Local digital component storage

By building a digital content repository on the user device, using user data to select a subset of digital content and adopting an asynchronous request mechanism, the problems of user privacy protection and resource consumption in the public network are solved, and faster content requests and better content User experience.

CN119096240APending Publication Date: 2024-12-06GOOGLE LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380028960.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-04-05
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art is difficult to effectively protect user privacy in data processing, especially in public network environments, and the resource consumption and response time between the content server and the user device are relatively long, which affects the user experience.

Method used

By building a digital content repository on a user device, using user data to select and store subsets of digital content related to it, reducing the amount of data retrieved from the content server, using asynchronous request and scoring mechanisms to select and provide digital components, avoiding the content server's relationship with the content server Share private third-party data.

Benefits of technology

It improves user privacy protection, reduces resource consumption and network consumption of user devices, shortens content request time, and improves user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119096240A_ABST
    Figure CN119096240A_ABST
Patent Text Reader

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for digital component storage are described. In one aspect, a method includes receiving, by a client device, a plurality of digital components from one or more content platforms. Each of the digital components corresponds to user data associated with at least a first application executing on the client device. The client device stores a plurality of digital components in a repository and determines a score for each digital component stored in the repository based on the number of times the digital component has been received. A client device receives a request for digital content for presentation in a second application different from a first application. The client device selects one of the p digital components based on the score and provides the selected digital component for presentation in the second application.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This statement relates to data processing, data privacy and data security. Background Art

[0002] In systems and devices connected to public networks such as the Internet, data security and user privacy are of paramount importance. Concerns about user privacy have led many developers to change the way they handle user data. For example, some browser developers are planning to abandon the use of third-party cookies. Summary of the invention

[0003] A repository on a user can store a collection of digital content to improve efficiency and privacy. A digital content service (e.g., providing digital content to an application on a user device) can include digital content targeting by selecting a subset of digital content at a content server and selecting target digital content on a user device. A digital content refinement selection (subselection) can bring a smaller collection of digital content to a user device for digital content selection on a device. Large content servers can store more digital content than the digital content selection and auction process on the device can support. Due to storage and processing constraints, all digital content in an online repository associated with a content server cannot be downloaded to a user device.

[0004] On-device digital content repository construction may include building models that can refine the selection of meaningful digital content from off-device digital content repositories with non-sensitive data that can leave the device. These models may be limited to selecting digital content based on third-party signals (e.g., user data associated with another application). The selection process performed by these models may not be as accurate as methods that have access to all signals (e.g., third-party signals).

[0005] The user device may send a request to the content server to extract digital content. For example, a website accessed on the user device may have organic content and tags (e.g., JavaScript tags, html tags). The website may include a rectangular frame (e.g., an iframe) to which digital content may be added. A request including an identifier (e.g., a URL) of the website may be sent to the content server. The content server may retrieve the digital content from an associated inventory based on the request, score the digital content using a digital signal, and send the digital content back to the user device to render for the user on the website.

[0006] The device digital content repository allows for digital content scoring and retrieval on the device. The on-device digital content service may not work with the entire inventory of digital content that the server has. The user device may lack the computing power of a content server to perform digital content retrieval and scoring for a large amount of digital content. For example, a content server may perform indexing, retrieval, extraction, scoring, and / or auctioning of digital content. The on-device digital content service may work on a smaller subset of the inventory of digital content from a content server.

[0007] Available user data (e.g., interests) can be used to improve the selection of a subset of digital content. In some implementations, a subset of digital content can be randomly selected for an on-device repository, and the digital content can be provided from the repository. However, using user data to select a subset of the digital content inventory can improve the efficiency of the digital content provider. For example, user data (e.g., interest or disinterest in games, music, and / or cooking) can be used to avoid randomly selected, less relevant digital content (e.g., digital content related to cooking) and efficiently use storage space on the device.

[0008] A subset of the digital content may be retrieved synchronously or asynchronously. Synchronous digital content retrieval may occur at the time of the digital content request when the application is active. Asynchronous digital content retrieval may occur during safe times to download digital content. For example, asynchronous digital content retrieval may occur when the application is inactive, when the device is charging, and / or when the device is connected to a non-metered connection.

[0009] In general, one innovative aspect of the subject matter described in this specification can be embodied in a method including the following operations: receiving, by a client device, a plurality of digital components from one or more content platforms, wherein each of the digital components corresponds to user data associated with at least a first application executed on the client device; storing, by the client device, the plurality of digital components in a repository on the client device; determining, by the client device, a score for each of the plurality of digital components stored in the repository, wherein the determination is based on the number of times the digital component has been received; receiving, by the client device, a request for digital content to be presented in a second application executed on the client device, wherein the second application is different from the first application; selecting, by the client device, one of the plurality of digital components based on the scores of the plurality of digital components; and providing, by the client device, the selected one of the digital components for presentation in the second application. Other implementations of this aspect include corresponding devices, systems, and computer programs configured to perform aspects of the method encoded on a computer storage device.

[0010] In general, one innovative aspect of the subject matter described in this specification can be embodied in a method comprising the following operations: receiving, by a server, a request for a digital component for presentation by the client device from a client device, wherein the request for the digital component includes user data associated with at least a first application executed on the client device; and in response to receiving the request for the digital component, transmitting, by the multi-platform server, a plurality of digital components to the client device, wherein each of the digital components corresponds to the user data.

[0011] These and other implementations may each optionally include one or more of the following features. In some aspects, the plurality of digital components are received in response to a request from a first application. The method may include the following operations: receiving a second plurality of digital components in response to a request from a third application on the client device.

[0012] In some aspects, wherein scoring each digital component in a plurality of digital components stored in a repository includes scoring a first digital component included in both a first subset of the plurality of digital components and a second subset of the plurality of digital components higher than a second digital component not included in both the first subset of the plurality of digital components and the second subset of the plurality of digital components.

[0013] In some aspects, the method may include the following operations: determining that the number of digital components in the repository on the client device exceeds a predetermined threshold; and in response to determining that the number of digital components in the repository on the client device exceeds the predetermined threshold, removing the digital component with the lowest score from the repository on the client device.

[0014] In some aspects, the user data associated with at least the first application includes at least one of first-party data, contextual data, or privacy-safe data.

[0015] In some aspects, the user data associated with at least the first application includes a sequence of actions performed by the user utilizing the second application.

[0016] In some aspects, a plurality of digital components are received in response to a request to transmit a message including user data associated with at least a first application.

[0017] In some aspects, the request for digital content for presentation in the second application includes user data; and one of the plurality of digital components is selected based on the user data.

[0018] In some aspects, the method may include the following operations: determining a second score for each of a plurality of digital components stored in a repository, wherein the second score is determined based on at least one of a first-party signal, a third-party signal, or a contextual signal; and selecting one of the plurality of digital components based on the scores of the plurality of digital components and the second scores.

[0019] Certain embodiments of the subject matter described in this specification may be implemented to achieve one or more of the following advantages. Storing and retrieving content from a repository on a client device reduces the amount of data retrieved from a content server, thereby preventing a degradation in the user experience due to overuse of resources of the client device. For example, content requests may be faster, battery consumption may be reduced, network consumption may be reduced, and response times may be faster when a user interacts with displayed content. User privacy may be improved because private third-party data does not need to be shared with a content server.

[0020] The details of one or more embodiments of the subject matter described in this specification are set forth in the accompanying drawings and the following description. Other features, aspects, and advantages of the subject matter will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a block diagram of an example environment in which a server distributes digital components to client devices in a privacy-preserving manner.

[0022] Figure 2 is a block diagram of an example environment in which a client device selects a digital component.

[0023] Figure 3 is a block diagram of an example environment in which a server distributes digital components to client devices in a privacy-preserving manner.

[0024] Figure 4 is a block diagram of an example environment in which a client device selects a digital component.

[0025] Figure 5 is a graph of the example embedding space.

[0026] Figure 6 is a diagram of an example environment that includes a two-tower model.

[0027] Figure 7 is a diagram of an example environment illustrating relationships between applications.

[0028] Figure 8 is a graph of the example embedding space.

[0029] Fig. 9is a flow chart of an example process for selecting and providing a digital component for display at a client device in a privacy-preserving manner.

[0030] Fig.10 is a block diagram of an example computer system.

[0031] Like reference numbers and designations in the various drawings indicate like elements. DETAILED DESCRIPTION

[0032] In general, this document describes systems and techniques for selecting digital content for storage in an on-device repository. The on-device repository can protect user privacy and confidential data of content providers while efficiently using storage space on the user's device. Digital content can be added to the repository based on signals from applications on the device. Applications can request digital content based on user information accessible to the application to receive the relevant digital content.

[0033] For example, the application has a first-party relationship with the user, in which case the application knows how the user interacts with the application. If the application has sufficient permissions, the application can send the user information to the content server. The digital content can be requested asynchronously with the latency critical path. For example, the digital content can be requested when the application is not displayed on the device and / or before the user opens the application and makes a content request.

[0034] Figure 1 1 is a block diagram of an example environment 100 in which a server 120 distributes digital components to client devices 110 in a privacy-preserving manner. Environment 100 includes a data communication network 105, such as a local area network (LAN), a wide area network (WAN), the Internet, a mobile network, or a combination thereof. Data communication network 105 connects one or more client devices 110 to server 120. Server 120 may include multiple computing devices (e.g., a cloud environment). Server 120 may include digital component providers, supply-side platforms (SSPs), and / or demand-side platforms (DSPs). Network 105 may connect various content platforms to each other.

[0035] The client device 110 is an electronic device capable of communicating over the network 105. Example client devices 110 include personal computers, server computers, mobile communication devices (e.g., smart phones and / or tablet computers), and other devices that can send and receive data over the network 105. The client device may also include a digital assistant device that accepts audio input through a microphone and outputs audio output through a speaker. When the digital assistant detects a "hot word" or "hot phrase" that activates the microphone to accept audio input, the digital assistant can be placed in a listening mode (e.g., ready to accept audio input). The digital assistant device may also include a camera and / or a display to capture images and present information visually. The digital assistant may be implemented in different forms of hardware devices (including wearable devices (e.g., watches or glasses), smart phones, speaker devices, tablet devices, or other hardware devices). The client device may also include a digital media device, such as a streaming device that is inserted into a television or other display to stream video to a television, a gaming system, or a virtual reality system.

[0036] The client device 110 may include applications 112, such as a web browser and / or native applications, to facilitate sending and receiving data over the network 105. Native applications are applications developed for a specific platform or a specific device (e.g., a mobile device with a specific operating system). Although operations may be described as being performed by the client device 110, such operations may be performed by the application 112 running on the client device 110.

[0037] Application 112 can present electronic resources, such as web pages, application pages, or other application content, to a user of client device 110. The electronic resource may include a digital component slot for presenting a digital component with the content of the electronic resource. A digital component slot is an area of ​​an electronic resource (e.g., a web page or application page) for displaying a digital component. A digital component slot may also refer to a portion of an audio and / or video stream (which is another example of an electronic resource) for playing a digital component.

[0038] Electronic resources are also referred to herein as resources. For the purposes of this document, a resource may refer to a web page, an application page, application content presented by a native application, an electronic document, an audio stream, a video stream, or other appropriate types of electronic resources that can be used to present a digital component.

[0039] As used throughout this document, the term "digital component" refers to a discrete unit of digital content or digital information (e.g., a video clip, an audio clip, a multimedia clip, an image, text, or another unit of content). A digital component may be electronically stored in a physical memory device as a single file or in a collection of files, and a digital component may take the form of a video file, an audio file, a multimedia file, an image file, or a text file and include advertising information, such that an advertisement is a type of digital component. For example, a digital component may be content that is intended to supplement the content of a web page or other resource presented by application 112. More specifically, a digital component may include digital content that is related to resource content (e.g., a digital component may relate to the same subject as the web page content, or relate to a related subject). The provision of a digital component may therefore supplement and generally enhance the web page or application content.

[0040] When application 112 loads a resource including a digital component slot, application 112 generates a digital component request that requests a digital component for presentation in the digital component slot. In some implementations, the digital component slot and / or the resource may include code (e.g., a script) that causes application 112 to request a digital component from server 120.

[0041] The client device 110 may use several signals to provide digital components through the application 112. The signals may include first-party signals, third-party signals, contextual signals, and privacy-safe signals. The client device 110 may include signals 114 specific to the application 112 (e.g., how the user interacts with the application 112) and signals 116 including cross-application data. The signals 114 may include first-party signals and contextual signals.

[0042] First-party signals may include data collected by an application based on how a user interacts with the application. First-party signals may be limited to applications that collect data. For example, when a user opens a first application, the first application has access to the actions performed by the user and the content presented to the user. First-party signals may include a sequence of actions performed by the user. For example, a sequence of actions may include clicking a link on a first page to request a second page, and clicking a link on the second page. First-party signals may include information about how different users interact with the current user of the application. First-party signals may include other applications that the user interacts with through the first application. First-party signals may include interactions between applications and content servers. For example, when an application requests content when the content server does not have access to the first-party signal, the first-party signal may be provided to the content server. First-party signals may have a historical dimension. For example, an application may use a first-party identifier to store interaction data for a previous time period (e.g., the past seven days, fourteen days, one year).

[0043] The contextual signal may include the action that the user is performing at a certain moment. The contextual signal may be associated with a content provider. For example, the contextual signal may include the content that the user is currently viewing in the application. The contextual signal may describe the environment in which the selected digital component will be presented. The contextual signal may include, for example, coarse location information indicating the approximate location of the client device 110, the resource (e.g., a website or native application) that will be presented with the selected digital component, the spoken language setting of the application 112 or the client device 110, the number of digital component slots in which the digital component will be presented with the resource, the type of digital component slot, and / or other appropriate contextual information.

[0044] Signal 116 may include a privacy-safe signal and a third-party signal. A privacy-safe signal may include any data that leaves the device in some form. In some examples, a privacy signal may include a private user signal with noise that is applied to anonymize the user associated with the data. A privacy-safe signal may include cross-publisher or per-device data that can be exposed to a content server in some form. Certain cross-site or cross-added information, although sensitive, can still be rendered securely by adding some noise to it. The noise may include differential private noise. Adding noise can increase the uncertainty of what operations the user has performed, so that the user's actual actions improve privacy. For example, a privacy-safe signal may indicate that the user has accessed a particular application. However, the noise in the signal introduces uncertainty that the user may not actually have access to the particular application.

[0045] Third-party signals may include data collected across different applications. For example, third-party signals may include a sequence of actions performed using different applications. The sequence of actions may include interaction with a first application, a second application, a third application, and then again with the first application. Third-party signals may include cross-application information that is considered privacy-sensitive (e.g., user sensitive data) because there is a privacy expectation that a content server should not know that a user is interacting with different applications.

[0046] The third-party signal may include, for example, data identifying a user group that includes the user as a member. The user group may include interest-based groups. Each interest-based group may include a subject of interest and a collection of members identified (e.g., determined or predicted) as being interested in the subject. The user group may also include, for example, a group of users who have performed a specific action using the publisher's electronic resources (e.g., a website or native application). For example, the user group may include users who have visited a website, requested more information about an item, interacted with a specific digital component (e.g., selected a specific digital component), and / or added an item to a virtual shopping cart to potentially acquire the item. The user data of a user may also include user profile data and / or attributes of the user.

[0047] In addition to the description throughout this document, controls (e.g., user interface elements with which the user can interact) may be provided to the user to allow the user to make choices about whether and when the systems, programs, or features described herein may collect user information (e.g., information about the user's social network, social actions or activities, occupation, the user's preferences, or the user's current location) and whether to send content or communications from a server to the user. In addition, certain data may be processed in one or more ways before it is stored or used so that personally identifiable information is removed. For example, the user's identity may be processed so that the user's personally identifiable information cannot be determined, or the user's geographic location in which location information is obtained may be generalized (such as to a city, zip code, or state level) so that the user's specific location cannot be determined. Thus, the user can control what information is collected about the user, how the information is used, and what information is provided to the user or others (e.g., third parties).

[0048] Figure 1 Stages A–F in ​​show an example process for selecting and providing digital components for presentation at client device 110 , which shows the flow of data between components of environment 100 .

[0049] In phase A, application 112 running on client device 110 sends a digital component request to server 120. As described above, application 112 may send a digital component request for a digital component to be presented in a digital component slot of a resource being presented by application 112. In some implementations, the digital component slot and / or resource may include code (e.g., a script) that causes application 112 to request a digital component from server 120. The digital component request sent by client device 110 may include a first-party signal, a contextual signal, and a privacy-safe signal. The digital component request may be sent asynchronously with a request for content from a user. For example, application 112 may request content before a user views the content through an application. The digital component request may be sent during a period when client device 110 is charging and / or connected to a non-metered connection.

[0050] Server 120 may be implemented using one or more server computers (or other appropriate computing devices), which may be distributed across multiple locations. In general, server 120 receives a request for a digital component from client device 110, selects a digital component from digital component repository 130 based on data included in the request, and sends the selected digital component to client device 110.

[0051] As described in more detail below, the server 120 may select a digital component from a collection of digital components stored in a digital component repository 130 and / or a collection of digital components received from an SSP. The digital component repository 130 stores digital components received from content platforms (e.g., from SSPs and DSPs) and additional data (e.g., metadata) for each digital component. The metadata for a digital component may include, for example, distribution criteria and / or selection parameters that define the circumstances under which a digital component is eligible to be provided to a client device 110 in response to a digital component request received from a client device 110, the selection parameters indicating the amount to be provided to a publisher if the digital component is displayed with a publisher's resource and / or a user interacts with it when it is presented. For example, the distribution criteria for a digital component may include location information indicating a geographic location in which the digital component is eligible to be presented, user group membership data identifying a user group to which the digital component is eligible to be presented, resource data identifying a resource with which an electronic resource is eligible to be presented, and / or other appropriate distribution criteria. The distribution criteria may also include negative criteria, for example, criteria indicating circumstances under which a digital component is not eligible (e.g., with a specific resource or in a specific location). Other data that can be used to select a digital component may also be stored in the digital component repository along with a reference to its digital component (eg, a link or as metadata).

[0052] SSP is a technology platform implemented in hardware and / or software that automates the process of obtaining digital components of resources. Publishers of resources can use SSP to manage the process of obtaining digital components of digital component slots of their resources. Each publisher can have a corresponding SSP or multiple SSPs. Some publishers can use the same SSP.

[0053] A DSP is a technology platform implemented in hardware and / or software that automates the process of distributing digital components for presentation with resources and / or applications. A DSP may interact with multiple supply-side platforms (SSPs) on behalf of digital component providers to provide digital components for presentation with resources of multiple different publishers. A digital component provider may create (or otherwise publish) a digital component that is presented in a digital component slot of a publisher's resource.

[0054] In phase B, server 120 queries digital component repository 130 for a user-based set of digital components selected based on user data of digital component requests. For example, server 120 may submit a query that defines the user data of digital component requests as a condition of the query. The user data may include first-party signals, contextual signals, and privacy-safety signals from requests received from application 112. In some implementations, the query may also include context-based conditions. For example, the query may request retrieval of digital components that include a specific user group and / or a specific geographic location as distribution criteria.

[0055] In phase C, server 120 receives a set of user-based digital components and selection parameters of each user-based digital component from digital component repository 130. The set of user-based digital components may include user-based digital components having distribution criteria that match the conditions of the query.

[0056] The selection engine 122 of the server 120 selects digital components to provide to the application 112 for presentation in the digital component slot. For example, the selection engine 122 can select digital components from a set of context-based digital components and a set of user-based digital components. The selection engine 122 can select digital components from the two sets based on selection parameters of each digital component in the two sets. For example, the selection engine 122 can select a certain number of digital components with the highest selection parameters based on the signal available to the selection engine 122.

[0057] In some implementations, the selection engine 122 can filter digital components and / or selection parameters based on publisher controls specified by the publisher of the resource being presented by the application 112. In a specific example, a publisher of a web page about a particular event can define as a publisher control that digital components related to another event may not be presented with the web page. The selection engine 122 can filter based on rules or other data provided by the publisher.

[0058] In stage D, server 120 provides the selected digital component to client device 110. Client device 110 stores the digital component received from server 120 in digital component repository 118. Digital component repository 118 may store digital components received from multiple content platforms (e.g., digital components received in response to requests from different applications on client device 110). For example, when selection engine 122 selects a digital component, server 120 may transmit the digital component to client device 110. In some examples, selection engine 122 may forward the selection value received from the SSP to client device 110. Client device 110 may add the digital component to digital component repository 118.

[0059] In stage E, application 112 queries digital component repository 118 for a digital component to be presented in a digital component slot of a resource being presented by application 112. In some implementations, the query may include signal 114. Although shown after stages A through D, application 112 may query digital component repository 118 in parallel with one or more of stages A through D to reduce latency in selecting and providing a digital component.

[0060] In phase F, the application 112 receives the digital component. The digital component may be selected based on the signals 114 and 116. In some implementations, the digital component may be selected based on the number of times each digital component is provided to the client device 110 in response to a request to the content server. For example, a given digital component may be received multiple times at the client device (e.g., in response to requests from different applications on the client device 110). A score may be assigned to a given digital component based on the number of times the given digital component is received. The client device 110 may select the digital component based on the score of each digital component stored in the digital component repository 118. In some implementations, the digital component may be selected based on a combination of the number of times each digital component is received and at least one of the signals 114 or 116. For example, the score of each digital component, the signal 114, and the signal 116 may be input into a trained model that outputs the selected digital component. The client device 110 may then render the digital component using the resource being rendered by the application 112.

[0061] Generally, better digital components that are more relevant (e.g., more targeted to a particular user, more contextually similar to an application) will be selected by using more available data signals. That is, more data about a particular request can result in a more informed selection of digital components. However, not all data sources can be used when protecting privacy with on-device content selection. By using first-party, contextual, and privacy-safe data, performance can be improved while protecting privacy. This protects user privacy and data security, especially when compared to techniques that use third-party cookies to send user data across the Internet.

[0062] Figure 2 2 is a block diagram of an example environment 200 in which a client device 210 selects a digital component. The environment 200 includes the client device 210 and a server 220, such as a multi-platform server. More than one client device may be included in the environment 200. For example, the server 220 may be similar to ( Figure 1 The example environment 200 includes a client device 210 (e.g., similar to the Figure 1 The client device 110 is shown connected to a data communication network 205 (e.g., similar to Figure 1 The data communication network 105 shown).

[0063] The client device 210 includes a selection engine 214 and a digital component repository 218 (e.g., similar to Figure 1 The selection engine 214 may receive requests for digital components from applications 212a and 212b. The requests may include first-party signals and context signals. The selection engine 214 may determine a privacy-safe signal based on data received from applications 212a and 212b. The selection engine 214 may use the privacy-safe signal to send a central request to the digital components from the server 220. The central request may include requests for digital components for multiple applications on the client device 210.

[0064] Using the privacy-safe signal may avoid sharing private third-party data with the server 220. For example, cross-application data such as the number of times a user has opened applications 212a and 212b may be saved on the client device 210. The privacy-safe signal also avoids the need for the selection engine 214 to share first-party data and contextual data received from different applications, since that data becomes third-party cross-application data when shared with the server 220. The selection engine 222 of the server 220 may select a set of digital components from the digital component repository 230 using the privacy-safe signal.

[0065] The client device 210 may receive the digital components from the server 220 and store the digital components in the digital component repository 218. The selection engine 210 may determine the digital components from the digital component repository 218 for presentation in the applications 212a and 212b based on the first-party signals and contextual signals received from the applications as well as the third-party signals and privacy-safety signals.

[0066] Figure 3 3 is a block diagram of an example environment 300 in which a server 320 distributes digital components to a client device 310 in a privacy-preserving manner. The environment 300 includes a client device 310 and a server 320, such as a multi-platform server. For example, the server 320 may be similar to ( Figure 1 The example environment 300 includes a client device 310 (e.g., similar to the Figure 1 The client device 110 is shown connected to a data communication network 305 (e.g., similar to Figure 1 The data communication network 105 shown).

[0067] Client device 310 includes applications 312a and 312b, selection engine 314, and digital component repository 318. The content presented on applications 312a and 312b can include personalized signals. The presented content is based on the content that the user interacts with. The user's first-party interaction with the application and the contextual content shown within the application can be considered as personalized signals. Each application on client device 310 can use the signals available to it to refine the selected content asynchronously with the content request on a per-application basis.

[0068] The content selected by each application refinement can be stored in the digital component repository 318 to provide digital components across multiple applications. The digital component repository 318 may include a centralized repository that acts as a cache on the client device 310. The collection of digital components associated with each application allows the creation of a personalized advertising repository without leaking third-party information. The digital component repository 318 may have fixed storage and may be updated so that the data is not outdated. For example, when a digital component is received from the server 320 based on a request from the client device 310, the digital component repository 318 may be updated. The selection engine 314 may include a rating system to save the highest ranked content in the digital component repository 318 and remove the lowest ranked content when the digital component repository 318 is full.

[0069] Applications 312a and 312b can use first-party signals, contextual signals, and privacy-safe signals to request content from server 320. Requests can be asynchronous with latency-critical paths. For example, applications 312a and 312b can request content before a user views the content through an application. Each application on client device 310 can request content at different time intervals. Therefore, content can be retrieved without interfering with the use of client device 310 (e.g., the retrieval process uses only a small portion of processing power, memory, and network bandwidth). Selection engine 322 of server 320 can select digital components from digital component repository 330 using signals included in the request from the application. Digital components received by applications 312a and 312b can be used to update digital component repository 318. The content received by each application from server 320 can be stored in a central repository.

[0070] Because selection engine 314 can access cross-domain rating information, the quality of content from digital component repository 318 can be more relevant (e.g., more targeted to a particular user, more contextually similar to an application) than content from server 320. Content refinement selection can result in an on-device repository that includes content based on user interactions across all applications. Because each application is responsible for refinement of content selection, each application notifies server 320 of all signals available to the application, including any personalized signals that the application has collected that would otherwise be considered sensitive information when used in a cross-application manner.

[0071] The selection engine 314 may include a scoring mechanism. For example, when a request is made from application 312a to server 320, the server may recommend a first group of digital components, a second group of digital components, and a third group of digital components. When application 312b makes a request to the server at some other time, server 320 may use the first-party information from application 312b to select the first group of digital components, the fourth group of digital components, and the fifth group of digital components. All groups of digital components may be added to the digital component repository 318. The first group of digital components may be ranked higher and have a higher retention priority because both applications have received the first group of digital components. In some examples, a third application on client device 310 may receive the first group of digital components, the third group of digital components, and the fifth group of digital components. The first group of digital components may be ranked highest because it has been received three times. The third and fifth groups of digital components may be ranked higher than the second and fourth groups of digital components because the third and fifth groups of digital components have been received twice, while the second and fourth groups of digital components have been received once.

[0072] The digital component repository 318 can remove digital components after reaching a threshold. For example, the threshold can be based on the storage space allocated for the repository and / or the number of digital components to be stored on the client device. The digital component with the lowest ranking can be discarded.

[0073] Server 320 may determine the number of digital components to send to client device 310 based on the number of digital components that digital component repository 318 can store. For example, the number of digital components to download may be calculated as the number of digital components that the device can store divided by the number of applications that displayed digital components to server 320 during the time period. Application-specific behavior may be used to calculate the number of digital components during the time period. For example, the application-specific behavior may include an indication that a user who visits application 312a typically does not visit application 312b. In some examples, a user who visits application 312a typically only visits application 312a and another given application.

[0074] In some implementations, the content server 320 may maintain a collection of digital components of a number that matches the number of digital components that can be stored in the digital component repository 318. The content server 320 may provide an embedding representing the digital component being extracted. After extraction, the content server 320 may generate an embedding on the device 310 using an on-device model with all device signals. For example, the embedding may be determined using a multi-tower approach. The selection engine 314 may include a model that may perform a dot product and a truncation of the first several digital components for the generated embedding (e.g., including all on-device signals) and the embedding associated with the candidate digital component. The truncation number of digital components may be tuned for the nearest neighbor to match the number of digital components that can be stored in the digital component repository 318 so that the device 310 never has more than that number of digital components from the server at a given time.

[0075] The server 320 receives requests from different applications at different times and therefore has no knowledge of the user's cross-domain, cross-application navigation. This improves privacy because the server is unaware of the different applications on the user's device and how the user interacts with the applications. First-party information from only one application is provided to the server at a time. Each application can request content asynchronously and during the uninstall time outside the latency critical path of providing content to the user.

[0076] The selection engine 314 can use cross-application activity and a rating system to select content on the device. A more efficient content system can be created on the device for future service provision while protecting privacy. Once the digital component is on the device, when a request is made (e.g., when a user accesses an application), the selection engine 314 can select the highest ranked digital component from the digital component repository 318. As the user interacts with the application on the client device, the first-party information can change, and each application can continue to download content asynchronously. The digital component repository 318 can be updated as new content is downloaded. As user behavior changes over time, the digital component repository 318 can also change and become more suitable for the user. The updated ranking of the content in the repository can be completed entirely on the user device.

[0077] In some implementations, content providers may request that their content not be shown on certain pages or applications. For example, content provided by server 320 may include information that the content cannot be presented with vile or offensive content. Selection engine 314 may check the conditional restrictions of all content in digital component repository 318 when selecting digital components. For example, if an application with vile or offensive content requests a digital component, and the top-ranked digital components are restricted from being displayed with vile or offensive content, the top-ranked digital components without such restrictions may be provided to the application.

[0078] In some implementations, the selection engine 314 may include a trained model that selects digital components based on quality. For example, the available signal may be input into the model to determine the digital components to provide to the application. In some implementations, the quality score may be combined with the number of times the content has been received to select the digital component.

[0079] Figure 4 4 is a block diagram of an example environment 400 in which a client device 410 selects a digital component. The environment 400 includes the client device 410 and a server 420, such as a multi-platform server. For example, the server 420 may be similar to ( Figure 1 ) server 120 as shown.

[0080] Application 412a running on client device 410 sends request 432 to server 420. For example, application 412a may have access to user signals that are extremely useful for content refinement selection. A single user on the device may have visited articles about football teams and articles about how certain supplements can help health within application 412a. These signals would otherwise contain sensitive information when joined across multiple applications using a shared ID. However, when not joined, these signals can be sent to server 420 to improve content refinement selection while maintaining user privacy.

[0081] Server 420 may respond to request 432 with digital component 434. For example, server 420 may use signals included in request 432 to select digital component 434. For example, the signals may include first-party signals, contextual signals, and privacy-safe signals. Server 420 may use the received signals to rank the digital components in order to select a content-driven digital component.

[0082] The repository 418 may be updated with digital components 434. The repository 418 of personalized digital components may be used in conjunction with other privacy-centric approaches for selecting digital components. For example, the repository may be used with matching in Batch Private Information Retrieval, Private Nearest Neighbor, and / or Private Compute Backend (Trusted Server - OAK). The client device 410 may use all available user data to determine the final ranking of digital components using on-device modeling.

[0083] Application 412b running on client device 410 sends request 436 to server 420. Request 436 may include signals related to how the user interacts with application 412b. Server 420 may respond to request 436 with digital component 438. For example, server 420 may use the signal included in request 436 to select digital component 436. Repository 418 may be updated with digital component 438.

[0084] Application 412c running on client device 410 sends request 440 to selection engine 414. Selection engine 414 may determine the highest ranked digital component and send request 442 to repository 418 of digital components. Selection engine 414 may receive digital component 444. Selection engine 414 may send highest ranked digital component 446 to application 412c.

[0085] Figure 5 506a-506j。

[0086] During the digital component service, a dot product of the embedding may be performed to score each of the candidate digital component embeddings 506a-506j, and the candidate digital component embeddings 506a and 506b included in the plurality of nearest neighbors 504 may be selected. The user signal may be embedded into the embedding space during content retrieval on the device (e.g., asynchronously with the ad retrieval call, during the ad retrieval call). In some implementations, the user signal embedding may exist in a separate embedding space. For a model that has been optimized using dot product similarity, a relationship between the user signal embedding and the digital component embedding may be established. The K nearest neighbors may select the first k nearest neighbors from a joint embedding space including both the digital component embedding space and the user signal embedding space. The nearest neighbor to the user signal embedding in the joint embedding space may be found. A similarity metric may be defined for the distance between the user signal embedding and the digital component embedding in the joint embedding space. The similarity metric allows the digital component embedding that is closest to the user signal embedding to be found. In some implementations, the similarity metric may be determined using the dot product similarity of the output scalar value. For example, user_s ignals_embedding·digital_component_1_embedding=10. In some examples, user_s ignals_embedding·digital_component_2_embedding=20. The more similar the embeddings, the higher the dot product similarity can output. For example, when K=1 to select the nearest neighbor, digital_component_2 can be selected because the dot product similarity between the user signal embedding and the digital component embedding 2 produces the highest similarity score of 20.

[0087] Figure 6 6 is a diagram of an example environment 600 including a twin tower model. The environment 600 includes a first model 610 and a second model 620. The first model 610 and the second model 620 can be trained to select digital components with which a user is more likely to interact. The training data can include digital components displayed to the user and user interactions (e.g., clicks) with the digital components. The first model 610 can receive a query 612 as input and output an embedding 614. The second model 620 can receive a query 622 as input and output an embedding 624. The embeddings 614 and 624 can be determined using a transformation to a model interpretable embedding space applied to an input signal (e.g., a user signal, a digital component signal). For example, the embedding 614 can correspond to the digital component signal, and the embedding 624 can correspond to the query signal (e.g., a user signal, a context signal). The first model 610 can encode digital component features into the embedding, and the second model 620 can encode query (user + context) features into the embedding. A digital component can produce a digital component embedding, and a query can produce a query embedding.

[0088] Embeddings 614 and 624 may be used to compute a dot product 630. The dot product may be computed as embedding 614*embedding 624 to produce a scalar value representing the similarity between the two embeddings. During serving or inference, the dot product between the embeddings may be used to produce a similarity score. The higher the similarity score, the better the match of the candidate digital component to the query. The dot product 630 may be used to select a digital component to send to the application. The input may include contextual data, first-party user behavior data, and noisy aggregated user behavior data.

[0089] Figure 7 is a diagram of an example environment 700 illustrating relationships between applications. Environment 700 includes applications AF. Historical data about aggregated application usage behavior can be used as input to the model to select digital components. Historical data can include aggregated cross-application information. For example, historical data can include an indication that a user typically visits applications B and C in the same week that the user visits application A. Historical data can be presented as a graph in which nodes are applications and edges are historical frequencies of users visiting both a first application and another application on a single device in aggregate over a period of time. An edge between application A and application B can include a value of 4 indicating the frequency with which the user visited application A and also visited application B. An edge between application A and application C can include a value of 2 indicating the frequency with which the user visited application A and also visited application C. There may be no edge between application A and application D, indicating that the user did not visit application A and application D within the time period. An edge between application A and application E can include a value of 8 indicating the frequency with which the user visited application A and also visited application E. An edge between application A and application F can include a value of 1 indicating the frequency with which the user visited application A and also visited application F.

[0090] Figure 8 is a diagram of an example embedding space 800. The embedding space 800 includes an average feature embedding 802, query feature embeddings 808a-808c, multiple nearest neighbors 804, and candidate digit component embeddings 806a-806j.

[0091] The embedding space 800 may include data accumulated using privacy-safe aggregate reporting, or data from voluntary panel data contributions where users opt-in and have the DSP collect data. The average feature embedding 802 may indicate that for a given first-party application (application 1) that is currently making digital component requests, applications 2 and 3 are also typically used by users who use application 1 (e.g., in aggregated behavior). This information may be obtained from users who voluntarily contribute third-party data using panel data collection and / or from aggregate reports. The average feature embedding 802 may include the average of all different query embeddings for each of the applications. When a digital component request includes only first-party data, the average feature embedding 802 may be used so that specific third-party information can be used through aggregate reporting and / or panel-based data collection to help customize better digital components sent down to the device. The top several closest nodes may be selected, and signals about those applications may be fed into the dual-tower model to enable better digital component retrieval. This same approach may be used for application similarity.

[0092] Fig. 9 is a flow chart of an example process 900 for providing a digital component for display at a client device in a privacy-preserving manner. The operations of process 900 may be performed by, for example Figure 1 The operations of process 900 may also be implemented as instructions stored on one or more computer-readable media that may be non-transitory, and execution of the instructions by one or more data processing devices may cause the one or more data processing devices to perform the operations of process 900.

[0093] A computing device receives a plurality of digital components from one or more content platforms. Each of the digital components corresponds to user data associated with at least a first application executed on a client device (910). The plurality of digital components may be received in response to a request from the first application. The user data associated with at least the first application may include at least one of first-party data, contextual data, or privacy-safe data. The user data associated with at least the first application may include a sequence of actions performed by a user using a second application.

[0094] The computing device stores the plurality of digital components in a repository on the client device (920). The repository may store digital components received from the content platform in response to requests from a plurality of applications executing on the client device. For example, a second plurality of digital components may be received in response to a request from a third application on the client device.

[0095] The computing device determines a score for each digital component in the plurality of digital components stored in the repository based on the number of times the digital component has been received (930). The score may be determined by scoring a first digital component included in both the first subset of the plurality of digital components and the second subset of the plurality of digital components higher than a second digital component not included in both the first subset of the plurality of digital components and the second subset of the plurality of digital components.

[0096] The computing device receives a request for digital content for presentation in a second application executed on the client device (940). The second application is different from the first application. The request for digital content for presentation in the second application may include user data.

[0097] The computing device selects one of the plurality of digital components based on the scores of the plurality of digital components (950).The digital component may be selected based on user data.

[0098] The computing device provides the selected one of the digital components for presentation in the second application (960).

[0099] Fig.10 1 is a block diagram of an example computer system 1000 that can be used to perform the operations described above. System 1000 includes a processor 1010, a memory 1020, a storage device 1030, and an input / output device 1040. Each of components 1010, 1020, 1030, and 1040 can be interconnected, for example, using a system bus 1050. Processor 1010 is capable of processing instructions for execution within system 1000. In some implementations, processor 1010 is a single-threaded processor. In another implementation, processor 1010 is a multi-threaded processor. Processor 1010 is capable of processing instructions stored in memory 1020 or on storage device 1030.

[0100] The memory 1020 stores information within the system 1000. In one implementation, the memory 1020 is a computer-readable medium. In some implementations, the memory 1020 is a volatile memory unit. In another implementation, the memory 1020 is a non-volatile memory unit.

[0101] The storage device 1030 can provide mass storage for the system 1000. In some implementations, the storage device 1030 is a computer-readable medium. In various implementations, the storage device 1030 may include, for example, a hard disk device, an optical disk device, a storage device shared by multiple computing devices over a network (e.g., a cloud storage device), or some other mass storage device.

[0102] In some embodiments, one or more elements of client device 110 (e.g., application 112, signal 114, signal 116, digital component repository 118), one or more elements of client device 210 (e.g., applications 212a and 212b, selection engine 214, digital component repository 218), one or more elements of client device 310 (e.g., applications 312a and 312b, selection engine 314, digital component repository 318) and / or one or more elements of client device 410 (e.g., applications 412a-412c, selection engine 414, digital component repository 418) may be included in at least one memory 1020 and / or at least one storage device 1030.

[0103] The input / output device 1040 provides input / output operations for the system 1000. In some implementations, the input / output device 1040 may include one or more of a network interface device (e.g., an Ethernet card), a serial communication device (e.g., an RS-232 port), and / or a wireless interface device (e.g., and an 802.11 card). In another implementation, the input / output device may include a driver device configured to receive input data and send output data to an external device 1060 (e.g., a keyboard, a printer, and a display device). However, other implementations may also be used, such as a mobile computing device, a mobile communication device, a set-top TV client device, etc.

[0104] Despite Fig.10 An example processing system is described in the specification, but the subject matter and implementation of the functional operations described in this specification may be implemented in other types of digital electronic circuit systems or in computer software, firmware or hardware (including the structures disclosed in this specification and their structural equivalents), or in a combination of one or more of them.

[0105] The embodiments of the subject matter and operations described in this specification may be implemented in a digital electronic circuit system or in computer software, firmware or hardware (including the structures disclosed in this specification and their structural equivalents), or in a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, that is, one or more modules of computer program instructions, which are encoded on multiple computer storage media (or one computer storage medium) for data processing equipment to execute or control the operation of data processing equipment. Alternatively or additionally, program instructions may be encoded on an artificially generated propagation signal (e.g., a machine-generated electrical, optical or electromagnetic signal), which is generated to encode information for transmission to a suitable receiver device for data processing equipment to execute. The computer storage medium may be a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of them, or be included in them. In addition, although the computer storage medium is not a propagation signal, the computer storage medium may be the source or destination of the computer program instructions encoded in the artificially generated propagation signal. The computer storage medium can also be, or be included in, one or more separate physical components or media (eg, multiple CDs, disks, or other storage devices).

[0106] The operations described in this specification can be implemented as operations performed by a data processing apparatus on data stored on one or more computer-readable storage devices or received from other sources.

[0107] The term "data processing device" covers all kinds of equipment, devices and machines for processing data, including, for example, a programmable processor, a computer, a system on a chip, or a plurality of the foregoing or a combination of the foregoing. The device may include a dedicated logic circuit system, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit). In addition to hardware, the device may also include code that creates an execution environment for the computer program in question, for example, code that constitutes processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or a combination of one or more of them. The device and the execution environment can implement a variety of different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0108] A computer program (also referred to as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages; and it may be deployed 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. A computer program may, but does not necessarily, correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or portions of code). A computer program may be deployed to execute on one computer or on multiple computers located at one site or distributed over multiple sites and interconnected by a communications network.

[0109] The processes and logic flows described in this specification may be performed by one or more programmable computers executing one or more computer programs to perform actions by operating on input data and generating output. The processes and logic flows may also be performed by, and the apparatus may also be implemented as, a special purpose logic circuit system, such as an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0110] Processors suitable for executing computer programs include, for example, both general-purpose microprocessors and special-purpose microprocessors. In general, the processor will receive instructions and data from a read-only memory or a random access memory or both. The basic elements of a computer are a processor for performing actions according to instructions and one or more memory devices for storing instructions and data. In general, a computer will also include one or more mass storage devices for storing data, such as a magnetic disk, a magneto-optical disk, or an optical disk, or operatively coupled to receive data from the one or more mass storage devices or transfer data to the one or more mass storage devices or both. However, a computer does not have to have such devices. In addition, a computer may be embedded in another device, such as 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 (e.g., a universal serial bus (USB) flash drive), to name a few. Devices suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks (e.g., internal hard disks or removable disks); magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0111] To provide interaction with a user, embodiments of the subject matter described in this specification may be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user, and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including sound, voice, or tactile input. In addition, the computer may interact with the user by sending documents to and receiving documents from a device used by the user; for example, by sending a web page to a web browser on a user's client device in response to a request received from the web browser.

[0112] Embodiments of the subject matter described in this specification may be implemented in a computing system that includes a back-end component (e.g., as a data server), or includes a middleware component (e.g., an application server), or includes a front-end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described in this specification), or any combination of one or more such back-end, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include local area networks ("LANs") and wide area networks ("WANs"), interconnected networks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).

[0113] A computing system may include a client and a server. The client and server are usually remote from each other and typically interact through a communication network. The relationship of client and server arises from computer programs running on respective computers and having a client-server relationship with each other. In some embodiments, the server transmits data (e.g., an HTML page) to a client device (e.g., for the purpose of displaying data to a user interacting with the client device and receiving user input from the user). Data generated at the client device (e.g., the result of a user interaction) may be received from the client device at the server.

[0114] Although this specification contains many specific implementation details, these details should not be interpreted as limitations on the scope of any invention or the scope that may be claimed, but should be interpreted as descriptions of features that are unique to specific embodiments of specific inventions. Certain features described in the context of separate embodiments in this specification may also be implemented in combination in a single embodiment. On the contrary, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments. In addition, although features may be described above as working in certain combinations and even initially claimed as such, one or more features from the claimed combination may be deleted from the combination in some cases, and the claimed combination may involve changes in sub-combinations or sub-combinations.

[0115] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that such operations be performed in the particular order shown or in a continuous order, or that all of the operations shown be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0116] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions set forth in the claims can be performed in different orders and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

Claims

1. A computer-implemented method comprising: receiving, by a client device, a plurality of digital components from one or more content platforms, wherein each of the digital components corresponds to user data associated with at least a first application executing on the client device; storing, by the client device, the plurality of digital components in a repository on the client device; determining, by the client device, a score for each of the plurality of digital components stored in the repository, wherein the determining is based on a number of times the digital component has been received; receiving, by the client device, a request for digital content for presentation in a second application executing on the client device, wherein the second application is different from the first application; selecting, by the client device, one of the plurality of digital components based on the scores of the plurality of digital components; and The selected one of the digital components is provided by the client device for presentation in the second application.

2. The computer-implemented method of claim 1, wherein: The plurality of digital components are received in response to a request from the first application, and the method further comprises: A second plurality of the digital components is received in response to a request from a third application on the client device.

3. The computer-implemented method of claim 2, wherein: Scoring each of the plurality of digital components stored in the repository includes scoring a first digital component included in both a first subset of the plurality of digital components and a second subset of the plurality of digital components higher than a second digital component not included in both the first subset of the plurality of digital components and the second subset of the plurality of digital components.

4. The computer-implemented method of claim 1 , further comprising: determining that a number of digital components in the repository on the client device exceeds a predetermined threshold; as well as In response to determining that the number of digital components in the repository on the client device exceeds the predetermined threshold, the digital component with the lowest score is removed from the repository on the client device.

5. The computer-implemented method of claim 1, wherein: The user data associated with at least the first application includes at least one of first-party data, contextual data, or privacy-safe data.

6. The computer-implemented method of claim 1, wherein: The user data associated with at least the first application includes a sequence of actions performed by a user using the second application.

7. The computer-implemented method of claim 1, wherein: The plurality of digital components are received in response to a request to transmit data including the user data associated with at least the first application.

8. The computer-implemented method of claim 1, wherein: The request for the digital content for presentation in the second application includes the user data; and The one of the plurality of digital components is selected based on the user data.

9. The computer-implemented method of claim 1 , further comprising: determining a second score for each of the plurality of digital components stored in the repository, wherein the second score is determined based on at least one of a first-party signal, a third-party signal, or a contextual signal; and The one of the plurality of digital components is selected based on the scores of the plurality of digital components and the second score.

10. A computer-implemented method comprising: receiving, by a server, from a client device, a request for a digital component for presentation by the client device, wherein the request for the digital component includes user data associated with at least a first application executing on the client device; and In response to receiving the request for the digital components, a plurality of digital components are transmitted by the multi-platform server to the client device, wherein each of the digital components corresponds to the user data.

11. A system comprising: one or more processors; as well as One or more storage devices storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method as claimed in any preceding claim.

12. A computer readable medium carrying instructions which, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 1 to 10.

13. A computer program product comprising instructions which, when executed by a computer, cause the computer to perform the steps of the method according to any one of claims 1 to 10.