Integrating User Declarations in Ad Personalization

Abstract

The present technology is generally directed to personalizing a digital component for a user based on a merged preference profile. The merged preference profile may be generated based on the user's declared and inferred preferences. The declared and inferred preferences may be preferences related to brands, topics, types of products, etc. The merged preference profile may be used to personalize the digital component output to the user. For example, when identifying digital components to be selected, at least some of the digital components may be selected based on the user's merged preference profile. At least a portion of the selected digital components may be digital components with subject matter that matches the user's preferences, thereby improving the digital component output to the user.

Description

[Background technology]

[0001] Digital content such as advertisements typically appear alongside organic search results on publisher websites or mobile applications when users perform searches or browse content. Advertisements are typically selected based on optimizing user engagement in an attempt to increase clicks or conversions, with little consideration of users' advertising preferences, such as their explicit preferences. This results in users being served advertisements that do not necessarily align with their preferences. Summary of the Invention [Means for solving the problem]

[0002] The present technology is generally directed to improving digital components output on a publisher's website or mobile application based on a user's merged preference profile. The merged preference profile may be determined based on the user's stated and inferred preferences. The stated and inferred preferences may be preferences related to content subject matter, such as brand, topic, or type of product. The merged preference profile may be used to identify digital components to be selected and provided for output to the user. At least some of the selected digital components may be digital components with subject matter that matches the user's preferences, thereby improving the digital components output to the user.

[0003] One aspect of the present technology is directed to a method including receiving, by one or more processors, a request from a publisher for at least one digital component for display on the publisher's page; determining, by the one or more processors, declared preferences of the user; determining, by the one or more processors, inferred preferences of the user; merging, by the one or more processors, the user's declared and inferred preferences into a merged preference profile, wherein when there is a conflict between the at least one declared preference and the at least one inferred preference, the one or more processors select at least one declared preference to be included in the merged preference profile; identifying, by the one or more processors, at least one digital component related to the merged preference profile; and providing, by the one or more processors, the at least one selected digital component to the publisher for output.

[0004] The method may also include discarding, by the one or more processors, at least one inferred preference that is inconsistent with the at least one declared preference.

[0005] The method may also include reserving, by the one or more processors, display space for one or more selected digital components related to the merged preference profile.

[0006] The user's declared preferences may relate to at least one subject of a digital component previously provided for output. The declared preferences may include at least one of a pure preference declaration or an influenced preference declaration. The inferred preferences may be determined by identifying one or more behaviors toward the subject of content previously provided for output or one or more search queries about the subject of the content.

[0007] Another aspect of the present technology is directed to a computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to receive a request from a publisher for at least one digital component for display on the publisher's page; determine a user's declared preferences; determine the user's inferred preferences; merge the user's declared and inferred preferences into a merged preference profile, wherein when there is a conflict between the at least one declared preference and the at least one inferred preference, select at least one declared preference to be included in the merged preference profile; identify at least one digital component related to the merged preference profile; and provide the at least one selected digital component to the publisher for output.

[0008] Yet another aspect of the present technology is generally directed to a system including one or more processors that may be configured to receive a request from a publisher for at least one digital component for display on the publisher's page, determine a user's declared preferences, determine the user's inferred preferences, merge the user's declared and inferred preferences into a merged preference profile, where, when there is a conflict between the at least one declared preference and the at least one inferred preference, the merged preference profile selects at least one declared preference to be included in the merged preference profile, identify at least one digital component related to the merged preference profile, and provide the at least one selected digital component to the publisher for output. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is an exemplary screenshot showing exemplary content according to aspects of the present disclosure. [Figure 2] FIG. 1 is a flow diagram for an example method for generating a merged preference profile according to aspects of the present disclosure. [Figure 3] 10 is an exemplary screenshot illustrating exemplary inputs for declaring genuine preferences, according to aspects of the present disclosure. [Figure 4] 10 is an exemplary screenshot illustrating exemplary inputs for declaring genuine preferences, according to aspects of the present disclosure. [Figure 5] 10 is an exemplary screenshot illustrating exemplary inputs for declaring influenced preferences, according to aspects of the present disclosure. [Figure 6] 10 is an exemplary screenshot illustrating exemplary content for inferring preferences, according to aspects of the present disclosure. [Figure 7] FIG. 10 is an example flow diagram for an example method for resolving conflicts, according to aspects of the present disclosure. [Figure 8] FIG. 10 is a diagram of an example of a merged preference profile, according to aspects of the present disclosure. [Figure 9] FIG. 10 is an exemplary flow diagram for serving advertisements according to aspects of the present disclosure. [Figure 10] FIG. 1 is a block diagram of an exemplary system according to aspects of the present disclosure. [Figure 11] FIG. 1 is a flow diagram for an exemplary method for selecting a digital component, according to aspects of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0010] The present technology is generally directed to improving a digital component for a user based on a merged preference profile. Improving a digital component for a user may, in some examples, include personalizing the digital component for the user. The merged preference profile may be generated based on the user's declared and inferred preferences. The declared and inferred preferences may be preferences related to brands, topics, types of products, etc. The merged preference profile may be used to personalize the digital component output to the user. For example, when selecting a digital component, there may be multiple digital components to choose from. At least some of the digital components may be selected based on the user's merged preference profile. The selected digital components may match the user's preferences. At least a portion of the selected digital components may be digital components with subject matter that matches the user's preferences, thereby personalizing the digital component output to the user.

[0011] Declared preferences may be preferences selected by the user, determined based on user responses to survey questions, or determined based on the user's reactions to the content, e.g., user light engagement with the content, such as "liking," sharing, "hearting," filtering, etc. Inferred preferences may be determined based on user behavior toward the content, such as search queries submitted by the user, ad clicks or watches, viewing for a threshold time period, or other user interactions with the content. According to some examples, content may include, be associated with, or be identified by embeddings. Embeddings may be representations of the content's brand, topic, product, etc. User preferences may, in some examples, be identified using embeddings. Embeddings may be numeric, alphabetic, or alphanumeric representations of the content's subject matter and / or user preferences expressed as vectors. Declared and inferred preferences may be merged into a merged preference profile.

[0012] According to some examples, when merging declared and inferred preferences, there may be a conflict between a user's declared and inferred preferences. For example, a user may declare that they do not want to view any digital components related to sports, but the user's inferred preferences may indicate that the user has searched for sporting goods stores. When merging declared and inferred preferences, conflicts such as those described may be resolved by favoring the declared preferences over the inferred preferences.

[0013] The merged preference profile may be used to target and retrieve digital components for output to a user. For example, a publisher may submit a request for one or more digital components for output to a user. When determining which digital components to select, at least a portion of the selected digital components are reserved for digital components that relate to the user's merged preference profile.

[0014] To determine whether the digital component under consideration matches the user's preferences, the brand, topic, product, etc. (collectively referred to herein as "subject") of the digital component under consideration may be compared to the user's merged preference profile. The subject of the digital component may be determined based on the content of the digital component, a classifier associated with the entity paying for the digital component, the description of the digital component, the landing page of the digital component, etc. According to some examples, the subject of the digital component may be determined based on embeddings associated with the digital component. Once the subject of the digital component is determined, it may be compared with the subject matter in the merged preference profile. At least one of the digital components having a threshold match with the subject matter of the merged preference profile is a selected digital component and may therefore be output to the user. Additionally or alternatively, embeddings associated with the digital component may be compared with embeddings associated with the merged preference profile. For example, coordinates of embeddings of the digital component may be compared with coordinates of embeddings associated with the merged preference profile. A threshold match between a digital component and the merged preference profile may be a digital component having embeddings within a threshold of coordinates of embeddings associated with the merged preference profile.

[0015] According to some examples, the subject matter of the digital components may be used to ask a survey question to the user. The survey question may be used to determine the user's declared preferences, such as to reconcile discrepancies between declared and inferred preferences. For example, if the subject matter of the digital components is "basketball" and the user previously declared that they are not interested in "sports," the survey question may be "Would you like to see more digital components related to basketball?" Based on the response, the declared preferences, and therefore the merged preference profile, may be updated.

[0016] A reserved digital space for digital components related to the merged preference profile ensures that the user is presented with personalized digital components that correspond to their declared and inferred preferences. Moreover, by resolving conflicts between the user's declared and inferred preferences by selecting a declared preference, irrelevant digital components are filtered out from the digital components being considered for selection. This may ensure that the user is presented with digital components that are relevant to their preferences, rather than what the digital component system may think is best for the user. For example, if the user declared that they would like to see fewer digital components related to electric vehicles ("EVs"), their declared preference to see fewer EV digital components would override any inference that would result in selecting EV digital components for output to the user.

[0017] Identifying digital components to be included in the selection process and reserving at least a portion of the selected digital components to be related to the positive preferences indicated in the merged preference profile can ensure that the digital components provided to the user are personalized to the user's interests and preferences. By using a merged preference profile to select digital components, the computational efficiency of the process for selecting digital components is improved compared to determining user preferences when the digital components are requested by the publisher. Moreover, generating the merged preference profile before the publisher requests the digital components improves the consistency and accuracy of the declarations.

[0018] By providing a digital component that will be accepted and used by the user, other resources, such as network bandwidth and processor and memory overhead associated with transmitting an unwanted digital component to the publisher and / or user device, are not wasted because one or more replacement digital components do not need to be transmitted to the user following the unwanted digital component. Furthermore, additional display space at the publisher and / or user device does not need to be reserved, conserving resources at the publisher / user device.

[0019] 1 illustrates exemplary content being output on a device. The subject matter, or focus, of the content 114 may be determined and used to determine user preferences. In some examples, embeddings associated with the subject matter of the content may be determined and used to determine user preferences. According to some examples, the content 114 may be used during digital component selection to identify digital components that match a user's merged preference profile. The subject matter of the content 114 may include, for example, a brand, topic, type of product, etc. The subject matter may be associated with embeddings. The content 114 may include, for example, a digital component, video, image, information, etc.

[0020] According to some examples, the content 114 may be a video advertisement for a retail store selling shoes. The subject matter of the content 114 may be determined based on the brand 110, topic, product 112, etc. in the advertisement, such as the retail store, shoe type, or shoe brand 110. The determined subject matter may be used to survey a user regarding the retail store 116, shoe type, or shoe brand 110. In some examples, the determined subject matter may be used to determine an inferred preference of a user based on the user's engagement or behavior with the content.

[0021] According to some examples, the subject matter of the content 114 may be determined based on the description 106, a landing page, a classification associated with the content 114, or the like. Continuing with the example above, a video for a retail store selling shoes may include a description of the type or brand 110 of shoes, information related to a sale, etc. In some examples, clicking on the video may lead to a landing page for the related webpage of the retail store, or a webpage for the brand of shoes in the video. Additionally or alternatively, there may be a classification associated with the content 114, such as a label related to the subject matter of the content 114. Continuing with the example provided, the classification may be "shoes," a particular brand 110, a particular type of shoe, etc.

[0022] In some examples, the subject of the content 114 may be provided for output along with the content 114. For example, an indicator may be included such that, when selected, a popup 102 identifying the subject 104 of the content 114 may be output. This may provide a user with clarity regarding the subject 104 of the content 114 compared to a publisher providing the content 114. According to some examples, the subject 104 of the content 114 may identify the brand 110, topic, or product 112 being promoted by the content 114 compared to the paying entity. Continuing with a video of a retail store 116 selling shoes, the shoe brand 110 and type of shoe may be identified rather than identifying the retail store 116.

[0023] 2 is an example flow diagram for an example method for generating a merged preference profile 212. The merged preference profile 212 may be generated based on the declared preferences 202, the inferred preferences 206, and the contextual preferences 208. The declared preferences 202, the inferred preferences 206, and / or the contextual preferences 208 may be determined based on a user's engagement with, interaction with, viewing, behavior, etc. As such, the declared preferences 202, the inferred preferences 206, and / or the contextual preferences 208 may be modified, updated, confirmed, etc. based on a user's engagement, interaction, searching, selection, viewing, etc.

[0024] When the declared preferences 202 and the inferred preferences 206 are determined, a conflict may arise between the declared preferences 202 and the inferred preferences 206. The conflict may be resolved via conflict resolution 210. Conflict resolution 210 may utilize a hierarchy, a weighted system, a sliding scale, a direct comparison, or the like to resolve the conflict between the preferences. For example, a conflict may arise if the declared preferences 202 are positive for sports but the inferred preferences 206 are negative for hockey. Hockey is a sport, and therefore, there is a conflict between the positive declared preferences 202 for sports and the negative inferred preferences 206 for hockey. To resolve the conflict, conflict resolution 210 may give greater weight to the declared preferences 202 compared to the inferred preferences 206. In some examples, conflict resolution 210 may consider other declared preferences 202 and inferred preferences 206 when resolving the conflict. In some examples, conflict resolution 210 may resolve conflicts between context preferences 208 and declared preferences 202 and / or inferred preferences 206. Similar to conflict resolution between declared preferences 202 and inferred preferences 206, conflict resolution 210 may resolve conflicts involving context preferences 208 using preference hierarchies, weights, totality, etc. Once any conflicts are resolved, a merged preference profile 212 may be generated.

[0025] The declared preferences 202 may include pure preference declarations 214 and influenced preference declarations 204. The pure preference declarations 214 may be preferences determined based on explicit user instructions related to topics, brands, interests, etc. The topics, brands, interests, etc. may correspond to the subject matter of the content. The influenced preference declarations 204 may be declarations based on the user's light engagement with the subject matter of the content. The content may include, for example, published web pages, advertisements, videos, images, etc. According to some examples, the declared preferences 202 may be determined based on content, digital components, advertisements, etc. that were previously provided for output. The declared preferences 202, inferred preferences 206, and contextual preferences 208 may be associated with embeddings. For example, a user interaction with content may be associated with an embedding, which is then included as a pure preference declaration 214 and / or an influenced preference declaration 204 depending on the type of interaction. Although the embeddings are not a human-understandable taxonomy, they may be used to identify similar content and / or based on the embeddings. According to some examples, the embeddings may be used to identify similar subject matter, personalized content, personalized digital components, etc. that have embeddings within a threshold coordinate distance of a given embedding.

[0026] 3 illustrates an exemplary user interface 310. The user interface 310 may include an input 302 that allows a user to switch between receiving personalized advertisements based on the merged preference profile 212, receiving advertisements based only on the contextual preferences 208, or not receiving personalized advertisements at all. Although the input 302 for the user to opt in to receiving personalized advertisements is shown as a drop-down menu that allows the user to select "on" or "off," the input 302 may be a radio button, a sliding scale, a checkbox, or the like. Thus, the input 302 of the user interface 310 as illustrated is by way of example and not limitation.

[0027] The pure preference declaration 214 may be determined based on input received via the user interface 310. The input received from the user may indicate a preference for a given advertising subject 308. The preference may be to increase or decrease the frequency of advertisements related to that subject 308. In some examples, the preference may be to increase 306 or decrease 304 the likelihood that the user will be shown advertisements related to that subject 308. As shown, the advertising subject 308 may be "handbags and purses," "hotels, motels, and resorts," "clothing," etc.

[0028] Input received via user interface 310 may provide instructions to increase 306 or decrease 304 the frequency of advertisements related to "handbags and purses," "hotels, motels, and resorts," and "clothing." In such an example, the pure declaration of preference 214 may be to increase 306 or decrease 304 the frequency and / or likelihood of showing advertisements related to "handbags and purses," "hotels, motels, and resorts," and "clothing." While the input for increasing and decreasing the frequency or likelihood of showing advertisements of a particular subject 308 is shown as "+" and "-" buttons, the input may be a sliding scale, radio buttons, text boxes, etc. Thus, user interface 310 is merely one example for receiving pure declaration of preference 214, and is not limiting.

[0029] FIG. 4 illustrates another example for determining a pure declaration of preference 214. For example, rather than receiving input via user interface 310, input 404 may be received in the form of a response to survey question 402. Survey question 402 may relate to a subject of digital component 406. For example, digital component 406 may be for shoes, such as work boots and dress shoes. Survey question 402 may be provided along with digital component 406 to confirm a user's interest in advertisements related to work boots. If input 404 corresponding to a "yes" selection is received, it may be determined that pure declaration of preference 214 is a positive declaration for advertisements related to work boots. If input 404 corresponding to a "no" selection is received, it may be determined that pure declaration of preference 214 is a negative declaration for advertisements related to work boots. According to some examples, a positive declaration may correspond to an increase in the frequency and / or likelihood of advertisements related to a given subject, e.g., work boots, while a negative declaration may correspond to a decrease in the frequency and / or likelihood of advertisements related to the given subject.

[0030] The influenced preference declaration 204 may be determined based on a user's light engagement with content, such as social media content, web page content, advertisements, etc. Light engagement may include a user reaction to the content. The reaction may include a "like," a "heart," or any other emoji reaction, such as a thumbs-up, a smiley face, or an angry face. For example, if a user reacts to a social media post related to insulated travel mugs by "liking" the post, the influenced preference declaration 204 may be a positive declaration toward insulated travel mugs. In some examples, if a user reacts to web page content related to disposable travel cups with an angry face emoji, the influenced preference declaration 204 may be determined to be a negative declaration toward disposable travel cups. A positive declaration, or preference, may correspond to a brand, topic, product, etc. that the user is interested in seeing more of, while a negative declaration, or preference, may correspond to a brand, topic, product, etc. that the user is less interested in seeing or not at all. According to some examples, the influenced preference declaration 204 may be determined based on the user's engagement, such as light engagement, with content, advertisements, digital components, etc., previously provided for output to the user.

[0031] Light engagement can be determined and used after a user provides authorization for the system to access or receive information related to the user's light engagement with content. According to some examples, authorization is provided via user engagement with content. Any use of the user's light engagement is authorized by the user. For example, a user may provide authorization for an application to generate a merged preference profile by setting certain permissions for the application. Authorization can be for the application or system to access one or more databases or sub-databases in the device's memory. According to one example, a user can select specific sub-databases that an application is allowed to access. For example, a user may allow access to a search history database but not to a video or content watch database.

[0032] 5 illustrates an example output 506. The output 506 may include content 510, survey questions 520, and responses 516. The output 506 further includes information about a retailer 512, a description 504 of the content 510, an indication of the subject matter 502 of the content 510, and inputs 522 for responding to the survey questions 520.

[0033] As shown, content 510 includes an advertisement for work boots. The work boots are of a given brand 508, and the content 510 is provided by a retailer 512. The content 510 can be a video, a video still, an image, a gif, or any form of media.

[0034] The reactions 516 may provide inputs, such as positive 518 and negative 514, for reacting to or engaging with the content 510. The reactions 516 may include positive 518 or negative 514 instructions related to a brand 508, a product, a retailer 512, etc. As shown, a positive 518 reaction 516 may be determined when input corresponding to selecting a "check mark" is received. A negative 514 light engagement 516 may be determined when input corresponding to selecting a "cancel" symbol is received. Although a "check mark" is shown as corresponding to a positive 518 reaction 516 and a "cancel" symbol is shown as corresponding to a negative 514 reaction 516, the reactions 516 may be any symbol, word, input, etc. Thus, the positive 518 and negative 514 are merely some examples and are not limiting.

[0035] According to some examples, a response 516 may be associated with an embedding. For example, rather than acknowledging a positive 518 response to a brand, product, retailer, etc., an embedding having coordinates at or near the brand, product, retailer, etc. may be identified in response to receiving input corresponding to selecting the positive 518 response. In some examples, rather than acknowledging a negative response 514, an embedding having coordinates opposite the brand, product, retailer, etc. may be identified as something that may be of interest to the user. Additionally or alternatively, in response to a negative response 514, an embedding having coordinates corresponding to the brand, product, retailer, etc. may be identified. An embedding associated with a negative response may be used to ensure that a digital component having subject matter with an embedding near a negative response embedding is not provided to the user.

[0036] The influenced preference declaration 204 may be determined based on input corresponding to a positive 518 or negative 514 selection. The reaction 516, or a positive 518 or negative 514 selection, may be received in association with the content 510, the brand 508, the retailer 512, the subject 502, etc. Although the reaction 516 is shown in association with the content 510, additional reactions 516, e.g., positive 518 and negative 514, may be provided in association with the brand 508, the retailer 512, the subject 502, etc.

[0037] The inferred preference 206 may be determined based on a user's interaction with content. User interactions may include, for example, search queries, clicks, watches, etc. about a subject, e.g., a brand, topic, product, etc. A click may correspond to a selection of content, and a watch may correspond to viewing a video, video clip, gif, etc. According to some examples, if the system receives a search query for left-handed scissors, receives input corresponding to a selection of an advertisement for left-handed scissors, and / or determines that content about left-handed scissors has been viewed, the system may infer a positive preference for left-handed scissors.

[0038] The influenced preference declarations 204 and / or inferred preferences 206 may be associated with embeddings. For example, rather than identifying the subject of the influenced preference declarations 204 and / or inferred preferences 206, the embeddings may be identified. The embeddings may map the influenced preference declarations 204 and / or inferred preferences 206 to coordinates so that digital components with nearby or within a threshold of embeddings can be selected and provided for output to the user. Thus, the embeddings may enable the system to identify digital components that are similar to the embeddings of the user preferences. This may enable the system to personalize the digital components provided to the user.

[0039] According to some examples, inferred preferences 206 may be determined based on a user's engagement with or behavior toward content, advertisements, digital components, etc., previously provided for output to the user. Inferred preferences may be determined and used after the user provides authorization for the system to access or receive information related to the user's interactions with content, any use of which is authorized by the user.

[0040] 6 shows an example output of search results in response to a search query. For example, a publisher 608 may receive a search query 602 for "shoes." In response to the search query 602, the publisher 608 may provide content 610 for output on a display of a user device 612. The content 610 may include one or more search results 606a, 606b, 606c, 606d, 606e, 606f. The search results may be products, such as products 1-6. The search results may be related to the search query 602. For example, because the search query 602 was for shoes, products 1-6 may be different types of shoes.

[0041] Inferred preferences 206 may be determined based on search query 602. For example, inferred preferences 206 may be determined to be shoes. Additionally or alternatively, inferred preferences 206 may be determined based on clicks. For example, if input 604 corresponding to a selection of given products 1-6 is received, inferred preferences 206 may be determined based on input 604, e.g., the selected product.

[0042] Although the content 610 is shown as a search result for a retailer, the content 610 can be any content, such as a video, a news article, an advertisement, etc. Thus, the inferred preferences 206 can be determined based on clicking, watching, hovering, selecting, etc., of any type of content.

[0043] According to some examples, the contextual preferences 208 may be determined based on the content 610 being viewed and / or the context of the content 610, without any user history. The contextual preferences 208 may be determined based on the content 610 currently being output to the user, whereas the inferred preferences 206 may be determined based on current and / or past content 610 output to the user. With reference to FIG. 6 , the search query 602 was for shoes, so that the contextual preferences 208 may be determined to be shoes, in addition to the inferred preferences 206. If other information related to the user's merged preference profile 212 was not available, a digital component related to the search query 602, e.g., shoes, may be provided. In examples where the user's merged preference profile 212 is available, the digital component provided for output may be related to the search query 602 and the user's declared preferences 202 and inferred preferences 206.

[0044] Context preferences may be determined and used after a user provides authorization for the system to access or receive information related to the user's interaction with the content and / or viewing of the content, any use of which is authorized by the user.

[0045] According to some examples, there may be conflicts between stated and inferred preferences. To resolve conflicts between stated, inferred, and contextual preferences, the system may use a hierarchy. For example, pure preference statements may be given the greatest weight when resolving conflicts compared to contextual preferences. According to some examples, the hierarchy from greatest weight to least weight may be pure preference statements, influenced preference statements, inferred preferences, and contextual preferences. Conflicts are resolved by selecting a subject, e.g., topic, brand, product, etc., starting with the preference with the greatest weight. Although the preferences are provided as a hierarchy from pure statements to contextual preferences, the hierarchy described is only an example, as the hierarchy may be provided in any order, with any of the preferences given the greatest weight.

[0046] According to some examples, the freshness of declared preferences, inferred preferences, and contextual preferences may be used to resolve conflicts between declared preferences, inferred preferences, and contextual preferences. Preference freshness may be, for example, the timing of the preference, the amount of freshness, etc. For example, when resolving a conflict, the system may determine whether a declared negative preference for a topic was received after the user had engaged with the topic for an extended period of time. In another example, when resolving a conflict, the system may determine that a preference for a topic was received a period of time before a recent engagement with the same topic. Thus, freshness such as the timing of the received preference, the timing of engagement with the topic compared to the received preference, etc. may be used when resolving a conflict.

[0047] 7 illustrates an example of resolving conflicts between stated preferences, inferred preferences, and contextual preferences. For example, a pure preference statement 702 may be negative toward car-related content, an inferred preference 704 may be positive toward content related to electric vehicles, and a contextual preference 706 may be toward content related to pickup trucks. In such an example, there is a conflict between the stated preferences, the inferred preferences, and the contextual preferences. That is, the pure preference statement 702, which indicates a negative declaration toward car-related content, contradicts the inferred preference 704 for electric vehicles and the contextual preference 706 for pickup trucks.

[0048] To resolve a conflict such as the one described above, conflict resolution 210 may determine the preference with the greatest weight in the hierarchy, e.g., pure preference statement 702. In this example, the preference with the greatest weight in the hierarchy may be pure preference statement 214. Because the declared preference is negative for car-related content, the conflict may be resolved by following the declared preference and ignoring the inferred and contextual preferences. Continuing with this example, the conflict may be resolved by indicating a negative preference for car-related content and ignoring the positive preferences for electric cars and pickup trucks.

[0049] In some examples, the conflict resolution may be determined based on responses to survey questions and / or natural language input. Continuing with the car-related example, if the declared preference is negative for car-related content but the inferred preference is positive for content related to electric vehicles, the system may send a survey question related to the user's declaration. For example, the survey question may be, "Would you like to change your declared preference?" or "Would you like to view car-related content?" The input received in response to the survey question may be used to update the declared preference and, therefore, to resolve the conflict between the user's preferences. According to some examples, the natural language input may be an automated chat providing a survey question asking the user to declare their preference.

[0050] According to some examples, the conflict may be resolved by inferring new preferences based on a combination of data. For example, a preference for EV pickup trucks may be inferred based on a combination of an inferred preference for electric vehicles 704 and a contextual preference for pickup trucks 706. In some examples, a preference for vehicles other than sedans with combustion engines may be inferred based on an inferred preference for electric vehicles 704 and a contextual preference for pickup trucks 706.

[0051] 8 is an example merged preference profile 212. As described above and herein, the merged preference profile 212 may be determined based on the declared preferences 202 and the inferred preferences 206. According to some examples, the merged preference profile may be the user's preferences after resolving conflicts between the user's declared preferences, inferred preferences, and contextual preferences. The resulting merged preference profile may be used for targeting and retrieving digital components, such as advertisements, to be output to the user.

[0052] The declared preferences 202 include pure preference declarations 214 and influenced preference declarations 204. The pure preference declarations 214 may be determined based on the user's explicit declarations of preference in the subject of the content. As described with respect to FIGS. 3 and 4, the explicit declarations may be determined based on input indicating a preference for a given subject or input in response to a survey question. As shown, the pure preference declarations 214 include instructions to not display any digital components or advertisements related to cars. The pure preference declarations 214 may additionally or alternatively include instructions to increase the number of digital components related to “Hotel H” and “Clothing,” but may include instructions to reduce the number of digital components related to “Handbags and Wallets.” According to some examples, the greater the value of the positive indication, the more frequently display components related to that subject should be shown. In some examples, the greater the value of the negative indication, the less frequently display components related to that subject should be shown. Although the instructions for increasing or decreasing frequency are shown as positive and negative values, these instructions may be provided as sliding scales, "yes" or "no," or check boxes such as "show" or "don't show," radio buttons, etc. Furthermore, in some examples, instructions may or may not be provided for output. Thus, the instructions as shown are by way of example only and not by way of limitation.

[0053] The influenced preference declaration 204 may be determined based on a user's light engagement with the content. As described with respect to FIG. 5, light engagement with the content may include user reactions to the content, such as "liking," "hearting," "being angry," etc. As shown in FIG. 8, the influenced preference declaration 204 includes work boots and the brand "Sportz." According to some examples, the influenced preference declaration may include instructions to increase or decrease the frequency of providing digital components related to a given subject. The instructions may be, for example, positive or negative values, sliding scales, checkboxes, radio buttons, etc., such as those shown in the pure preference declaration 214.

[0054] The inferred preferences 206 may be determined based on a user's interactions with or behavior toward content. As described with respect to FIG. 6 , user interactions may include, for example, a search query, clicks corresponding to selecting content, watches corresponding to viewing content, time on page, long clicks versus short clicks, long watches versus short watches, etc. A long click may refer to, for example, a user's interaction with a search result in response to a search query, whereas a short click may indicate, for example, little user interaction with the search result. In some examples, a short click may indicate that the search result did not include content that was of interest to the user. A long watch may refer to, for example, a user's watch time for a given content such as a video. A short watch, in comparison, may indicate that the user spent little time watching the content.

[0055] 8, the inferred preferences 206 may include electric cars, earbuds, video games, and basketball. According to some examples, the inferred preferences 206 may include instructions to increase or decrease the frequency of providing digital components related to a given subject matter. In some examples, a survey question may be output to the user asking whether the inferred preferences 206 should be a pure preference statement 214.

[0056] According to some examples, as opposed to generating a merged preference profile when determining which advertisements to include in an auction, the merged preference profile may be generated offline in a user personalization system (“UPS”). For example, generating a merged preference profile offline may include generating a merged preference profile based on the user's past history and / or activity, rather than at the time an ad server receives a request for an advertisement. The UPS may generate personalization information for the user that will be included in the merged preference profile. According to some examples, the UPS may be performed offline and / or when new activity for the user is detected. The UPS may update the merged preference profile based on the generated personalization information.

[0057] When an ad server receives a request from a publisher for an advertisement to fill a display space, the ad server may identify the user viewing the publisher's website or mobile application. The ad server may receive the user's merged preference profile. For example, at the time of the ad request, the ad server may have the complete context for the request, such as who, where, when, and what. According to some examples, who may be the user, where may be the publisher's website or application, when may be the day of the week, the time of day, and the like, and what may be the user's action. For example, what may be included in the ad request when the user is watching a video, after watching a sequence of videos, after searching for reviews on a topic, and the like. According to some examples, the ad server may additionally or alternatively identify the context of the request for the advertisement. The context may include who, what, where, when, and the like, such as the time of day, what day it is, and what content the user is viewing. The ad server may use the merged preference profile and / or content to identify relevant advertisements to be included during the auction. In some examples, the offline-generated merged preference profile may improve the efficiency of an ad server when responding to ad requests. For example, the ad server may use the offline-generated merged preference profile, including user declarations, to identify relevant ads given the context of the request.

[0058] Generating a merged preference profile prior to the auction can ensure consistency of declared preferences across all applications. According to some examples, generating a merged preference profile on the build-side and instantiating the merged preference profile on the server-side can enable multiple ad serving stacks to read one source. Reading one source, such as a merged preference profile, can enable systems to consistently apply the preferences in the merged preference profile.

[0059] Multiple separate ad delivery stacks may operate based on the shared data. The shared data may be, for example, personalization data. According to some examples, the merged preference profile may be used to train a machine learning model across users. For example, the merged preference profiles of multiple users may be used to train a machine learning model to predict the interests or preferences of other users based on the preferences of users with similar interests. In another example, the merged preference profile may be used as ground truth for a model that attempts to predict interests for other users. In yet another example, the merged preference profile may be used as input to a recommendation model. The recommendation model may be, for example, a model for recommending content. The content recommendation may be, for example, in response to a search query.

[0060] The merged preference profile 212 may be used to target and retrieve advertisements to be included in the selection process. For example, advertisers may bid to have their advertisements displayed on publishers' websites or mobile applications as part of the selection process. The advertisements included in the selection may be based at least in part on the user's merged preference profile 212. According to some examples, advertisements with subjects related to negative preferences may be limited in number or filtered out so as not to be included in the selection process. At least a portion of the selected advertisements may be reserved for advertisements with subjects related to positive preferences in the user's merged preference profile 212.

[0061] 9 shows an example flow diagram of a selection process. A publisher 908, such as "retailer.com," may receive a search query 906 for "shoes." In response to receiving the search query 906, the publisher 908 may send a request to an ad server for one or more advertisements to be presented to the user in addition to the search results. The request may be based on the search query for "shoes." For example, the request may include a request for advertisements corresponding to or associated with "shoes."

[0062] The ad server may receive a request that includes a search query term, e.g., "shoes," and may identify one or more available advertisements 902 that relate to the request from the publisher and / or the search query term. As shown in Figure 9, the available advertisements 902 may include advertisements for products 1-5.

[0063] When selecting one or more of the available advertisements 902 to return in response to a request from a publisher 908, the advertisement server may select advertisements that relate to preferences in the merged preference profile 212. For example, the advertisement server may compare brands, topics, products, etc. identified as having positive or negative preferences with the brands, topics, products, etc. of the advertisement. According to some examples, if the merged preference profile 212 includes a positive preference for an athletic brand and the advertisement subject is sports, the system may determine that the advertisement is a match with the merged preference profile. In another example, if the merged preference profile 212 includes a negative preference for a clothing brand and the advertisement subject is apparel, the system may determine that the advertisement is not a match with the merged preference profile 212. In examples where the advertisement server determines that the advertisement is a match with the merged preference profile 212, the advertisement may be included in the selection process. In examples where the system determines that the advertisement is not a match with the merged preference profile 212, the advertisement may be excluded from the selection process. This may ensure that advertisements provided for output to the user substantially correspond to the preferences expressed in the merged preference profile 212 .

[0064] As shown in FIG. 9 , one or more available ads 902 may be identified. The available ads 902 may be for products 1-6. According to some examples, products 1-6 may be related or relevant to the request from the publisher. The ad server may compare the available ads 902 with the preferences of the merged preference profile 212. For example, the merged preference profile 212 may indicate that there is a positive preference for work boots, and the ad server may ensure that an advertisement for product 4 is included in the selection process. The winning or selected ad 904 may be provided by the publisher 908 for output along with the search results.

[0065] In some examples, a machine learning (“ML”) model may be used to identify advertisements to be included in the selection process. The ML model may be trained to determine whether the subject of the advertisement matches the preferences expressed in the merged preference profile 212. Each training example may consist of an advertisement. Input features to the ML model may be the subject of the advertisement, such as a topic, brand, or product, the positive preferences expressed in the merged preference profile 212, and the negative preferences expressed in the merged preference profile 212. According to some examples, the input features to the ML model may additionally or alternatively be embeddings associated with the advertisement and preferences expressed in the merged preference profile. The ML model may use the input features to more accurately determine whether the subject of the advertisement matches the preferences in the merged preference profile 212. In some examples, the ML model may use the input features to more accurately determine whether the embeddings of the advertisement match the embeddings in the merged preference profile. The output of the ML model may be a determination of whether the advertisement should be included in the selection process. In some examples, the system may solicit feedback from the user, such as by providing survey questions related to the brand, topic, product, etc. in the advertisement. For example, the user may be asked to confirm whether or not an advertisement related to a given brand, topic, or product should be served. The user may provide feedback, such as yes or no, indicating that the decision was correct.

[0066] 10 illustrates an example system in which the features described above and herein may be implemented. This should not be considered as limiting the scope of the disclosure or the usefulness of the features described herein. In this example, system 1000 includes a device 1016, an ad server 1018, an ad server storage system 1022, a publisher server 1020, a publisher storage system 1026, and a network 1024.

[0067] The device 1016 may include one or more processors 1002, memory 1004, data 1006, and instructions 1008. The device 1016 may also include an input 1010, an output 1012, and a communication interface 1014. The device may be, for example, a smartphone, a tablet, a laptop, a smartwatch, an AR / VR headset, a smart helmet, a home assistant, etc.

[0068] The device's memory 1004 may store information accessible by the processor 1002. The memory 1004 may also include data that may be retrieved, manipulated, or stored by the processor 1002. The memory 1004 may be of any type capable of storing information accessible by the processor 1002, including a computer-readable medium, which may be non-transitory, or other medium that stores data that may be read with an electronic device, such as a hard drive, a memory card, a read-only memory (“ROM”), a random access memory (“RAM”), an optical disk, and other writable and read-only memory. The memory 1004 may store instructions that may be executed by the processor 1002, and information accessible by the processor, including data 1006.

[0069] Data 1006 may be retrieved, stored, or modified by processor 1002 in accordance with instructions 1008. For example, although this disclosure is not limited by a particular data structure, data may be stored in a computer register, in a relational database as a table with multiple different fields and records, in an XML document, or in a flat file. Data may also be formatted in a computer-readable format, such as, but not limited to, binary values, ASCII, or Unicode. By way of further example only, data 1006 may comprise sufficient information to identify associated information, such as numbers, descriptive text, proprietary code, pointers, references to data stored in other memory (including other network locations), or information used by a function to calculate associated data.

[0070] The instructions 1008 may be any set of instructions to be executed by a processor, either directly, such as machine code, or indirectly, such as a script. In that regard, the terms "instructions," "application," "steps," and "program" may be used interchangeably herein. The instructions may be stored in object code format for direct processing by a processor, or in any other computing device language, including a script or collection of independent source code modules that are interpreted on demand or pre-compiled. The functions, methods, and routines of the instructions are described in more detail below.

[0071] The one or more processors 1002 may include any conventional processor, such as a commercially available CPU or microprocessor. Alternatively, the processor 1002 may be a dedicated component, such as an ASIC or other hardware-based processor. Although not required, the device 1016 may include dedicated hardware components to perform certain computing functions faster or more efficiently.

[0072] 10 functionally depicts the processor 1002, memory 1004, and other elements of the device 1016 as being within the same respective block, those skilled in the art will understand that the processor 1002 or memory 1004 may actually include multiple processors or memories that may or may not be housed within the same physical housing. Similarly, the memory 1004 may be a hard drive or other storage medium located in a housing different from that of the device 1016. Thus, it will be understood that reference to a processor or device includes reference to a collection of processors or devices or memories that may or may not operate in parallel.

[0073] The input 1010 may be, for example, a mouse, keyboard, touchscreen, microphone, or any other type of input. The input may receive keywords for a search on a publisher's website or mobile application. According to some examples, the input 1010 may receive indications regarding positive and negative pronouncements on a given subject. Additionally or alternatively, the input 1010 may receive light engagement with the content. In some examples, the input 1010 may receive user interaction with the content, such as a click.

[0074] The output 1012 may be a display, such as a monitor with a screen, a touch screen, a projector, or a television. The device's display 1012 may electronically display information to a user via a graphical user interface ("GUI") or other type of user interface. For example, the display may electronically display product information, digital components, advertisements, and the like on a publisher's website or mobile application.

[0075] While only one device is shown in FIG. 10 , it should be appreciated that a typical system may include one or more computing devices 1016, with each computing device residing at a different node of the network. Devices may be capable of communicating directly and indirectly with other nodes of the network. The networks and intervening nodes described herein may be interconnected using a variety of protocols and systems, such that a network may be part of the Internet, the World Wide Web, a particular intranet, a wide area network, or a local network. The network may utilize standard communication protocols, such as WiFi, Bluetooth, 4G, 5G, or the like, that are proprietary to one or more companies. While several advantages are obtained when information is transmitted or received as described above, other aspects of the subject matter described herein are not limited to any particular method of transmission.

[0076] The system 1000 may include one or more server computing devices, such as an ad server 1018 and a publisher server 1020. The server computing devices may be, for example, load-balanced server farms that exchange information with different nodes of a network for the purpose of receiving, processing, and transmitting data to and from other computing devices. For example, the ad server 1018 and the publisher server 1020 may be web servers that are capable of communicating with devices over a network. Additionally, the ad server 1018 and the publisher server 1020 may use the network to transmit and provide information to users of the device 1016. The ad server 1018 and the publisher server 1020 may include one or more processors, memory, data, instructions, etc. These components operate in the same or similar manner as described above with respect to the device 1016.

[0077] The ad server 1018 may manage digital components such as advertisements and provide various services to advertisers, publishers, and devices. According to some examples, the ad server 1018 may receive ad campaigns from one or more advertisers. The ad campaigns may include campaign information such as products, bidding strategies, targeting information, duration, etc. The ad campaigns may be stored in the memory of the ad server 1018 and / or in the ad server storage system 1022.

[0078] According to some examples, publisher server 1020 may receive a search query from device 1016. For example, the search query may be for specific content, such as product information. In response to the request, publisher server 1020 may retrieve relevant content from publisher storage system 1026. Publisher server 1020 may send a content page or other presentation, representation, or characterization of the content to the requesting device 1016. The content page may include, for example, a digital component such as an advertisement.

[0079] According to some examples, in response to a received search query, the publisher server 1020 may send a request to the ad server 1018. The request may be for one or more digital components, such as an advertisement. The ad server 1018 may facilitate identification of relevant advertisements for delivery to the publisher. The relevant advertisements may be determined based at least in part on the user's merged preference profile. For example, the ad server may identify available advertisements in response to a request from the publisher server. The ad server may identify which of the available advertisements match preferences in the merged preference profile. At least one of the advertisements selected to be returned to the publisher may correspond to preferences in the merged preference profile.

[0080] The device 1016 may present the search query results integrated with one or more of the advertisements provided by the ad server in a viewer such as a browser, a mobile application, or other content display system.

[0081] 11 illustrates an exemplary method for providing at least one acquired advertisement in response to a request from a publisher. The following operations need not be performed in the exact order described below. Rather, various operations may be performed in a different order or simultaneously, and operations may be omitted.

[0082] At block 1102, a request for at least one digital component for display on a publisher's page may be received. The request may be received from a publisher. The digital component may be an advertisement, so the request from the publisher will be for one or more advertisements to be displayed.

[0083] At block 1104, a user's declared preferences may be determined. The user's declared preferences may relate to at least one subject matter of a digital component previously provided for output. The subject matter of a digital component may include, for example, a brand, a topic, or a product. In some examples, the declared preferences may be determined based on user input received regarding the digital component previously provided for output.

[0084] According to some examples, the declared preferences may include at least one of a pure preference declaration or an influenced preference declaration. A pure preference declaration may be determined based on at least one of a user profile or input received in response to one or more survey questions. An influenced preference declaration may be determined based on user interaction with at least one of content or digital components previously provided for output.

[0085] At block 1106, inferred preferences of the user may be determined. The inferred preferences may be determined by identifying one or more engagements with the subject matter of content previously provided for output or one or more search queries about the subject matter of the content. The content may include a digital component such as an advertisement, and the subject matter of the content may include at least one of a brand, a topic, or a product.

[0086] At block 1108, the user's declared and inferred preferences may be merged into a merged preference profile. The merged preference profile may include declared preferences, such as pure preference declarations and / or influenced preference declarations, inferred preferences, and / or contextual preferences.

[0087] At block 1110, when there is a conflict between at least one declared preference and at least one inferred preference, at least one declared preference may be selected for inclusion in the merged preference profile. According to some examples, at least one inferred preference that is in conflict with at least one declared preference may be discarded.

[0088] At block 1112, at least one digital component related to the merged preference profile may be identified. For example, in response to receiving a request for the at least one digital component, multiple available digital components may be identified. Based on the multiple available digital components, at least one digital component may be identified as related to the merged preference profile. For example, the at least one digital component identified as related to the merged preference profile may have subject matter corresponding to preferences indicated in the merged preference profile.

[0089] At block 1114, one or more digital components may be selected, at least one of the one or more digital components being at least one identified digital component related to the merged preference profile. According to some examples, display space may be reserved for the selected one or more digital components related to the merged preference profile.

[0090] At block 1116, the selected digital component or components may be provided to a publisher for output. The publisher may output the digital component for display on its website, mobile application, etc. For example, the publisher may output the digital component along with search results or other content such as videos, articles, etc.

[0091] By providing a digital component based on the user's merged preference profile, the digital component will likely be accepted and used by the user. By providing a digital component that will be accepted and used by the user, other computer-based resources, such as network bandwidth and associated processor and memory overhead, may be reduced. For example, by providing a digital component that will be accepted and used by the user, unwanted and / or replacement digital components do not need to be sent to the user to replace previously sent unwanted digital components. Furthermore, display space for the publisher may be saved because the publisher does not need to reserve additional display space for unwanted digital components.

[0092] Moreover, the digital components are likely to be accepted and used by the user in light of the preferences expressed in the user's merged preference profile. Using the merged preference profile to select the digital components to be accepted and used by the user improves computational efficiency for selecting the digital components compared to determining user preferences at the publisher's request. Moreover, selecting the digital components based on the merged preference profile improves the accuracy and consistency of selecting the digital components to be accepted and used by the user.

[0093] Unless otherwise specified, the above alternatives are not mutually exclusive and may be implemented in various combinations to achieve inherent advantages. Because these and other variations and combinations of the features described above can be utilized without departing from the subject matter defined by the claims, the above description of examples should be construed as examples, and not as limitations on the subject matter defined by the claims. Additionally, the provision of examples described herein, as well as clauses such as "such as," "including," and the like, should not be construed as limiting the subject matter of the claims to specific examples; rather, the example illustrates only one of many possible implementations. Furthermore, the same reference numbers in different drawings may identify the same or similar elements. [Explanation of symbols]

[0094] 102 Pop-up 104, 502 Subject 106, 504 Description 110,508 brands 112 products 114, 510, 610 Contents 116 retail stores 202 Declared Preferences 204 Influenced Preference Statements 206, 704 inferred preferences 208, 706 Contextual preferences 210 Resolving contradictions 212 Merged Preference Profiles 214, 702 Pure Preference Declaration 302, 404, 522, 604, 1010 input 304 decrease 306 increase 308 Advertising subject, subject 310 User Interface 402, 520 Survey Questions 406 Digital Components 506 Output 512 retailers 514 Negative, negative reaction 516 Reactions, Light Engagement, Additional Reactions 518 positive 602, 906 search queries 606a, 606b, 606c, 606d, 606e, 606f search results 608, 908 Publisher 612 User Devices 708 Conflict Resolution Input 710 Conflict Resolution Output 902 available ads 904 winning or selected ads 1000 systems 1002 processor 1004 memory 1006 Data 1008 Instructions 1012 output, display 1014 Communication Interface 1016 Device, computing device, requesting device 1018 Ad Server 1020 Publisher Server 1022 Advertising Server Storage System 1024 Network 1026 Publisher Storage System

Claims

1. receiving, by one or more processors, a request from a publisher for at least one digital component for display on the publisher's page; determining, by the one or more processors, declared preferences of the user, the declared preferences comprising at least one of a pure preference declaration or an influenced preference declaration; determining, by the one or more processors, inferred preferences of the user; merging, by the one or more processors, the declared preferences and the inferred preferences of the user into a merged preference profile; selecting, by the one or more processors, when there is a conflict between at least one declared preference and at least one inferred preference, the at least one declared preference to be included in the merged preference profile; identifying, by the one or more processors, at least one digital component related to the merged preference profile; selecting, by the one or more processors, one or more digital components; at least one of the one or more digital components is the at least one identified digital component related to the merged preference profile; providing, by the one or more processors, the selected one or more digital components to the publisher for output; A method comprising:

2. The method of claim 1 , further comprising: discarding, by the one or more processors, the at least one inferred preference that is inconsistent with the at least one declared preference.

3. 3. The method of claim 1, further comprising reserving, by the one or more processors, display space for the selected one or more digital components related to the merged preference profile.

4. The method of claim 1 , wherein the declared preferences of the user relate to at least one subject matter of a digital component previously provided for output.

5. The method of claim 4 , wherein the at least one subject of the digital component includes a brand, a topic, or a product.

6. 6. The method of claim 4 or 5, wherein the declared preference is determined based on user input received regarding the digital component previously offered for output.

7. the genuine declaration of preference is determined based on at least one of a user profile or input received in response to one or more survey questions; The method of claim 1 , wherein the influenced preference declaration is determined based on user interaction with at least one of content or digital components previously provided for output.

8. 10. The method of claim 1, wherein the inferred preferences are determined by identifying one or more behaviors toward a subject of content previously provided for output or one or more search queries about the subject of the content.

9. the content includes a digital component; The method of claim 8 , wherein the subject matter of the content includes at least one of a brand, a topic, or a product.

10. 1. A computer-readable storage medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to: receiving a request from a publisher for at least one digital component for display on the publisher's page; determining declared preferences of a user, the declared preferences including at least one of a pure preference declaration or an influenced preference declaration; determining inferred preferences of the user; merging the declared preferences and the inferred preferences of the user into a merged preference profile; merging, by the one or more processors, when there is a conflict between at least one declared preference and at least one inferred preference, selecting the at least one declared preference to be included in the merged preference profile; identifying at least one digital component related to said merged preference profile; selecting one or more digital components; selecting at least one of the one or more digital components to be the at least one identified digital component related to the merged preference profile; providing the selected one or more digital components to the publisher for output; A computer-readable storage medium that causes the

11. 11. The computer-readable storage medium of claim 10, wherein the instructions further configure the one or more processors to discard, by the one or more processors, the at least one inferred preference that is inconsistent with the at least one declared preference.

12. 12. The computer-readable storage medium of claim 10, wherein the instructions further configure the one or more processors to reserve display space for the selected one or more digital components that relate to the merged preference profile.

13. 11. The computer-readable storage medium of claim 10, wherein the declared preferences of the user relate to at least one subject matter of a digital component previously provided for output.

14. The computer-readable storage medium of claim 13 , wherein the at least one subject of the digital component includes a brand, a topic, or a product.

15. 15. The computer-readable storage medium of claim 13 or 14, wherein the declared preference is determined based on user input received regarding the digital component previously provided for output.

16. the genuine preference declarations are determined based on at least one of a user profile or input received in response to one or more survey questions; The computer-readable storage medium of claim 10 , wherein the influenced preference declaration is determined based on user interaction with at least one of content or digital components previously provided for output.

17. 11. The computer-readable storage medium of claim 10, wherein the inferred preferences are determined by identifying one or more behaviors toward a subject of content previously provided for output or one or more search queries about the subject of the content.

18. the content includes a digital component; 20. The computer-readable storage medium of claim 17, wherein the subject matter of the content includes at least one of a brand, a topic, or a product.

19. one or more processors, wherein the one or more processors: receiving a request from a publisher for at least one digital component for display on the publisher's page; determining declared preferences of a user, the declared preferences including at least one of a pure preference declaration or an influenced preference declaration; determining inferred preferences of the user; merging the declared preferences and the inferred preferences of the user into a merged preference profile; merging, when there is a conflict between at least one declared preference and at least one inferred preference, selecting the at least one declared preference to be included in the merged preference profile; identifying at least one digital component related to said merged preference profile; selecting one or more digital components; selecting at least one of the one or more digital components to be the at least one identified digital component related to the merged preference profile; providing the selected one or more digital components to the publisher for output; A system configured to:

20. 20. The system of claim 19, wherein the one or more processors are further configured to: discard the at least one inferred preference that is inconsistent with the at least one declared preference by the one or more processors.

21. 21. The system of claim 19 or 20, wherein the one or more processors are further configured to reserve display space for the selected one or more digital components related to the merged preference profile by the one or more processors.

22. 20. The system of claim 19, wherein the declared preferences of the user relate to at least one subject matter of a digital component previously provided for output.

23. The system of claim 22 , wherein the at least one subject of the digital component includes a brand, a topic, or a product.

24. 24. A system according to claim 22 or 23, wherein the declared preference is determined based on user input received regarding the digital component previously offered for output.

25. the genuine preference declarations are determined based on at least one of a user profile or input received in response to one or more survey questions; 20. The system of claim 19, wherein the influenced preference declaration is determined based on user interaction with at least one of content or digital components previously provided for output.

26. 20. The system of claim 19, wherein the inferred preferences are determined by identifying one or more behaviors toward a subject of content previously provided for output or one or more search queries about the subject of the content.

27. the content includes a digital component; 27. The system of claim 26, wherein the subject matter of the content includes at least one of a brand, a topic, or a product.

Images