the described implementation.

  Referring generally to the figures, systems and methods for automated content generation and optimization in accordance with various implementations are shown. The systems and methods described herein may be specific content providers, specific resources (eg, web pages), specific platforms (eg, display content, video content, mobile device content, text content, etc.), specific It may be used to automatically generate content items (eg, advertisements) tailored to a profile of interest (eg, a user's set of interests), a particular impression, or any combination thereof. Content items may be generated by the content generation system, provided to the client device, and presented to the user via the client device. The generated content item is (e.g., by embedded hyperlinks) the client device in response to user interaction with the landing resource (e.g., clicking on the content item, hovering over the content item, etc.) Can be configured to guide the landing resource.

  In some implementations, the content generation system extracts data assets from landing resources and / or other related data sources (eg, secondary resources associated with landing resources, separate databases, etc.). The resource from which the data asset is extracted may be defined by the identification of the landing resource. Data assets to be extracted include images, colors, fonts, text, graphics, videos, styles, company related information (eg, geographical location, contact information, etc.), page classification, and / or landing resources. It may include other types of related data. The content generation system uses the extracted data asset to direct landing resources and / or associated secondary resources in response to user interaction with the generated content item (eg, by embedded hyperlinks) Content items may be generated.

  User actions (eg, clicks, conversions, and other types of events) related to the generated content item are logged to optimize the performance of subsequent content items generated by the content generation system It can be used for The performance of the generated content item may be quantified using various performance metrics and / or statistical data derived from logged user actions. One example of such a performance metric is the clickthrough rate (CTR) associated with a content item, a group of content items, or a content delivery campaign. The CTR for content items is the percentage of clicks on content items that lead to conversion (ie

May be defined as A conversion may be any event or user action that meets predetermined conversion criteria (eg, product purchases, user account creation, threshold time spent viewing specific resources, etc.) There is sex.

  In some implementations, content providers are charged for content items based on cost-per-click (CPC). But not all clicks lead to conversions. In a CPC charging system, the CTR for the content item may be correlated with the return on investment (ROI) realized by the content provider. In general, content providers seek to maximize the ROI associated with their content delivery campaigns. One way to maximize the ROI is to optimize the content selection and delivery decisions with the goal of maximizing various performance metrics such as CTR.

  The content generation system described herein may optimize the performance of the content by automatically adjusting various elements, features or attributes of the generated content item. In some implementations, the content generation system uses one or more prediction models to calculate an estimated performance metric for a particular feature or combination of features of the generated content item. The content generation system may use the predictive model to select the best features to include in the generated content item for a particular service provision context. The prediction model is: landing resource ID (eg, URL) or type (eg, page classification), device type (eg, mobile, tablet, desktop etc.), content platform (eg, video, text, image etc.), location of device It may be configured to receive inputs such as the user's interest or context of service delivery and / or other information indicative of available impressions. The predictive model may be used to calculate predicted performance metrics (eg, predicted click rates (pCTRs)) for features of various content items based on the context of a given service provision.

  In some implementations, the content generation system trains a predictive model using logged events and / or statistical data associated with previously generated content items. The logged event data may be used as a feedback signal for the predictive model and may be used to adjust various parameters of the predictive model (eg, using machine learning techniques) there is a possibility. Training the prediction model using actual event data may improve the accuracy of the prediction, as new events are logged (eg, at regular intervals or continuously) It is possible to allow the prediction model to be updated.

  A feature of one content item that can be optimized by a predictive model is the "click type" of the content item. The click type for the content item can affect the layout of the content item, the interactivity of the content item, and / or how the content item is rendered or presented by the client device. In some implementations, the click type for the content item charges the content provider and defines the type of action of the user who is eligible as a "click" for the purpose of calculating the pCTR. The content generation system may select the click type from a plurality of different click types, including “button” click type, “entire content item” click type, and “confirm” click type.

  The button click type may define the click as a user interaction with a particular part of the content item, such as a clickable button or other subset of the total area of the content item. For content items that have a button click type, user interaction with other parts of the content item (eg, parts outside the clickable area) may not cause the client device to navigate to the landing resource, and charging And / or may not qualify as a click for the purpose of calculating performance metrics.

  The entire content item click type may define a click as the user's interaction with any part of the content item. For content items that have a content item overall click type, user interaction with any part of the content item may cause the client device to navigate to the landing resource, and calculate billing and / or performance metrics. It may be eligible as a targeted click.

  The confirmation click type may cause the content item to display a confirmation prompt in response to a first user interaction (e.g., a first click) with the content item. The confirmation prompt may display a message instructing the user to click again to navigate to the landing resource. For content items that have a confirmatory click type, a second user interaction (eg, a second click) with the content item may cause the client device to navigate to the landing resource, and for billing and / or performance It may qualify as a click for the purpose of calculating metrics. Confirmation click types can help protect against unintentional clicks that are unlikely to lead to conversions.

  Another content item feature that may be optimized by the predictive model is the content item's 'creative extension' feature. Creative extensions may be complementary elements of content items other than the main "creative" part. Creative extensions may include click-to-call buttons, "location" buttons, clickable buttons such as "secondary resources" buttons, and / or other types of supplemental content that may be included in the content item. Each creative extension may cause a different action to be taken when the corresponding portion of the content item is clicked.

  A click-to-call button may be included for content items displayed on the mobile communication device when the telephone number or other contact information for the subject associated with the content item is known. Such contact information may be extracted automatically from the landing resource or may be obtained from a separate database. Selecting the click-to-call button may initiate a call or other communication with an entity (eg, a retail store, a customer service phone, a sales agent, etc.) associated with the content item. For other device types (eg, desktop computers, tablets, etc.), click-to-email buttons or more instead of click-to-call buttons when contact information is known A "click-to-contact" button may be included.

  The location button may cause a map to be displayed indicating the geographic location of the company associated with the landing resource. The geographic location of the associated company (e.g., street address, store location, email address, GPS coordinates, etc.) may be extracted from the landing resources, a separate database, or resources associated with the landing resources. Selecting a location button may cause the map application to load (eg, on a mobile device) or may cause the user's web browser to navigate to a map resource (eg, a Google map).

  The secondary resource button may cause the secondary resource to be displayed. Content items may include creative extensions (eg, selectable buttons or links) for portions of multiple different resources or resources (eg, secondary resources, social resources, landing resources, etc.). In some implementations, the content item links only link to secondary resources (not landing resources) and may be referred to as social content items. In other implementations, the content item link links to both the landing resource and the secondary resource.

  Content items generated by the content generation system are provided to client devices via a communication network (e.g., the Internet). Events (eg, impressions, clicks, conversions, etc.) associated with the content item are logged and stored in a database that may be accessed by the content generation system. The content generation system uses the logged events to calculate metrics of performance associated with the content item and to train a predictive model. The content generation system uses a predictive model to estimate which features or combination of features of the content item will lead to optimal content performance for a given serving context (eg CTR, pCTR, or Determine the features that optimize different performance metrics. The content generation system may then automatically generate content items having features estimated to lead to optimal content performance.

  Referring now to FIG. 1, a block diagram of a computer system 100 in accordance with the described implementation is shown. Computer system 100 is shown to include a network 102, a content requestor 104, a resource 106, a client device 108, a resource renderer 110, a data storage device 112, and a content generation system 114.

  Network 102 may include any type of computer network, such as a local area network (LAN), a wide area network (WAN), a cellular network, a satellite network, a wireless network, the Internet, or any other type of data network. Network 102 may include any number of computing devices (eg, computers, servers, routers, network switches, etc.) configured to send, receive, or relay data. Network 102 may further include any number of wired and / or wireless connections. For example, content requestor 104 may communicate wirelessly (eg, via WiFi, cellular, wireless, etc.) with a transceiver wired to the computing devices of network 102 (eg, via a fiber optic cable, CAT5 cable, etc.).

  Network 102 may facilitate communication between content generation system 114 and content requestor 104. Content generation system 114 may receive a content generation request from content requester 104 via network 102. Content generation system 114 may generate content items in response to the request and provide the generated content items to content requestor 104 for review or approval.

  Network 102 may also facilitate communication between content generation system 114, resources 106, and resource renderer 110. Content generation system 114 may receive data assets from resource 106 and / or resource renderer 110. Upon receiving a request for content generation, content generation system 114 may invoke resource renderer 110 to obtain (eg, download) data (eg, HTML data, web page data, etc.) from resource 106 and render. The resource renderer 110 may receive data from the resource 106 via the network 102 and render such data as a snapshot image (eg, a visual representation of the resource 106) and / or as a document object model (DOM) tree . The rendered data may be transmitted from the resource renderer 110 to the content generation system 114 via the network 102.

  With continuing reference to FIG. 1, computer system 100 is shown to include content requestor 104. Content requestor 104 may include one or more principals for which a request to generate a content item is received. For example, the content requestor 104 may include an advertiser, an advertising agency, a third party content provider, a publisher, a website provider, or any other entity for which a request to generate a content item may be received. There is.

  In some implementations, the content requestor 104 includes one or more electronic devices (eg, computers, computer systems, servers, etc.) that can send requests for content generation. Content requestor 104 may include a user input device (e.g., a keyboard, a mouse, a microphone, a touch screen, a tablet, a smartphone, etc.) that allows the user to input a content generation request. Content requestor 104 may send a content generation request to content generation system 114 via network 102. In some implementations, the content generation request includes a uniform resource locator (URL). The URL may specify the location of a particular landing resource (e.g., one of the resources 106).

  In some implementations, content requester 104 sends campaign parameters to content generation system 114. Campaign parameters may be used to control the delivery of content items generated by content generation system 114. The campaign parameters may be keywords to content items, bids corresponding to the keywords, budgets for content delivery, geographic limiters, or content generation system 114, or content items may be presented to client device 108 It may include other criteria used by a separate content server to determine which.

  Content requestor 104 may access content generation system 114 to monitor the performance of the content item delivered in accordance with the established campaign parameters. For example, content requestor 104 may access content generation system 114 to review one or more performance metrics associated with the content item or set of content items. Performance metrics may indicate interactions (eg, CTR, number of impressions, number of clicks, number of conversions, amount spent, etc.) between client devices 108 associated with the content item or set of content items to be delivered. Performance metrics may be based on user actions logged and processed by an accounting system or log file processing system.

  With continuing reference to FIG. 1, computer system 100 is shown to include resources 106. Resources 106 may include any type of information or data structure that may be provided via network 102. In some implementations, the resource 106 may be identified by a resource address, such as a uniform resource locator (URL). Resources 106 may be web pages (eg, HTML web pages, PHP web pages, etc.), word processing documents, portable document format (PDF) documents, images, videos, programming elements, interactive content, streaming video / audio sources, or other May contain some type of electronic information.

  Resources 106 may include local resources, intranet resources, Internet resources, or other network resources. In some implementations, the resource 106 is one or more to which the client device 108 is directed (e.g., by embedded hyperlinks) when the client device 108 interacts with the content item generated by the content generation system 114. Including web pages. In some implementations, resources 106 provide additional information about products, services, or companies that are specifically marketed within the generated content item. For example, resource 106 may be a web page or web site where products or services specifically marketed within the generated content item may be purchased.

  Resources 106 may include landing resources and / or secondary resources. In some implementations, the landing resource is specified by the content requestor 104 as part of a request to generate a content item. The landing resource may be designated as a URL that leads to one of the resources 106 or otherwise specifies the location of the landing resource. The URL of the landing resource may be included as part of the content generation request. Secondary resources may be associated with designated landing resources. Secondary resources may include any type of resource 106 (eg, web pages, websites, word processing documents, videos, PDF documents, etc.) and may be associated with a primary landing resource. In various implementations, the association between the landing resource and the secondary resource may be data assets extracted from the landing resource (eg, a hyperlink linking the landing resource to the secondary resource) and / or (eg, the data storage device 112 May be identified and / or generated using the previously stored association between the landing resource and the secondary resource. In some implementations, content generation system 114 accesses data storage device 112 to identify a secondary resource associated with the designated landing resource.

  In some implementations, resources 106 may be combined with content requestors 104. For example, resources 106 may include data stored on one or more electronic devices (eg, computers, servers, etc.) maintained by content requestor 104. In other implementations, resource 106 may be separate from content requester 104. For example, resource 106 may be a remote server (eg, FTP server, file sharing server, web server, etc.), a combination of servers (eg, data center, cloud computing platform, etc.), or other data separate from content requestor 104 It may include data stored on the storage device.

  With continuing reference to FIG. 1, computer system 100 is shown to include client device 108. Client device 108 may include any number and / or type of user operable electronic devices. For example, client device 108 interacts with a desktop computer, laptop computer, smart phone, tablet, mobile communication device, remote workstation, client terminal, entertainment console, or other components of computer system 100 (eg, via a communication interface) Can include any other device that can. Client device 108 may be able to receive resource content from resource 106 and / or third party content items generated by content generation system 114. Client devices 108 may include mobile devices or non-mobile devices.

  In some implementations, the client device 108 is an application (e.g., a web browser, a resource renderer, etc.) for converting electronic content into a format (e.g., visual, audible, graphical, etc.) that the user can understand. )including. The client device 108 facilitates presenting the content to the user, receiving user input, or user interaction with the electronic content (eg, clicking on the content item, hovering over the content item, etc.) User interface elements (eg, electronic displays, speakers, keyboards, mice, microphones, printers, etc.). The client device 108 may act as a user agent to allow the user to view HTML encoded content.

  Client device 108 may include a processor capable of processing embedded information (eg, meta information embedded in hyperlinks, etc.) and executing embedded instructions. The embedded instructions may include computer readable instructions (eg, software code, JavaScript, ECMAScript, etc.) associated with the content slot in which the third party content item is presented.

  In some implementations, the client device 108 can detect interactions with the delivered content item. Interaction with the content item may be displaying the content item, hovering over the content item, clicking the content item, viewing source information about the content item, or between the client device 108 and the content item It may include any other type of interaction. Interaction with content items does not require an explicit action by the user for a particular content item. In some implementations, an impression (eg, displaying or presenting a content item) may qualify as an interaction. The criteria for defining which user actions (e.g. active or passive) qualify as interactions are determined individually by the content requester 104 or the content generation system 114 (e.g. for each content item) There is a possibility of

  The client device 108 may generate event data indicating the user's action on the content item. For example, client device 108 may generate event data in response to a detected interaction with a content item. The event data may include multiple attributes including content identifier (eg, content ID or signature element), device identifier, reference URL identifier, timestamp, or any other attribute indicating an interaction. In some implementations, the event data is indicative of a serving context (eg, device type, platform, etc.) and one or more attributes of the content item provided (eg, click type, creative extension, etc.) Including instructions. The client device 108 may generate event data when certain actions (eg, viewing resources, purchasing online, sending a search query, etc.) are performed by the client device. Event data generated by client device 108 may be communicated to content generation system 114 or a separate accounting system. Content generation system 114 may use event data to train a predictive model to optimize the performance of the content.

  With regard to the circumstances under which the system discussed herein may collect personal information about the user or may utilize personal information, the user may program or feature user information (eg, the user's social network, social actions or activities). Control whether to collect information about the user's occupation, user preferences, or current position of the user, or whether content that may be more relevant to the user should be received from the content server and / or You may be given the opportunity to control how it should be received. Furthermore, certain data may be processed in one or more ways (e.g., by the content generation system 114) before being stored or used such that personally identifiable information may be deleted. There is. For example, if the user's identification information can not determine personally identifiable information about the user, or if location information is obtained, the user's geographical location (by the level of the city, zip code or state) Etc.) and thus may be processed such that the user's particular position can not be determined. Thus, the user may be able to control how the information is collected (eg, by the application, by the client device 108, etc.) and used by the content generation system 114.

  With continuing reference to FIG. 1, computer system 100 is shown to include a resource renderer 110. Resource renderer 110 may be a hardware or software component capable of interpreting resource 106 and generating a rendered representation of that resource 106 (eg, an image, a display, etc.). For example, resources 106 may include marked up content (eg, HTML, XML, image URL (image URL), etc.) and formatting information (eg, CSS, XSL, etc.). The resource renderer 110 may download the marked up content and format information and render the resource 106 according to the World Wide Web Consortium (W3C) standard. The resource renderer 110 may generate a “snapshot image” of the resource 106 and / or build a document object model (DOM) tree that represents the resource 106.

  The snapshot image may be a visual representation of a particular landing resource. The snapshot image may show the appearance of landing resources presented on a user interface device (e.g., an electronic display screen, computer monitor, touch display, etc.) after rendering the landing resources. The snapshot image may include color information (eg, pixel color, intensity, saturation, etc.) and style information (eg, right angle corners, rounded edges, modern, rustic, etc.) regarding the landing resources. In some implementations, the snapshot image may be an image file with any viable file extension (eg, .jpg, .png, .bmp, etc.).

  The DOM tree may be a hierarchical model of a particular landing resource. The DOM tree may identify multiple data assets of landing resources. The DOM tree contains image information related to landing resources (eg, image URL, display position, display size, alternative text, etc.), font information (eg, font name, size, effects etc.), color information (eg, RGB color values, Can include hex color codes, etc., and text information. The DOM tree may include directly invisible data assets (e.g., metadata, hyperlink URLs, object attributes, etc.) in the snapshot image. Resource renderer 110 may generate a rendered representation of the landing resource, including all of the landing resource's data assets. Data assets may be provided to content generation system 114 as features of nodes and / or snapshot images of a DOM tree.

  In various implementations, resource renderer 110 may be part of content generation system 114, client device 108, or a separate component. Resource renderer 110 may prepare snapshot images and / or DOM trees in response to rendering requests from content generation system 114. Resource renderer 110 may send the snapshot image and / or the DOM tree to content generation system 114 in response to the rendering request.

  With continuing reference to FIG. 1, computer system 100 is shown to include data storage device 112. Data storage device 112 may store profile data, content item data, accounting data, or any other type of data used by content generation system 114 or another component of computer system 100. It can be any kind of memory device that can. Data storage device 112 may include any type of non-volatile memory, media, or memory device. For example, data storage device 112 may be a semiconductor memory device (eg, EPROM, EEPROM, flash memory device, etc.), a magnetic disk (eg, internal hard disk, removable disk, etc.), a magneto-optical disk, and / or a CD ROM and DVD. -May contain ROM disks.

  In some implementations, data storage device 112 is local to content generation system 114, resource 106, or content requestor 104. In other implementations, data storage device 112 is a remote data storage device connected to content generation system 114 and / or content requestor 104 via network 102. In some implementations, data storage device 112 is part of a data storage server or system that can receive queries from content generation system 114 and / or content requestor 104 and respond to the queries.

  In some implementations, data storage device 112 stores data assets extracted from resources 106. For example, data storage device 112 may store image data for various images displayed on resource 106. The image data may include the actual image (e.g., an image file), the URL location of the image, the attributes of the image, the metadata of the image, or other attributes of the image displayed on the resource 106. Data storage device 112 stores text data, color data, style data, video data, layout data, classification data, and / or other types of data extracted from resource 106 or obtained from other data sources. there is a possibility. Data assets may be stored on data storage device 112 in association with resource identifiers. The resource identifier may indicate the resource from which the data asset was extracted or the resource to which the data asset relates.

  In some implementations, data storage device 112 stores an association between landing resources and secondary resources (eg, in a database, in a data table, etc.). Content generation system 114 may access data storage device 112 to identify secondary resources associated with the designated landing resources. Data storage device 112 may store the URL of a particular social networking resource (eg, a Google+ page) associated with the designated landing resource. In some implementations, data storage device 112 stores branding information associated with resource 106. Data storage device 112 may store a knowledge base that includes semantic information gathered from a wide variety of sources (eg, Google Knowledge Graph). The knowledge base may provide structured detailed information about the various landing resources in addition to the list of links to other resources associated with the landing resources.

  Data storage device 112 may store previous content items used in connection with content requestor 104. The previous content item may be a content item provided by content requester 104, a content item generated by content generation system 114 for content requester 104, an image previously used or approved by content requester 104, and / or May contain other components of the generated content item. Data storage device 112 may include an image on a page extracted from resource 106, an image previously used or approved by content requestor 104, and / or other not extracted from resource 106 or otherwise approved by content requestor 104. It may be an image repository for images of.

  In some implementations, data storage device 112 stores event data, statistical data, or performance data regarding content items provided to client device 108. Event data may be indicative of the service delivery context (eg, device type, platform, etc.) and indication of one or more attributes of the provided content item (eg, click type, creative extensions, etc.), and / or provided. May include user behavior (eg, clicks, conversions, etc.) associated with the content item being The statistical data may include statistics (eg, total number of clicks, total number of conversions) based on event data for various content items or groups of content items. Statistical data may indicate the performance of a content item having a particular feature or set of features in a given service provision context. Performance data may include performance metrics (eg, CTR) calculated based on event data and / or statistical data for content items or groups of content items.

  With continuing reference to FIG. 1, computer system 100 is shown to include a content generation system 114. Content generation system 114 may be configured to extract data assets (eg, images, colors, text, fonts, styles, etc.) from resources 106. Content generation system 114 processes the extracted data assets to generate additional data assets (eg, generate behavioral reminder text based on web page classifications) and / or additional data assets May identify secondary resources that may be obtained. The content generation system 114 processes the extracted data assets (eg, cropping the image, identifying high contrast color schemes, generating text snippets from extracted text, etc.), and within the generated content item Various data assets may be selected for use.

  Content generation system 114 may generate a content item that includes the selected data asset. In some implementations, content generation system 114 generates content items in a variety of different formats (eg, video, display, text, etc.) and stores content items in each format. Content generation system 114 may provide content requester 104 with the highest scoring content item for approval and / or store the content item for subsequent delivery to client device 108. Content generation system 114 is described in more detail with reference to FIGS.

  Referring now to FIG. 2, a closed loop system 200 for optimizing the performance of content according to the described implementation is shown. System 200 is shown to include content generation system 114 and client device 108. Content generation system 114 may receive content request 202 from a remote system or device. In various implementations, content request 202 may be received from content requester 104, content server, real-time bidding system, or client device 108. Content request 202 may be received from client device 108 as part of an online content provision process (eg, a request for an advertisement to display on a web page). The content request 202 may be a device type, platform, location of the device at which the content is presented, current time, category of interest associated with the client device, ID or category of the resource at which the content is presented, or a specific impression and And / or may include an indication of a particular service provisioning context, such as other attributes of the service provisioning context.

  Content generation system 114 is shown to receive event data 204 from event log database 208. In various implementations, event data 204 may be received from event log database 208, from a log file processing system, or directly from client device 108. Event data 204 may indicate the behavior of client device 108 associated with the content item previously provided to client device 108. Content generation system 114 may use event data 204 to train one or more content performance prediction models 206. Content performance prediction model 206 may be configured to predict the performance of a feature or combination of features potentially included in a content item generated for a given service delivery context.

  Content generation system 114 uses prediction model 206 to select specific features or combinations of features that are estimated to lead to optimal content performance (eg, features that maximize performance metrics such as pCTR) It can. In some implementations, content generation system 114 uses predictive model 206 to generate or select creative 212, click type 214, and / or creative extension 216. Generating the creatives 212 may include extracting data assets from the landing resources, and using the selected data assets to generate creatives tailored to the landing resources. The generation of creatives is described in more detail with reference to FIGS.

  Selecting the click type 214 may be performed using the prediction model 206 to estimate the performance of the content item having various click type attributes (eg, button click type, entire content item click type, confirmation click type, etc.) It may include calculating a metric (eg, pCTR). Content generation system 114 may select click type 214 from a plurality of potential click types based on the estimated performance metric. In some implementations, the content generation system 114 selects a click type 214 that optimizes the calculated performance metrics for the particular service delivery context.

  Selecting creative extension 216 determines which of a plurality of creative extensions (eg, click-to-call button, location button, secondary resource button, etc.) are available for content request 202 May be included. The availability of creative extensions 216 may vary based on the content request 202 and the particular service delivery context. For example, a click-to-call button may be available when the client device 108 is a mobile device (eg, a smart phone), but may not be available when the client device 108 is a desktop client. Content generation system 114 may generate creative extensions using information extracted from landing resources and / or other databases regarding content items (eg, company contact information, company location, etc.).

  Content generation system 114 may generate content item 210 having features selected for optimization of the performance of the content. Content item 210 is shown to include a selected creative 212, a selected click type 214, and a selected creative extension 216. Content generation system 114 may deliver content item 210 to client device 108 for presentation to a user. The user's actions associated with content item 210 may generate event data 204 stored in event log database 208 for use in further training prediction model 206.

  Closed loop system 200 allows event data 204 to be used as feedback to train and / or update predictive model 206. Training the prediction model 206 using event data 204 may increase the accuracy of the prediction, and the prediction model 206 may (e.g., at regular intervals or continue) as new events are logged. ) May be able to be updated.

  Referring now to FIG. 3, the content generation system 114 according to the described implementation is shown in more detail. Content generation system 114 is shown to include processing circuitry 302 having processor 304 and memory 306. Processor 304 may be a general purpose processor, an application specific integrated circuit (ASIC), one or more field programmable gate arrays (FPGAs), a CPU, a GPU, a group of processing components, or other suitable electronic processing components. May be implemented as

  Memory 306 may be one or more devices (eg, RAMs) for storing data and / or computer code for completing and / or facilitating the various processes, layers and modules described in this disclosure. , ROM, flash memory, hard disk storage, etc.). Memory 306 may include volatile memory or non-volatile memory. Memory 306 may include the structure of database components, object code components, script components, or any other type of information to support the various activities and information structures described in this disclosure. In some implementations, memory 306 is communicatively coupled to processor 304 via processing circuitry 302 and is computer code (eg, for performing one or more processes described herein). , Data module stored in the memory 306).

  Continuing to refer to FIG. 3, memory 306 is shown to include content extractor 308, creative selector 310, click type selector 312, and creative extension selector 314. Content extractor 308 and selectors 310-314 may be modules of content generation system 114 (e.g., in memory 306). In various implementations, content generation system 114 may be a single system or device (as shown in FIG. 3) or may be distributed across multiple systems or devices. In a distributed implementation, the functions of content extractor 308, creative selector 310, click type selector 312, and creative extension selector 314 may be performed by a plurality of different systems or devices configured to communicate via network 102. There is a possibility.

  In some implementations, the content extractor 308 is configured to be run once per creative. Content extractor 308 identifies and extracts information that may be used to select or generate creatives (eg, by creative selector 310) or to select or generate creative extensions (eg, by creative extension selector 314) there is a possibility. Content extractor 308 may be performed prior to service delivery time to build a library of data assets and / or information that may be selected later for inclusion in content item 210. Content extracted by content extractor 308 may determine what type of creative extension may be used for selection. Click type selector 312 and creative extension selector 314 may be configured to provide the appropriate click type and / or creative extension for inclusion in the generated content item 210 at service time (ie, in response to content request 202). It may be implemented. The click type selector 312 and the creative extension selector 314 may select the click type and the creative extension based primarily on the service delivery context.

  Content extractor 308 may be configured to extract data assets from various data sources for use in generating content item 210. The resource from which the data asset is extracted may be defined by the identification of the landing resource. Data assets to be extracted include images, colors, fonts, texts, graphics, videos, styles, company related information (eg, geographic location, contact information, etc.), page classification, and / or landing resources 318 May include other types of data related to

  Content extractor 308 may extract data assets from landing resource 318, secondary resource 320 associated with landing resource 318, and / or customer information database 322. In some implementations, landing resource 318 is one of resources 106. Landing resource 318 may be defined as a resource to which client device 108 is directed by content item 210. Secondary resources 320 can be any type of resource (eg, web pages, websites, word processing documents, videos, PDF documents, etc.) and can be associated with landing resources 318. In some implementations, secondary resources 320 are social networking resources, such as Google+ pages associated with landing resources 318.

  Customer information database 322 may store various types of information regarding landing resources 318 and / or content requestors 104. For example, customer information database 322 may provide information that may be used to generate a creative extension for inclusion in content item 210. In some implementations, customer information database 322 may include company contact information (e.g., phone number, email address, etc.), geographical location of company, type of goods or services offered by company, company's Information associated with the company, such as classification or other types of information that may be included in the content item 210, is stored.

  In some implementations, content extractor 308 includes rendered resources configured to generate rendered representations of landing resources 318 and / or secondary resources 320. The rendered representation may be a Document Object Model (DOM) tree or snapshot image that identifies various data assets extracted by the content extractor 308. Content extractor 308 is described in more detail with reference to FIG.

  Still referring to FIG. 3, data assets extracted by content extractor 308 may be provided to creative selector 310, click type selector 312, and creative extension selector 314. Creative selector 310 may be configured to select or generate creative 212 for use in content item 210. In various implementations, the creative selector 310 selects a previously generated creative from the creative database 316 or uses the creative generator 324 to generate a new creative. Creative generator 324 customizes to landing resource 318 for presentation on client device 108 using the data asset extracted by content extractor 308 and / or the service delivery context provided by content request 202 The creative to be Creative generator 324 is described in more detail with reference to FIG.

  Continuing to refer to FIG. 3, memory 306 is shown to include click type selector 312. Click type selector 312 may be configured to select click type 214 for use in content item 210. The click type 214 may be an attribute of the content item 210 or a snippet of code embedded in the content item 210. Click type 214 may affect the layout of content item 210, the interactivity of content item 210, and / or the manner in which content item 210 is rendered or presented by client device 108. In some implementations, the click type 214 charges the content provider and defines the type of action of the user who is eligible as a "click" for the purpose of calculating performance metrics such as CTR. Click type selector 312 may select click type 214 from a plurality of potential click types, including “button” click types, “entire content item” click types, and “confirm” click types.

  The button click type may define the click as a user interaction with a particular part of the content item 210, such as a clickable button or other subset of the total area of the content item 210. If content item 210 has a button click type, the user's interaction with other parts of content item 210 (e.g., parts outside the clickable area) may not cause client device 108 to navigate to landing resource 318 And may not qualify as a click for the purpose of calculating billing and / or performance metrics.

  The entire content item click type may define the click as user interaction with any part of the content item 210. If the content item 210 has the entire content item click type, user interaction with any part of the content item 210 may cause the client device 108 to navigate to the landing resource 318 and measure billing and / or performance. It may qualify as a click for the purpose of calculating the criteria.

  The confirmation click type may cause the content item 210 to display a confirmation prompt in response to a first user interaction (eg, a first click) with the content item 210. The confirmation prompt may display a message instructing the user to click again to navigate to the landing resource 318. If content item 210 has a confirmation click type, a second user interaction (eg, a second click) with content item 210 may cause client device 108 to navigate to landing resource 318, charging and It may qualify as a click for the purpose of calculating performance metrics. Confirmation click types can help protect against unintentional clicks that are unlikely to lead to conversions.

  Continuing to refer to FIG. 3, click type selector 312 is shown to include click type performance model 326 and click type model trainer 328. Click type performance model 326 may be configured to predict the performance of content item 210 for each of the potential click types that may be selected by click type selector 312 based on the serving context of content item 210.

  The click type performance model 326 includes landing resource ID (eg, URL) or type (eg, page classification), device type (eg, mobile, tablet, desktop etc.), content platform (eg, video, text, images etc.), It may be configured to receive inputs such as the location of the device, the user's interest, or other information indicative of the particular service delivery context. The click type selector 312 may use the click type performance model 326 to calculate expected performance metrics (eg, pCTR) for various click types based on the serving context of the content item 210. Click type selector 312 may select click type 214 based on metrics of expected performance for various click types.

  Click type model trainer 328 may be configured to access event log database 208 to retrieve event data 204 and / or performance metrics 334. Event data 204 and performance metrics 334 may indicate the performance of content items previously provided to client device 108 (or other client devices). The click type model trainer 328 uses data from the event log database 208 to ensure that the click type performance model 326 provides the click type selector 312 with an accurate prediction of content performance for various click types. The click type performance model 326 may be trained and / or updated. Click type selector 312 is described in more detail with reference to FIG.

  Continuing to refer to FIG. 3, memory 306 is shown to include creative extension selector 314. Creative extension selector 314 may be configured to select a creative extension 216 for use in content item 210. Creative extension 216 may be a complement to content item 210 in addition to main creative 212. Creative extension selector 314 may select creative extensions 216 from the plurality of potential creative extensions based on the serving context for content item 210 and / or the data asset extracted by content extractor 308. In some implementations, potential creative extensions may be clickable buttons such as "click to call" buttons, "location" buttons, "secondary resources" buttons, and / or other types that may be included in the content item. Contains supplementary content of

  The click to call button may be available for selection when the serving context for content item 210 indicates that content item 210 is presented on the mobile communication device. In some implementations, click-to-call buttons may be available for selection when phone numbers or other contact information is extracted by content extractor 308. Contact information may be extracted automatically by the content extractor 308 from the landing resource 318 or customer information database 322. Selecting the click-to-call button may initiate a call or other communication with an entity (eg, a retail store, a customer service phone, a sales agent, etc.) associated with the content item. For other device types (for example, desktop computers, tablets, etc.), when the contact information is known, a "click to email" button or a wider "click to contact" button instead of a click to call button It may be included.

  The location button is selected when the geographic location (eg, a street address, store location, email address, GPS coordinates, etc.) is extracted by the content extractor 308 or when the location of the client device 108 is known. Could be used for Selecting a location button may cause a map to be displayed indicating the extracted geographic location. If the serving context indicates that the content item 210 is presented on a mobile device, selecting the location button may cause the map application or navigation application to load. In some implementations, selecting the location button causes the client device 108 to navigate to a map resource (eg, a Google map).

  The secondary resource button may be used for selection when the identification information of the secondary resource 320 is known. Selecting the secondary resource button may cause the client device 108 to navigate to the secondary resource 320. Content item 210 may include creative extensions (eg, selectable buttons or links) for portions of multiple different resources or resources (eg, secondary resources 320, social resources, landing resources 318, etc.). In some implementations, content item 210 links only to secondary resource 320 (as opposed to landing resource 318) and may be referred to as a social content item. In other implementations, content item 210 links to both landing resource 318 and secondary resource 320.

  Continuing to refer to FIG. 3, creative extension selector 314 is shown to include creative extension performance model 330 and creative extension model trainer 332. Creative extension performance model 330 may be configured to predict the performance of content item 210 for each of the available creative extensions or combinations of creative extensions that may be selected by creative extension selector 314 based on the serving context of content item 210. It can be configured.

  The creative extension performance model 330 includes landing resource ID (eg, URL) or type (eg, page classification), device type (eg, mobile, tablet, desktop etc.), content platform (eg, video, text, image etc.), It may be configured to receive inputs such as the location of the device, the user's interest, or other information indicative of the particular service delivery context. Creative extension selector 314 uses creative extension performance model 330 to calculate predicted performance metrics (eg, pCTR) for various types of creative extensions based on the serving context of content item 210. obtain. Creative extension selector 314 may select a creative extension or combination of creative extensions for content item 210 based on the predicted performance metric.

  Creative extension model trainer 332 may be configured to access event log database 208 to retrieve event data 204 and / or performance metrics 334. Event data 204 and performance metrics 334 may indicate the performance of content items previously provided to client device 108 (or other client devices). The Creative Extension Model Trainer 332 can also use data from the Event Log Database 208 to ensure that the Creative Extension Performance Model 330 provides the Creative Extension Selector 314 with an accurate prediction of the content's performance for various types of creative extensions. The creative extension performance model 330 may be used to train and / or update. Creative extension selector 314 is described in more detail with reference to FIG.

  Referring now to FIG. 4, the content extractor 308 according to the described implementation is shown in more detail. Content extractor 308 is shown to include resource renderer module 402. In some implementations, rendering of resources is performed by the resource renderer module 402 rather than an external resource rendering service (eg, resource renderer 110). The resource renderer module 402 may include the functionality of the resource renderer 110 described with reference to FIG. For example, resource renderer module 402 may be able to interpret resource 106 and generate a representation (eg, an image, a display, etc.) of that resource 106.

  The resource renderer module 402 may identify a particular landing resource using the URL or other indicator provided by the content request 202 as part of the request to generate the content item. The resource renderer module 402 reads and interprets content (eg, HTML, XML, image URL, etc.) and format information (eg, CSS, XSL, etc.) marked up from the landing resource 318 and the secondary resource 320 (eg, Resources 318-320 may be rendered according to the W3C standard. The resource renderer module 402 may generate snapshot images of the resources 318-320 and / or build a DOM tree representing the resources 318-320.

  A snapshot image may be a visual representation of a resource. For example, a snapshot image for landing resource 318 may render the appearance of landing resource 318 presented on a user interface device (eg, an electronic display screen, computer monitor, touch display, etc.) after rendering landing resource 318. There is a possibility to show. The snapshot image may include color information (eg, pixel color, intensity, saturation, etc.) and style information (eg, right angle corners, rounded edges, modern, rustic, etc.) for landing resource 318 . In some implementations, the snapshot image may be an image file having any suitable file extension (eg, .jpg, .png, .bmp, etc.).

  The DOM tree can be a hierarchical model of resources. For example, the DOM tree for landing resource 318 may include image information for landing resource 318 (eg, image URL, display position, display size, alternate text, etc.), font information (eg, font name, size, effects, etc.), color information (eg, For example, it may include RGB color values, hexadecimal color codes, etc., and text information. Resource renderer module 402 may store snapshot images and / or DOM trees (eg, in memory 306 or an external database) for subsequent use by other modules of content generation system 114. In some implementations, resource renderer module 402 stores snapshot images and / or DOM trees as rendered resource data 410.

  With continuing reference to FIG. 4, the content extractor 308 is shown to include a secondary resource module 404. Secondary resource module 404 may be configured to identify secondary resource 320 associated with landing resource 318. In some implementations, secondary resource module 404 accesses resource association database 408 to identify one or more secondary resources 320 associated with landing resource 318. Resource association database 408 stores mappings, links, associations, and / or other connections between different resources (eg, in the form of data tables, tabular databases, associative databases, etc.) It can. In some implementations, resource association database 408 stores branding information associated with resources 318-320. Resource association database 408 may store semantic and / or detailed information about the various landing resources, and may include a list of links to other resources associated with the landing resources. In some implementations, resource association database 408 stores associations between landing resources 318 and social networking resources (eg, Google+ pages) associated with landing resources 318.

  In some implementations, the secondary resource module 404 uses the information extracted from the landing resource 318 to identify the secondary resource 320. For example, landing resource 318 may include a link of a particular secondary resource 320, a textual description, metadata, and / or other identifying information. Secondary resource module 404 determines whether secondary resource 320 is associated with the same entity as landing resource 318 (eg, owned, operated, or maintained by the same entity as landing resource 318), or secondary resource 320 with landing resource 318. Secondary resource 320 may be authenticated to determine if it is associated with a different subject (eg, a fan's page, imitation, etc.).

  Secondary resource module 404 may be configured to determine the quality of secondary resource 320. If secondary resource 320 is a social networking resource, secondary resource module 404 may determine quality based on the number of connections with other social networking resources (eg, number of followers, number of links, number of subscribers, etc.). In some implementations, the secondary resource module 404 determines the quality of the secondary resource 320 by popularity of the secondary resource 320 (eg, number of visits, number of views, etc.). The secondary resource module 404 may rank or score the plurality of secondary resources associated with the landing resource 318 and provide the resource renderer module 402 with an indication of the secondary resource with one or more scores on top.

  Resource renderer module 402 may generate a rendered representation of secondary resource 320 and store the rendered data in rendered resource data 410. In some implementations, resource renderer module 402 extracts and stores secondary resource data from secondary resource 320. Secondary resource data may include any type of information obtained from secondary resource 320. Secondary resource data may include company classification, company contact information (eg, company phone number, company email, etc.), company geographical location, type of goods or services offered by company, image, text , Color, style, and / or other types of information that may be extracted from the secondary resource 320.

  With continued reference to FIG. 4, the content extractor 308 is shown providing rendered resource data 410 to the various extractor modules 412-424. Each of the extractor modules 412-424 may be configured to extract different types of data from the rendered resource data 410. For example, image extractor 412 may be configured to extract image data asset 426, and video extractor 414 may be configured to extract video data asset 428, a color extra Kuta 416 may be configured to extract color data asset 430, font extractor 418 may be configured to extract font data asset 432, and text extractor 420 may be configured to extract Text data asset 434 may be configured to extract, location extractor 422 may be configured to extract location data asset 436 (eg, address, GPS coordinates, etc.), contact information Extractors 424 may be configured to extract contact data assets 438 (eg, telephone numbers, email addresses, etc.). Data assets 426-438 may be stored in memory 306 or a separate database for use in generating creatives 212 and / or creative extensions 216.

  Referring now to FIG. 5, the creative generator 324 according to an exemplary embodiment is shown in more detail. Creative generator 324 may use data assets 426-438 extracted by content extractor 308 to generate a creative customized for landing resource 318. Creative selector 310 may select creative 212 from the plurality of potential creatives generated by creative generator 324. In other implementations, creative selector 310 may select creative 212 from a database of creatives (ie, creative database 316) previously generated or provided by the content provider.

  Creative generator 324 is shown to include an image / video module 502. Image / video module 502 may analyze extracted image data asset 426 to detect visual content of the image. Detecting the visual content may be to determine the position of prominent objects represented in the image, to determine the position of text in the image, and / or to increase the visual impact of the image. It may include determining whether it can be cropped or processed. In some implementations, the image / video module 502 analyzes the extracted image to detect semantic content of the image. Detecting semantic content may include identifying the object conveyed in the image or the meaning conveyed by the image. The image / video module 502 may assign the image one or more labels or keywords indicating the semantic content of the image. Labels and / or keywords may be used to determine the relevance of the image to a particular third party content item.

  Image / video module 502 may process the image to prepare the image for use in a third party content item. Image processing involves cropping the image to highlight objects that are noticeable or delete text, resizing the image, formatting the image, or otherwise adjusting the image. May be included. In some implementations, the image / video module 502 identifies and extends logo images.

  Image / video module 502 may filter and rank images based on various attributes of the images. Image / video module 502 may determine a quality score for each of the images and / or a saliency score on the page. The quality score for an image may indicate the aesthetic beauty of the image based on various image attributes. The saliency score may indicate the significance of the extracted image being displayed on the landing resource. The image / video module 502 may discard or filter the images having a score of quality less than the display size or quality of the threshold less than the display size of the threshold. In some implementations, the image / video module 502 ranks the images based on the saliency scores associated with the images. The image / video module 502 may select the image or images with the highest rank for inclusion in the display content item.

  Image / video module 502 may analyze and process extracted video data asset 428 using processing steps similar to those applied to image data asset 426. In some implementations, the image / video module 502 combines multiple extracted images into a video file or video slide show.

  Still referring to FIG. 5, creative generator 324 is shown to include color / font module 504. The color / font module 504 includes color data asset 430 (eg, background color, image color, font color, text color, etc.), font data asset 432 (eg, font face, font size etc.), and content extras. Other types of style information may be received that are extracted by Kuta 308. In some implementations, the color / font module 504 selects the color of the generated content item background, heading, description, button background, and / or button text. The color / font module 504 may identify and use the color displayed on the landing resource 318, the secondary resource 320, or a combination thereof. The color / font module 504 may select a color for the content item using the snapshot image of the landing resource and / or the DOM tree. In some implementations, the color / font module 504 identifies clusters of colors from the snapshot image using clustering techniques (eg, k-means clustering).

  The color / font module 504 may select a font or font family for use in the generated content item. In some implementations, font data asset 432 may include font information as HTML, CSS, or XML font tags. The color / font module 504 may use the font data asset 432 to identify and select one or more fonts (eg, font face, font family, etc.).

  In some implementations, the color / font module 504 divides the extracted font into multiple categories based on font size. For example, color / font module 504 may generate a first category for large fonts (eg, greater than 20 pt, greater than 16 pt, etc.) and a second category for relatively smaller fonts. In some implementations, the color / font module 504 identifies multiple fonts or font families for use in the generated content item. For example, the color / font module 504 identifies a first font to use as a heading font for the content item to be generated and a second font to use as a font for the descriptive part of the content item or the text of the button. there's a possibility that. The color / font module 504 is a style generator module for using the extracted colors and fonts in generating a style (eg, color scheme, font scheme, etc.) for the generated content item 210. It may be provided to 510.

  Continuing to refer to FIG. 5, creative generator 324 is shown to include text module 506. The text module 506 receives the text data asset 434 and uses the text data asset 434 to generate heading text, description text, metadata on the page, title on the page, caption for the image, and the generated content item Other types of text may be selected for use within. In some implementations, text module 506 uses text data asset 434 to generate a summary of the text displayed on landing resource 318.

  In some implementations, text module 506 retrieves textual data from other data sources in addition to or instead of landing resources 318. For example, text module 506 may receive textual data from reviews created by a user of a company, product, or service. The reviews may be retrieved from Internet resources (eg, websites) that allow the user to post or send comments, reviews, or other text related to a particular company, product, or service. The URL of the landing resource 318 may be used to specify the location of such critiques and / or direct the text module 506 to a particular resource.

  The text module 506 may use a numerical rating (e.g., "one out of five," "four stars," etc.) or by such rating whether the criticism is positive or negative. It may also include a sentiment detection system that can be determined. The emotion detection system may analyze the words of criticism and look for adjectives that indicate positive (eg, exceptional, good, nice, nice, etc.). Then, the mood detection system may select or extract relatively short snippets of reviews that include such positive phrases for inclusion in content item 210.

  Still referring to FIG. 5, creative generator 324 is shown to include a classification module 508. In some implementations, classification module 508 uses resource data 410 to classify or categorize landing resources 318. In other implementations, the classification module 508 accesses the category database (eg, customer information database 322 or resource association database 408) to obtain categories for landing resource 318 (eg, based on the URL of landing resource 318). obtain. The category database may specify the company's category (eg, fast food, car parts, etc.) associated with the landing resource 318 and other attributes of the associated company. The categories of landing resources 318 may be used by the text generator module 512 to generate behavioral reminder text for the generated content item 210.

  Classification module 508 may use data from secondary resource 320 to determine classification of landing resource 318. For example, if the secondary resource 320 is a social networking resource, such as a Google+ profile, it may include classification information provided by the same entity associated with the landing resource 318. Classification module 508 may use classification information from secondary resources 320 to determine whether landing resources 318 are generated for branding or for a particular regional company. The classification information provided by the user may provide more detailed and accurate categories than other sources of classification information and may be advantageously utilized by the classification module 508 to improve classification of the landing resource 318 There is sex.

  Still referring to FIG. 5, creative generator 324 is shown to include a style generator module 510. Style generator module 510 may be configured to generate color schemes and / or font schemes for the generated content item 210. Style generator module 510 may use the colors extracted by color / font module 504 to generate color schemes for automatically generated content items. Style generator module 510 may select the color of the background, the color of the button, the color of the heading, the color of the description, the color of the text of the button, or the color for other portions of the content item to be generated. Style generator module 510 may determine the contrast between each of the extracted color saturation, intensity, salience, and / or other attributes, and the extracted color.

  In some implementations, the style generator module 510 may use the most dominant color (eg, the most heavily weighted, most dominant) extracted by the color / font module 504 as the background color for the content item And so on. Style generator module 510 may select the extracted color with the highest number of times multiplied by saturation as the button color for the content item. The style generator module 510 may select the color with the largest difference in contrast and / or brightness with the selected background color as the color for the heading and description text. If more than two colors are available, the style generator module 510 may select a more noticeable color as the heading color.

  In other implementations, style generator module 510 selects a predefined color scheme for content item 210. Instead of immediately applying the color extracted by the color / font module 504, a predefined color scheme may be generated as the background color, the button color, the heading color, the description color, the button text color, or May be used to select other parts of the content item. The predefined color scheme may be a combination of colors previously grouped into color templates or groups of colors. In some implementations, the predefined color scheme may be selected from a set of predefined color schemes based on the colors extracted by the color / font module 504. For example, the style generator module 510 may compare the color extracted by the color / font module 504 to the colors included in the plurality of predefined color schemes. The style generator module 510 determines the difference between one or more of the colors extracted by the color / font module 504 and one or more of the colors included in the predefined color scheme (eg, RGB values) Predefined color schemes may be ranked based on, saturation, brightness, contrast, etc.). The color from the predefined color scheme may complement or replace the color specified by the color / font module 504 in the automatically generated content item.

  In some implementations, the style generator module 510 selects a color scheme that improves the readability of the image and / or text. If the image is displayed within the content item 210 being generated, the style generator module 510 may select the background color of the image to provide high contrast with the color of the image (eg, RGB contrast> 200) . In some implementations, style generator module 510 identifies the original background color of the extracted image. The original background color may be the color of the background of the image displayed on the resource from which the image was extracted. The style generator module 510 may use the original background color of the image in the generated content item 210.

  In some implementations, the style generator module 510 identifies the boundaries in the image that separate the regions within the boundaries from the color of the background. Style generator module 510 may determine the longest boundary such that the contrast between the area within the boundary and the background color (eg, average RGB contrast) exceeds the threshold contrast value (eg, RGB contrast> 200) . If the area within the boundary exceeds the threshold area (eg, 80% of the image area), the style generator module 510 may determine that the color scheme improves the readability of the image.

  Style generator module 510 may select a combination of fonts for use in generated content item 210. In some implementations, the style generator module 510 selects a first font for heading text and a second font for description text and / or button text. Style generator module 510 may use the fonts extracted from landing resource 318 to select a combination of fonts that best matches the font used in landing resource 318. In this manner, the style generator module 510 facilitates the generation of content items that have a look and feel similar to the landing resources 318.

  With continuing reference to FIG. 5, creative generator 324 is shown to include a text generator module 512. Text generator module 512 may be configured to generate portions of text of content item 210. Text generator module 512 may generate heading text, description text, button text, behavior call text, mouse over text, metadata text, and / or other types of text for inclusion in content item 210. .

  Text generator module 512 is shown receiving input from classification module 508 and text module 506. The text generator module 512 may use the categories of landing resources 318 determined by the classification module 508 to generate behavioral reminder text tailored for particular categories of landing resources 318. For example, if the landing resource 318 is associated with a category of games, the text generator module 512 may generate action callout text such as “play now” or “try now”. If the landing resource 318 is associated with a subscription service, the text generator module 512 may generate behavioral reminder text such as “sign up now” or “register now”.

  In some implementations, text generator module 512 identifies text snippets (eg, phrases, text strings, portions, etc.) for use within generated content item 210. The text snippet may be part of landing resource 318, text displayed on secondary resource 320, or other text not displayed on resource 106 (eg, text of metadata). The text generator module 512 may process various types of extracted text and use it as the description text or heading text in the generated content item 210 (e.g., a threshold number of words, letters, or sentences) Less) can be identified. Text generator module 512 may highlight or highlight important features of the text such as price or date (eg, bold, underline, italic, increase font size, etc.).

  In some implementations, the text generator module 512 uses text extracted from user reviews of companies, products, or services associated with the landing resource 318. The text generator module 512, when read alone, selects a portion of the user's critique that effectively conveys why the critiqued user had a positive experience with the critiqued company, product or service It can. The snippet may include one or more positive adjectives used by the text module 506 in identifying sentiment related to the critique. For example, the text generator module 512 may select the snippet "extra pasta and crisp service" from the relatively long critique of an Italian restaurant. In some implementations, the text snippets identified by the text generator module 512 are presented to the content requestor 104 as potential "creatives" (e.g., descriptive text) for use in text-only content items. There is a possibility of In other implementations, the text snippet may be used as part of the text of one or more display content items generated by the content generation system 114.

  Continuing to refer to FIG. 5, creative generator 324 is shown to include layout module 514. Layout module 514 may be configured to generate a layout for content item 210 using the extracted and / or processed data. In some implementations, layout module 514 generates a creative 212 for content item 210 and may be referred to as a creative builder. The layout module 514 may select a layout from a set of predefined layout options (eg, template layouts) or may generate a new layout (eg, not based on a template). Layout module 514 may generate a layout based on the display size of the image selected by image / video module 502 and / or the length of the text selected by text module 506. The layout module 514 may resize the image to fit the selected layout and / or adjust the text, or adjust the layout to fit the selected image and / or text.

  In some implementations, the layout module 514 uses data assets extracted from the landing resources 318 to determine a style, a category of companies, or an appearance for the content item 210. For example, layout module 514 may use a category of landing resource 318 company (eg, fast food, car parts, etc.), a style of landing resource 318 (eg, modern or rustic), and a shape displayed on landing resource 318 (For example, a 90 degree corner, a rounded corner, etc.) may be determined. The layout module 514 may call an external database to retrieve company category information based on the URL of the landing resource 318.

  Layout module 514 may combine various data assets to generate creative 212 and provide creative 212 to rendering service 336. The rendering service 336 may be combined with the click 212 of the creative 212 and the creative extension 216 to generate and render the content item 210.

  Referring now to FIG. 6, the click type selector 312 according to the described implementation is shown in more detail. Click type selector 312 may be configured to select click type 214 for use in content item 210. The click type 214 may be an attribute of the content item 210 or a snippet of code embedded in the content item 210. The click type 214 may, for example, define the layout of the content item 210 (eg, which defines what parts of the content item 210 are clickable), the interactivity of the content item 210 (eg, a click that triggers navigation to the landing resource 318). Type) and / or how the content item 210 is rendered or presented by the client device 108. In some implementations, the click type 214 charges the content provider and defines the type of action of the user who is eligible as a "click" for the purpose of calculating performance metrics such as CTR. Click type 214 may define one or more conditions or triggers for navigating client device 108 to landing resource 318.

  Click type selector 312 is shown to include click type model trainer 328. Click type model trainer 328 may be configured to access event log database 208 to retrieve event data 204. Event data 204 may indicate the performance of content items previously provided to client device 108 in the context of various service offerings. Event data 204 may include logged user actions such as clicks, conversions, and / or other user behavior associated with previously provided content items. Event data 204 may include previously provided content item attributes (eg, click type, creative ID, creative extension, content type, etc.) and service delivery context details (eg, device type, device location, content platform, It may include the publisher's page classification, landing resource ID, etc.). Click type model trainer 328 may use data from event log database 208 to train and update click type performance model 326.

  Continuing to refer to FIG. 6, click type selector 312 is shown to include performance metric predictor 604 and click type performance model 326. Performance metric predictor 604 may provide click-type performance model 326 with serving context data 602. Serving context data 602 may be received as part of content request 202 and may indicate the context in which content item 210 is presented. Serving context data 602 may include landing resource ID (eg, URL), landing resource type (eg, page classification), device type (eg, mobile, tablet, desktop, etc.), content platform (eg, video, text, image) Etc.), the location of the device, the user profile ID associated with the content request 202, the creative ID, or other information indicative of the specific service delivery context.

  Performance metric predictor 604 uses click type performance model 326 to calculate the predicted performance (eg, pCTR) of the content item with various click types with respect to the serving context indicated by serving context data 602 It can. Performance metric predictor 604 may generate a score or ranking for each click type based on the predicted performance of the click type. In some implementations, the performance metric predictor 604 predicts the performance of content items having “button” click types, “entire content item” click types, and “confirm” click types.

  The button click type may define the click as a user interaction with a particular part of the content item 210, such as a clickable button or other subset of the total area of the content item 210. If content item 210 has a button click type, user interaction with other parts of content item 210 (e.g., parts outside the clickable area) may not cause client device 108 to navigate to landing resource 318 And may not qualify as a click for the purpose of calculating billing and / or performance metrics.

  The entire content item click type may define the click as user interaction with any part of the content item 210. If the content item 210 has the entire content item click type, user interaction with any part of the content item 210 may cause the client device 108 to navigate to the landing resource 318 and measure billing and / or performance. It may qualify as a click for the purpose of calculating the criteria.

  The confirmation click type may cause the content item 210 to display a confirmation prompt in response to a first user interaction (eg, a first click) with the content item 210. The confirmation prompt may display a message instructing the user to click again to navigate to the landing resource 318. If content item 210 has a confirmation click type, a second user interaction (eg, a second click) with content item 210 may cause client device 108 to navigate to landing resource 318, charging and It may qualify as a click for the purpose of calculating performance metrics. Confirmation click types can help protect against unintentional clicks that are unlikely to lead to conversions.

  Still referring to FIG. 6, the click type selector 312 is shown to include a click type selector module 606. The click type selector module 606 may be configured to select the click type 214 from a plurality of different click types for which the performance of the content is predicted by the performance metric predictor 604. The click type selector module 606 may take into account one or more performance metrics and select a click type that optimizes such performance metrics. The click type selector module 606 may output an indication of a particular click type 214 to the rendering service 336. Rendering service 336 may combine click type 214 with creative 212 and creative extension 216 to generate and render content item 210.

  Referring now to FIG. 7, the creative extension selector 314 according to the described implementation is shown in more detail. Creative extension selector 314 may be configured to select a creative extension 216 for use in content item 210. Creative extension 216 may be a complement to content item 210 in addition to main creative 212. Creative extensions 216 may include various buttons or clickable elements that cause different actions (eg, displaying a map, initiating a call, navigating to a landing resource 318, etc.) when selected. . Creative extension selector 314 may select creative extensions 314 from a plurality of potential creative extensions based on the serving context for content item 210 and / or data assets extracted by content extractor 308.

  Creative extension selector 314 is shown to include a creative extension model trainer 332. Creative extension model trainer 332 may be configured to access event log database 208 to retrieve event data 204. Event data 204 may indicate the performance of content items previously provided to client device 108 in the context of various service offerings. Event data 204 may include logged user actions such as clicks, conversions, and / or other user behavior associated with previously provided content items. Event data 204 may include previously provided content item attributes (eg, click type, creative ID, creative extension, content type, etc.) and service delivery context details (eg, device type, device location, content platform, It may include the publisher's page classification, landing resource ID, etc.). Creative extension model trainer 332 may use data from event log database 208 to train and update creative extension performance model 330.

  Continuing to refer to FIG. 7, creative extension selector 314 is shown to include performance metric predictor 704 and creative extension performance model 330. Performance metric predictor 704 may provide creative extension performance model 330 with serving context data 602. Serving context data 602 may be received as part of content request 202 and may indicate the context in which content item 210 is presented. Serving context data 602 may include landing resource ID (eg, URL), landing resource type (eg, page classification), device type (eg, mobile, tablet, desktop, etc.), content platform (eg, video, text, image) Etc.), the location of the device, the user profile ID associated with the content request 202, the creative ID, or other information indicative of the specific service delivery context.

  Performance metric predictor 704 uses creative extension performance model 330 to predict the performance (eg, pCTR) of a content item having various types of creative extensions with respect to the serving context indicated by serving context data 602 Can be calculated. Performance metric predictor 704 may generate a score or ranking for various creative extensions based on the predicted performance of the creative extensions. In some implementations, performance metric predictor 704 has “click to call” buttons, “location” buttons, “secondary resources” buttons, and / or other types of creative extensions that may be included in content item 210 Predict the performance of content items.

  The click-to-call button may initiate a call or other communication with an entity associated with the content item (eg, a retail store, a customer service phone, a sales agent, etc.). For other device types (for example, desktop computers, tablets, etc.), when the contact information is known, a "click to email" button or a wider "click to contact" button instead of a click to call button It may be included.

  The location button may cause a map showing the extracted geographical location to be displayed. If the serving context indicates that the content item 210 is presented on a mobile device, selecting the location button may cause the map application or navigation application to load. In some implementations, selecting the location button causes the client device 108 to navigate to a map resource (eg, a Google map).

  The secondary resource button may cause client device 108 to navigate to secondary resource 320. Content item 210 may include creative extensions (eg, selectable buttons or links) for portions of multiple different resources or resources (eg, secondary resources 320, social resources, landing resources 318, etc.). In some implementations, content item 210 links only to secondary resource 320 (as opposed to landing resource 318) and may be referred to as a social content item. In other implementations, content item 210 links to both landing resource 318 and secondary resource 320. Performance metric predictor 704 may calculate the predicted performance for content items with various types of creative extensions based on the context in which the content item is presented.

  Continuing to refer to FIG. 7, creative extension selector 314 is shown to include an extension selector module 706. In some implementations, the extension selector module 706 receives position data 436. Location data 436 may be extracted from various data sources such as landing resource 318, secondary resource 320, customer information database 322, or received from client device 108. Location data 436 may include the physical or geographical location of the company or entity associated with content item 210. For example, if content item 210 is associated with a restaurant chain, location data 436 may include one or more locations of restaurants. In some implementations, location data 436 includes the location of client device 108 (eg, GPS coordinates, a location based on WiFi, etc.).

  In some implementations, the extension selector module 706 receives contact data 438. Contact data 438 may be extracted from various data sources such as landing resource 318, secondary resource 320, customer information database 322, and the like. Contact data 438 may include contact information regarding the company or other entity associated with content item 210. Contact data 438 may be used to contact or communicate with a telephone number, an email address, a URL of a web page (eg, a URL for landing resource 318 or secondary resource 320), or a company or entity associated with content item 210. It may include other types of information that may be used.

  The extension selector module 706 may use the serving context data 602, location data 436, and / or contact data 438 to determine which of a plurality of creative extensions may be available for selection. Different types of creative extensions may be available under different circumstances. For example, a click-to-call button may be available for selection when the serving context for content item 210 indicates that content item 210 is presented on a mobile communication device. In some implementations, the click-to-call button may be available for selection when the contact data 438 includes a phone number or other contact information. The location button is selected when the geographic location (eg, a street address, store location, email address, GPS coordinates, etc.) is extracted by the content extractor 308 or when the location of the client device 108 is known. Could be used for The secondary resource button may be used for selection when the identification information of the secondary resource 320 is known.

  The extension selector module 706 may be configured to select a combination of creative extensions or creative extensions from the set of creative extensions that the content's performance is predicted by the performance metric predictor 704. In some implementations, the performance metric predictor 704 predicts the performance of the content item with respect to various types of creative extensions that may be utilized for selection. The extension selector module 706 may select one or more creative extensions that optimize one or more performance metrics and optimize such performance metrics. Creative extension selector module 706 may output an indication of a particular creative extension 216 or combination of creative extensions 216 to rendering service 336.

  Continuing with FIG. 7, rendering service 336 may combine creative extension 216 with creative 212 and click type 214 to generate and render content item 210. In some implementations, the rendering service 336 is a component of the client device 108 (eg, a web browser operating on the client device 108). In other implementations, rendering service 336 may be a component of content generation system 114. Creative 212, click type 214, and creative extension 216 may each include rendering instructions specific to the selected creative, click type, or creative extension. For example, the click type 214 may be rendered as a subset of the content item 210 as a clickable element for the button click type or as an entire area of the content item 210 for the entire content item click type as a clickable element May be included. The rendering service 336 may be configured to render the content item 210 in accordance with the instructions provided by the creative 212, the click type 214, and the creative extension 216.

  Content item 210 may be provided to client device 108. User interaction (eg, impressions, clicks, conversions, etc.) of content item 210 may be logged and stored in event log database 208. Content generation system 114 may use the logged events to calculate metrics of performance associated with content item 210 and to train prediction models 326 and 330. Content generation system 114 uses predictive models 326 and 330 to determine which feature or combination of features of the content item (e.g., click type, creative extension, etc.) optimize content performance for a given service delivery context. It can be estimated to be connected (eg, features that optimize CTR, pCTR, or another performance metric). The content generation system 114 may then automatically generate a new content item with features estimated to lead to optimal content performance.

  Referring now to FIG. 8, a flow diagram of a process 800 for optimizing content performance using click types in accordance with the described implementations is shown. Process 800 may be performed by content generation system 114 described with reference to FIGS. 1-7. In some implementations, process 800 is performed by processing circuit 302 using one or more of processor 304 and modules stored in memory 306. In various implementations, the steps of process 800 may be rearranged (ie, performed in a different order) or performed simultaneously.

  Process 800 is shown to include receiving a request for a content item for presentation on a client device (step 802). The content item request may include an indication of the service provision context for the content item. The indication of context of service provision may be landing resource ID (eg, URL), landing resource type (eg, page classification), device type (eg, mobile, tablet, desktop etc.), content platform (eg, video, text, etc.) It may include service provision context data such as images), device location, user interest, or other information indicating the context of a particular service provision. A request for content item may be received from content requester 104, content server, real-time bidding system, or client device 108. In some implementations, the request for content item is received from client device 108 as part of an online content provision process (e.g., a request for advertisement to display on a web page).

  Still referring to FIG. 8, process 800 uses the click type performance model and service delivery context for the content item to calculate metrics of the predicted performance of the content item for a plurality of different potential click types. It is shown to include (step 804). In some implementations, the performance metric is the click rate. Each of the potential click types may define different criteria for defining clicks for the purpose of calculating click rates. For example, a potential click type is a button that defines a click as the user's interaction with the first part of the content item excluding the user's interaction with the second part of the content item distinct from the first part It may include a click type. Potential click types may include whole content item click types that define clicks as the user's interaction with any part of the content item. The potential click types may include confirmation click types that define clicks as the user's interaction with the content item that occurs while the confirmation prompt is displayed. Confirmation prompts may be displayed in response to previous user interaction with the content item.

  Each of the potential click types may define different criteria for triggering an event to be performed in response to the user's interaction with the content item when the defined criteria are met. For example, each of the potential click types may be different user actions associated with the content item (eg, clicking a button, clicking anywhere within the content item's display area, content in response to a confirmation prompt) There is a possibility to define such as clicking on the item. Triggered events may include landing resources, navigating to secondary resources, initiating communication, displaying a map, launching an application, or any other event that may be triggered automatically. There is sex. Different click types may require different types of user interaction to trigger an event.

  Continuing to refer to FIG. 8, process 800 is shown to include selecting one of the potential click types based on a metric of expected performance (step 806). Step 806 may include selecting a click type associated with the extremum of the performance metric to be predicted. In some implementations, step 806 includes selecting a button click type. If the button click type is selected, the process 800 determines that the user interacts with the first part of the content item (except for the user's interaction with the second part of the content item separate from the first part). The method may include defining a criteria for triggering an event as and rendering a clickable button that occupies only a first portion of the content item.

  In some implementations, step 806 includes selecting an entire content item click type. If the entire content item click type is selected, the process 800 may define criteria for triggering an event as user interaction with any part of the content item, and may click the entire display area of the content item. Rendering as an element.

  In some implementations, step 806 includes selecting a confirmation click type. If a confirmation click type is selected, the process 800 displays a confirmation prompt in response to the first user interaction with the content item and a confirmation prompt is displayed after the first user interaction. Defining criteria for triggering the event as a second user interaction with the content item that takes place during the

  Still referring to FIG. 8, process 800 generates a content item having the selected click type (step 808) and provides the generated content item for presentation on the client device (step 810). And is included. Content items may be generated in response to the request received at step 802 as part of a real-time service provision process. Step 808 may include combining the selected click type with the selected creative and / or the selected creative extension. In some implementations, step 808 includes rendering the content item according to the instructions provided by the selected click type. Rendering content items may be performed by a remote rendering service or by a client device. In some implementations, step 810 is performed before step 808. For example, the selected click type may be provided to the client device, and the client device may render the content item using the selected click type.

  With continuing reference to FIG. 8, process 800 is shown to include collecting and storing event data indicating user actions associated with content items having each of the potential click types (step 812). Event data may indicate the performance of content items previously provided to a client device or other client device in the context of various service offerings. Event data may include logged user actions such as clicks, conversions, and / or other user behavior associated with previously provided content items. Event data may include previously provided content item attributes (eg, click type, creative ID, creative extension, content type, etc.) and service delivery context details (eg, device type, device location, content platform, publishing Page classification, landing resource ID, etc.).

  Continuing to refer to FIG. 8, process 800 is shown to include using event data as feedback for training a click-type performance model (step 814). Step 814 may be performed by the click type model trainer 328 described with reference to FIGS. 3 and 6. In some implementations, step 814 includes accessing an event log database (eg, database 208) to retrieve event data and / or performance metrics. Step 814 trains and / or updates the click type performance model using data from the event log database to ensure that the click type performance model accurately predicts the performance of the content for various click types. Can be included.

  Referring now to FIG. 9, a flow diagram of a process 900 for optimizing content performance using creative extensions according to the described implementation is shown. Process 900 may be performed by content generation system 114 described with reference to FIGS. 1-7. In some implementations, process 900 is performed by processing circuit 302 using one or more of processor 304 and modules stored in memory 306. In various implementations, the steps of process 900 may be rearranged (ie, performed in a different order) or performed simultaneously.

  Process 900 is shown to include receiving a request for a content item to present on a client device (step 902). The content item request may include an indication of the service provision context for the content item. The indication of context of service provision may be landing resource ID (eg, URL), landing resource type (eg, page classification), device type (eg, mobile, tablet, desktop etc.), content platform (eg, video, text, etc.) It may include service provision context data such as images), device location, user interest, or other information indicating the context of a particular service provision. A request for content item may be received from content requester 104, content server, real-time bidding system, or client device 108. In some implementations, the request for content item is received from client device 108 as part of an online content provision process (e.g., a request for advertisement to display on a web page).

  Still referring to FIG. 9, process 900 uses the creative extension performance model and serving context for the content item to calculate metrics of the expected performance of the content item for a plurality of different potential creative extensions. It is shown to include (step 904). In some implementations, the performance metric is the click rate. Each of the potential creative extensions may define different actions to be taken in response to the user's interaction with the content item. For example, potential creative extensions may include click-to-call extensions that cause client devices to initiate communication with a subject associated with the content item. Potential creative extensions may include location extensions that launch map applications or display geographic locations associated with content items. Potential creative extensions may include secondary resource extensions that cause the client device to navigate to secondary resources associated with the content item.

  Continuing to refer to FIG. 9, process 900 is shown to include selecting one of the potential creative extensions based on the predicted performance metric (step 906). Step 906 may include selecting a creative extension associated with the extremum of the performance metric to be predicted. In some implementations, step 906 includes using the service delivery context for the content item to determine which of the potential creative extensions may be utilized for selection. For example, click-to-call extensions may be used for selection if the client device is identified as a mobile phone, but may not be used for selection if the client device is identified as a desktop computer.

  In some implementations, step 906 includes using the identification information of the creative portion of the content item to determine which of the potential creative extensions may be utilized for selection. For example, a "location" creative extension may be available for selection with respect to content items that specifically market a restaurant chain, and may provide the location of the nearest restaurant location of the chain. However, location creative extensions may not be available for selection, particularly with regard to content items that are only sold online and specifically market products or services that do not have physical locations that the user may potentially visit. is there.

  In some implementations, step 906 includes extracting data assets from landing resources, secondary resources associated with landing resources, and / or customer information databases. Step 906 may include using the extracted data asset to determine which of the potential creative extensions may be utilized for selection. Determining which of the potential creative extensions can be used for selection involves identifying the data assets needed for the creative extensions and whether the identified data assets have been extracted. And determining, in response to determining that the required data asset has not been extracted, determining that the creative extension can not be utilized for selection.

  Still referring to FIG. 9, process 900 generates a content item having the selected creative extension (step 908) and provides the generated content item for presentation on the client device (step 910). And is included. Content items may be generated in response to the request received at step 902 as part of a real-time service provision process. Step 908 may include combining the selected creative extension with the selected creative and / or the selected click type. In some implementations, step 908 includes rendering the content item according to the instructions provided by the selected creative extension (eg, rendering the creative extension as a selectable button). Rendering content items may be performed by a remote rendering service or by a client device. In some implementations, step 910 occurs before step 908. For example, the selected creative extension may be provided to the client device, and the client device may render the content item using the selected creative extension.

  Continuing to refer to FIG. 9, process 900 is shown to include collecting and storing event data indicating user actions associated with content items having each of the potential creative extensions (step 912). Event data may indicate the performance of content items previously provided to a client device or other client device in the context of various service offerings. Event data may include logged user actions such as clicks, conversions, and / or other user behavior associated with previously provided content items. Event data may include previously provided content item attributes (eg, click type, creative ID, creative extension, content type, etc.) and service delivery context details (eg, device type, device location, content platform, publishing Page classification, landing resource ID, etc.).

  Continuing to refer to FIG. 9, process 900 is shown to include using event data as feedback for training a creative extension performance model (step 914). Step 914 may be performed by the creative extension model trainer 332 described with reference to FIGS. 3 and 7. In some implementations, step 914 includes accessing an event log database (eg, database 208) to retrieve event data and / or performance metrics. Step 914 trains and / or uses the creative extension performance model using data from the event log database to ensure that the creative extension performance model accurately predicts the performance of the content with respect to the various types of creative extensions. It may include updating.

  Implementations and operations of the subject matter described herein include digital electronic circuitry, or computer software, firmware, or hardware, or any of them, including the structures disclosed herein and their structural equivalents. It may be implemented in one or more combinations. An implementation of the subject matter described herein may be one or more computer programs, ie, one or more computer storage media for execution by a data processing apparatus or to control operation of a data processing apparatus. It may be implemented as one or more modules of computer program instructions encoded above. Alternatively or additionally, the program instructions are artificially generated propagation signals (eg, for example, generated to encode information for transmission to a suitable receiver device for execution by a data processing device) , Machine-generated electrical signals, optical signals, or electromagnetic signals). The computer storage medium may be or be included in a computer readable storage device, a computer readable storage substrate, a random or serial access memory array or device, or one or more thereof. Additionally, the computer storage medium may be a source or destination of computer program instructions encoded in an artificially generated propagated signal, but not a propagated signal. Computer storage media may be or be included in one or more separate components or media (eg, multiple CDs, disks, or other storage devices). Thus, computer storage media are tangible and non-transitory.

  The operations described in the present disclosure may be implemented as operations performed by a data processing apparatus on data stored in one or more computer readable storage devices or received from other sources.

  The terms "client" or "server" refer to all types of data processing, including, by way of example, one programmable processor, one computer, one system on a chip, or a plurality or combination thereof. Includes devices, devices, and machines. The apparatus may include dedicated logic circuitry, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The device, in addition to the hardware, code that generates an execution environment for the computer program in question (eg, processor firmware, protocol stack, database management system, operating system, cross platform runtime environment, virtual machine, or The code which comprises one or more combination among them may also be included. The apparatus and execution environment may implement a variety of different computing model infrastructures, such as a web services infrastructure, a distributed computing infrastructure, and a grid computing infrastructure.

  The systems and methods of the present disclosure may be completed by any computer program. A computer program (also known as a program, software, software application, script or code) can be written in any form of programming language, including a compiled or interpreted language, a declarative language or a procedural language. It may be arranged in any form, including as a stand-alone program, or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. Computer programs may, but do not necessarily, correspond to files in the file system. The program may be part of a file that holds other programs or data (eg, one or more scripts stored in a markup language document), a single file dedicated to the program in question, or In one or more modules, subprograms, or files storing portions of code. The computer program may be located on one computer, at one location, or distributed at multiple locations and may be arranged to run on multiple computers interconnected by a communications network.

  The processes and logic flows described herein perform operations on input data and one or more programmable processors of one or more computer programs to perform an action by generating an output. It can be executed by executing. The processes and logic flows may be performed by dedicated logic circuitry (eg, an FPGA or ASIC) and the devices may be implemented as dedicated logic circuitry (eg, an FPGA or ASIC).

  Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random access memory or both. The essential elements of a computer are a processor for performing actions in accordance with instructions and one or more memory devices for storing instructions and data. Also, generally, does the computer include or receive data from one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data? And / or are operatively coupled to transfer data to their mass storage devices, or both. However, the computer may not have such a device. In addition, the computer may be another device (eg, a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device (eg, a universal serial bus) (USB) flash drive etc.). Devices suitable for storing computer program instructions and data are, by way of example, semiconductor memory devices (e.g. EPROM, EEPROM and flash memory devices, magnetic disks, e.g. internal hard or removable disks, magneto-optical disks, and CDs). Includes all forms of non-volatile memory, media, and memory devices, including ROM disks and DVD-ROM disks). The processor and the memory may be supplemented by dedicated logic circuits or may be incorporated in the dedicated logic circuits.

  In order to provide user interaction, implementations of the subject matter described herein include display devices (e.g., CRTs (brown tubes), LCDs (liquid crystal displays), OLEDs (organic light emitting diodes), TFTs (thin film transistors), Or any other flexible configuration, or any other monitor that displays information to the user, and a keyboard, pointing device, such as a mouse, a trackball, etc., or a touch screen, a touch through which the user can provide input to the computer And may be implemented on a computer having a pad or the like. Other types of devices may also be used to interact with the user, eg, the feedback provided to the user may be in any form of sensory feedback (eg visual feedback, auditory feedback Or tactile feedback, and input from the user may be received in any form, including acoustic, speech or tactile input. In addition, the computer sends the document to the device used by the user and receives the document from the device, for example, to the web page on the web browser of the user's client device in response to the request received from the web browser. It is possible to interact with the user by sending

  Implementations of the subject matter described in this disclosure may include back-end components (eg, as data servers), or middleware components (eg, application servers), or users described in the subject matter of the disclosure. Includes a front end component (eg, a client computer) with a graphical user interface or web browser that can interact with the implementation, or one or more such back end components, middleware components, or front end components May be implemented on a computing system including any combination of The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include LANs and WANs, internetworks (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks).

  Although the specification includes many specific implementation details, these should not be considered as limitations on the scope of any disclosure or what may be claimed, but rather on the particular implementation of a particular disclosure. It should be considered as an explanation of the features unique to. Certain features that are described in the present disclosure in the context of different implementations may also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation may also be implemented in multiple implementations separately or in any suitable subcombination. Further, the features may be described above as operating in a particular combination, and may even be first asserted as such, although one or more of the claimed combinations are Features may possibly be deleted from the combination, and the claimed combination may be directed to partial combinations or variations of partial combinations.

  Likewise, although the operations are shown in a particular order in the figures, this may be performed such that the operations are performed in the particular or sequential order shown, or to achieve the desired result. It should not be understood that all the actions indicated are required to be performed. In certain situations, multitasking and parallel processing may be advantageous. Moreover, the partitioning of the various system components in the implementations described above should not be understood as requiring such partitioning in all implementations, and the program components and systems described are generally single. It should be understood that the software product may be integrated together or packaged into multiple software products embodied on one or more tangible media.

The features disclosed herein are configured with processing circuitry configured to integrate Internet connectivity with a more traditional television program source (e.g., received by cable, satellite, propagation, or other signal). It may be implemented on a smart television module (or connected television module, hybrid television module, etc.) that may be included. Smart TV modules may be physically integrated into the television set, or set-top boxes, Blu-ray or other digital media players, game consoles, hotel television systems, and other companion devices etc. May contain separate devices. Smart TV module to allow viewers to search and find videos, movies, photos and other content stored on the web, local cable TV channels, satellite TV channels or on a local hard drive May be configured. A set top box (STB) or set top unit (STU) includes a tuner and may include a home appliance device that connects to a television set and an external source of signals, converting the signals into content And the content is displayed on a television screen or other display device. Smart TV modules are icons for multiple different applications such as web browsers and multiple streaming media services (eg Netflix, Vudu, Hulu etc), connected cable or satellite media sources, other web "channels" etc May be configured to provide a home screen or top-level screen including The smart television module may be further configured to provide the user with an electronic program guide. A companion application to the smart TV module provides mobile computing for the purpose of providing the user with additional information about available programs, enabling the user to control the smart TV module, etc. It may be able to work on the device. In alternative embodiments, the features may be implemented on a laptop computer or personal computer, a smart phone, other mobile phones, handheld computers, tablet PCs, or other computing devices.

  Thus, a specific implementation of the subject has been described. Other implementations are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be in the particular order or sequential order depicted to achieve the desired results. In certain implementations, multitasking and parallel processing may be advantageous.

100 computer systems
102 Network
104 Content Requester
106 Resources
108 Client Device
110 Resource Renderer
112 Data Storage Device
114 Content Generation System
200 systems
202 Content request
204 Event data
206 Content Performance Prediction Model
208 Event Log Database
210 content items
212 Creative
214 Click type
216 Creative Extensions
302 processing circuit
304 processor
306 memory
308 Content Extractor
310 Creative Selector
312 Click Type Selector
314 Creative Extension Selector
316 Creative Database
318 Landing Resources
320 Secondary Resource
322 Customer Information Database
324 Creative Generator
326 Click Type Performance Model
328 Click Type Model Trainer
330 Creative Extended Performance Model
332 Creative Expansion Model Trainer
334 Performance Metrics
336 Rendering Service
402 Resource Renderer Module
404 secondary resource module
408 Resource Association Database
410 Rendered Resource Data
412 image extractor
414 video extractor
416 color extractor
418 font extractor
420 Text Extractor
422 position extractor
424 Contact Extractor
426 Image data assets
428 Video Data Assets
430 color data asset
432 Font Data Assets
434 Text data assets
436 Position Data Asset
438 Contact Data Assets
502 Image / Video Module
504 color / font module
506 text module
508 classification module
510 Style Generator Module
512 text generator module
514 Layout Module
602 Service Provision Context Data
604 Performance Measurement Reference Predictor
606 Click Type Selector Module
704 Performance Measurement Reference Predictor
706 Extended Selector Module
800 processes
900 processes

Claims (20)

A method for optimizing the performance of content,
In the processing circuit, comprising: receiving a request for a third of the content for presentation on the client device, including an indication of the request is a service provided regarding the contents of the third party context, the steps,
Selecting, by the processing circuitry, a creative for presentation in the content item to the client device in response to the request;
Identifying, by the processing circuitry, a plurality of types of potential creative extensions available for selection to include in the content item based on the context of the service provision, the identified potential creatives Each of the types of extensions defines different actions that occur in response to user interaction with the content item;
Creative extension performance model for the content item and provision of the service to calculate predicted performance criteria of the content item for each of a plurality of identified types of potential creative extensions by the processing circuit Using the context of, wherein the creative extension performance model is configured to provide content performance predictions for various types of creative extensions;
Selecting , by the processing circuitry, potential creative extensions available to the content item based on the predicted performance metric.
Generating the content item having the selected creative and the selected creative extension, wherein the content item is generated by the processing circuit in response to the request;
Providing the generated content item for presentation on the client device. Collecting and storing event data indicating user actions associated with content items having each of the potential creative extensions;
Using the event data as feedback to train the creative extension performance model. Extracting a data asset from at least one of a landing resource associated with the content item, a secondary resource associated with the landing resource, and a customer information database;
The method of claim 1, further comprising: using the extracted data asset to determine which potential creative extensions are available for selection . Using the selected data asset to determine which of the potential creative extensions are available for selection:
Identifying the data assets required to generate the first creative extension;
Determining whether the identified data asset has been extracted;
Determining that the first creative extension is not available for selection in response to the determination that the required data asset has not been extracted
The method according to claim 3, comprising: The method according to claim 1, wherein the step of selecting the creative extension uses the service provision context for the third party content to determine which potential creative extensions are available for selection. . The step of selecting the creative extension includes the step of selecting a click-to-call extension, the method further comprising:
Using the extracted contact information to generate a first creative extension to initiate communication with an entity associated with the content item;
Rendering the generated first creative extension as a selectable element of the content item
The method of claim 1 comprising: The step of selecting the creative extension includes the step of selecting a position extension, the method further comprising:
Launching the map application or using the extracted location information to generate a first creative extension configured to display the geographical location associated with the content item;
Rendering the generated first creative extension as a selectable item of content item
The method of claim 1 comprising: The step of selecting the creative extension includes the step of selecting a secondary resource extension, the method further comprising:
Using the extracted secondary resource information to generate a first creative extension configured to navigate the client device to a secondary resource associated with the content item;
Rendering the generated first creative extension as a selectable element of the content item;
The method of claim 1 comprising: The method of claim 1, wherein selecting the creative extension comprises selecting the creative extension associated with an extremum of a metric of predicted performance for the potential creative extension . The method according to claim 1, wherein the service providing context comprises at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association . A system for optimizing the performance of content,
A processing circuit comprising a processor and a memory, said processing circuit comprising
The method comprising: receiving a request for a third of the content for presentation on the client device, including an indication of the request is a service provided regarding the contents of the third party context, and receiving,
Selecting a creative for presentation in the content item to the client device in response to the request;
Identifying a plurality of types of potential creative extensions available for selection to include in the content item based on the context of the service provision, each of the types of potential creative extensions identified Define different actions that occur in response to user interaction with the content item, specifying;
Using a creative extension performance model for the content item and the service delivery context to calculate predicted performance criteria of the content item for each of a plurality of identified types of potential creative extensions Wherein said creative extension performance model is configured to provide content performance predictions for various types of creative extensions;
Selecting potential creative extensions available to the content item based on the predicted performance metric;
Generating the content item having the selected creative and the selected creative extension in response to the request ;
Providing the generated content item for presentation on the client device. The processing circuit
Collecting and storing event data indicative of user actions associated with content items having each of the potential creative extensions;
The system of claim 11, further configured to: use the event data as feedback to train the creative extension performance model. The processing circuit
Extracting a data asset from at least one of a landing resource associated with the content item, a secondary resource associated with the landing resource, and a customer information database;
The system of claim 11, further configured to: use the extracted data asset to determine which potential creative extensions are available for selection . Using the selected data asset to determine which of the potential creative extensions are available for selection:
Identifying the data assets needed to generate the first creative extension;
Determining whether the identified data asset has been extracted;
Determining that the first creative extension is not available for selection in response to the determination that the required data asset has not been extracted
The system of claim 13, comprising: 12. The method of claim 11, wherein selecting the creative extension includes using the serving context for the third party content to determine which potential creative extensions are available for selection. System described. Selecting the creative extension includes selecting a click-to-call extension, and the processing circuit
Using the extracted contact information to generate a first creative extension to initiate communication with an entity associated with the content item;
Rendering the generated first creative extension as a selectable element of the content item;
The system of claim 11, wherein the system is further configured to: Selecting the creative extension includes selecting a location extension, the processing circuitry
Using the extracted location information to launch a map application or to generate a first creative extension configured to display a geographic location associated with the content item;
Rendering the generated first creative extension as a selectable item of content item;
The system of claim 11, wherein the system is further configured to: Selecting the creative extension includes selecting a secondary resource extension button, the processing circuit
Using the extracted secondary resource information to generate a first creative extension configured to navigate the client device to a secondary resource associated with the content item;
Rendering the generated first creative extension as a selectable element of the content item;
The system of claim 11, wherein the system is further configured to: The system of claim 11, wherein selecting the creative extension comprises selecting the creative extension associated with an extremum of a metric of expected performance for the potential creative extension . The system according to claim 11, wherein the service providing context includes at least one of the type of client device, the platform of the client device, and the resource to which the content item is presented in association .

Images