SYSTEM FOR DETERMINING INTERESTS OF USERS OF MOBILE AND NONMOBILE COMMUNICATION DEVICES BASED ON DATA RECEIVED FROM A PLURALITY OF DATA PROVIDERS
A system for determining interests of users of mobile and non-mobile communication devices based on data received from a plurality of data providers, wherein the system is configured to perform the steps of: (a) obtaining multiple datasets, wherein each dataset comprises at least one user and at least one corresponding attribute for the at least one user; (b) creating a first cluster comprising a first user from at least one dataset and the at least one corresponding attribute for the first user; (c) creating a second cluster comprising a second user from the at least one dataset and the at least one corresponding attribute for the second user; (d) merging the first cluster with the second cluster; and (e) assigning values to previously unknown attributes based on probabilistic estimations.
This application claims the benefit of U.S. Provisional Pat. App. No. 61/558,522 filed Nov. 11, 2011, and titled “Targeted Advertising Across a Plurality of Mobile and Non-Mobile Communication Facilities Accessed By the Same User,” U.S. Provisional Pat. App. No. 61/569,217 filed Dec. 9, 2011, and titled “Targeted Advertising Across Web Activities On an MCF and Applications Operating Thereon,” U.S. Provisional Pat. App. No. 61/576,963 filed Dec. 16, 2011, and titled “Targeted Advertising to Mobile Communication Facilities,” and U.S. Provisional Pat. App. No. 61/652,834 filed May 29, 2012, and titled “Validity of Data for Targeting Advertising Across a Plurality of Mobile and Non-Mobile Communication Facilities Accessed By the Same User,” the contents of which are incorporated herein by reference.
This application also incorporates herein by reference the content of each of the following applications: U.S. application No. 13/666,690, filed on Nov. 1, 2012 and entitled “Identifying a Same User of Multiple Communication Devices Based on Web Page Visits”; and U.S. application No. 13/667,515 filed on Nov. 2, 2012 and entitled “Validation of Data for Targeting Users Across Multiple Communication Devices Accessed By the Same User”; and U.S. application No. 13/018,952 filed on Feb. 1, 2011, which is a non-provisional of application No. 61/300,333 filed on Feb. 1, 2010 and entitled “INTEGRATED ADVERTISING SYSTEM,” and which is a continuation-in-part of U.S. application No. 12/537,814 filed on Aug. 7, 2009 and entitled “CONTEXTUAL TARGETING OF CONTENT USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/486,502 filed on Jun. 17, 2009 and entitled “USING MOBILE COMMUNICATION FACILITY DEVICE DATA WITHIN A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/485,787 filed on Jun. 16, 2009 and entitled “MANAGEMENT OF MULTIPLE ADVERTISING INVENTORIES USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,199 filed on Mar. 9, 2009 and entitled “USING MOBILE APPLICATION DATA WITHIN A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,185 filed on Mar. 9, 2009 and entitled “REVENUE MODELS ASSOCIATED WITH SYNDICATION OF A BEHAVIORAL PROFILE USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,166 filed on Mar. 9, 2009 and entitled “SYNDICATION OF A BEHAVIORAL PROFILE USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,153 filed on Mar. 9, 2009 and entitled “SYNDICATION OF A BEHAVIORAL PROFILE ASSOCIATED WITH AN AVAILABILITY CONDITION USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,138 filed on Mar. 9, 2009 and entitled “AGGREGATION AND ENRICHMENT OF BEHAVIORAL PROFILE DATA USING A MONETIZATION PLATFORM,” which is a continuation of U.S. application No. 12/400,096 filed on Mar. 9, 2009 and entitled “AGGREGATION OF BEHAVIORAL PROFILE DATA USING A MONETIZATION PLATFORM,” which is a non-provisional of application No. 61/052,024 filed on May 9, 2008 and entitled “MONETIZATION PLATFORM” and App. No. 61/037,617 filed on Mar. 18, 2008 and entitled “PRESENTING CONTENT TO A MOBILE COMMUNICATION FACILITY BASED ON CONTEXTUAL AND BEHAVIORIAL DATA RELATING TO A PORTION OF A MOBILE CONTENT,” and which is a continuation-in-part of U.S. application No. 11/929,328 filed on Oct. 30, 2007 and entitled “CATEGORIZATION OF A MOBILE USER PROFILE BASED ON BROWSE BEHAVIOR,” which is a continuation-in-part of U.S. application No. 11/929,308 filed on Oct. 30, 2007 and entitled “MOBILE DYNAMIC ADVERTISEMENT CREATION AND PLACEMENT,” which is a continuation-in-part of U.S. application No. U.S. application No. 11/929,297 filed on Oct. 30, 2007 and entitled “MOBILE COMMUNICATION FACILITY USAGE AND SOCIAL NETWORK CREATION”, which is a continuation-in-part of U.S. application No. 11/929,272 filed on Oct. 30, 2007 and entitled “INTEGRATING SUBSCRIPTION CONTENT INTO MOBILE SEARCH RESULTS,” which is a continuation-in-part of U.S. application No. 11/929,253 filed on Oct. 30, 2007 and entitled “COMBINING MOBILE AND TRANSCODED CONTENT IN A MOBILE SEARCH RESULT,” which is a continuation-in-part of U.S. application No. 11/929,171 filed on Oct. 30, 2007 and entitled “ASSOCIATING MOBILE AND NONMOBILE WEB CONTENT,” which is a continuation-in-part of U.S. application No. 11/929,148 filed on Oct. 30, 2007 and entitled “METHODS AND SYSTEMS OF MOBILE QUERY CLASSIFICATION,” which is a continuation-in-part of U.S. application No. 11/929,129 filed on Oct. 30, 2007 and entitled “MOBILE USER PROFILE CREATION BASED ON USER BROWSE BEHAVIORS,” which is a continuation-in-part of U.S. application No. 11/929,105 filed on Oct. 30, 2007 and entitled “METHODS AND SYSTEMS OF MOBILE DYNAMIC CONTENT PRESENTATION,” which is a continuation-in-part of U.S. application No. 11/929,096 filed on Oct. 30, 2007 and entitled “METHODS AND SYSTEMS FOR MOBILE COUPON TRACKING,” which is a continuation-in-part of U.S. application No. 11/929,081 filed on Oct. 30, 2007 and entitled “REALTIME SURVEYING WITHIN MOBILE SPONSORED CONTENT,” which is a continuation-in-part of U.S. application No. 11/929,059 filed on Oct. 30, 2007 and entitled “METHODS AND SYSTEMS FOR MOBILE COUPON PLACEMENT,” which is a continuation-in-part of U.S. application No. 11/929,039 filed on Oct. 30, 2007 and entitled “USING A MOBILE COMMUNICATION FACILITY FOR OFFLINE AD SEARCHING,” which is a continuation-in-part of U.S. application No. 11/929,016 filed on Oct. 30, 2007 and entitled “LOCATION BASED MOBILE SHOPPING AFFINITY PROGRAM,” which is a continuation-in-part of U.S. application No. 11/928,990 filed on Oct. 30, 2007 and entitled “INTERACTIVE MOBILE ADVERTISEMENT BANNERS,” which is a continuation-in-part of U.S. application No. 11/928,960 filed on Oct. 30, 2007 and entitled “IDLE SCREEN ADVERTISING,” which is a continuation-in-part of U.S. application No. 11/928,937 filed on Oct. 30, 2007 and entitled “EXCLUSIVITY BIDDING FOR MOBILE SPONSORED CONTENT,” which is a continuation-in-part of U.S. application No. 11/928,909 filed on Oct. 30, 2007 and entitled “EMBEDDING A NONSPONSORED MOBILE CONTENT WITHIN A SPONSORED MOBILE CONTENT,” which is a continuation-in-part of U.S. application No. 11/928,877 filed on Oct. 30, 2007 and entitled “USING WIRELESS CARRIER DATA TO INFLUENCE MOBILE SEARCH RESULTS,” which is a continuation-in-part of U.S. application No. 11/928,847 filed on Oct. 30, 2007 and entitled “SIMILARITY BASED LOCATION MAPPING OF MOBILE COMMUNICATION FACILITY USERS,” which is a continuation-in-part of U.S. application No. 11/928,819 filed on Oct. 30, 2007 and entitled “TARGETING MOBILE SPONSORED CONTENT WITHIN A SOCIAL NETWORK,” which is a non-provisional of U.S. application No. 60/946,132 filed on Jun. 25, 2007 and entitled “BUSINESS STREAM: EXPLORING NEW ADVERTISING OPPORTUNITIES AND AD FORMATS,” and U.S. application No. 60/968,188 filed on Aug. 27, 2007 and entitled “MOBILE CONTENT SEARCH” and a continuation-in-part of U.S. application No. 11/553,746 filed on Oct. 27, 2006 and entitled “COMBINED ALGORITHMIC AND EDITORIAL-REVIEWED MOBILE CONTENT SEARCH RESULTS,” which is a continuation of U.S. application No. 11/553,713 filed on Oct. 27, 2006 and entitled “ON-OFF HANDSET SEARCH BOX,” which is a continuation of U.S. application No. 11/553,659 filed on Oct. 27, 2006 and entitled “CLIENT LIBRARIES FOR MOBILE CONTENT,” which is a continuation of U.S. application No. 11/553,569 filed on Oct. 27, 2006 and entitled “ACTION FUNCTIONALITY FOR MOBILE CONTENT SEARCH RESULTS,” which is a continuation of U.S. application No. 11/553,626 filed on Oct. 27, 2006 and entitled “MOBILE WEBSITE ANALYZER,” which is a continuation of U.S. application No. 11/553,598 filed on Oct. 27, 2006 and entitled “MOBILE PAY PER CALL,” which is a continuation of U.S. application No. 11/553,587 filed on Oct. 27, 2006 and entitled “MOBILE CONTENT CROSS-INVENTORY YIELD OPTIMIZATION,” which is a continuation of U.S. application No. 11/553,581 filed on Oct. 27, 2006 and entitled “MOBILE PAYMENT FACILITATION,” which is a continuation of U.S. application No. 11/553,578 filed on Oct. 27, 2006 and entitled “BEHAVIORAL-BASED MOBILE CONTENT PLACEMENT ON A MOBILE COMMUNICATION FACILITY,” which is a continuation application of U.S. application No. 11/553,567 filed on Oct. 27, 2006 and entitled “CONTEXTUAL MOBILE CONTENT PLACEMENT ON A MOBILE COMMUNICATION FACILITY”, which is a continuation-in-part of U.S. application No. 11/422,797 filed on Jun. 7, 2006 and entitled “PREDICTIVE TEXT COMPLETION FOR A MOBILE COMMUNICATION FACILITY”, which is a continuation-in-part of U.S. application No. 11/383,236 filed on May 15, 2006 and entitled “LOCATION BASED PRESENTATION OF MOBILE CONTENT”, which is a continuation-in-part of U.S. application No. 11/382,696 filed on May 10, 2006 and entitled “MOBILE SEARCH SERVICES RELATED TO DIRECT IDENTIFIERS”, which is a continuation-in-part of U.S. application No. 11/382,262 filed on May 8, 2006 and entitled “INCREASING MOBILE INTERACTIVITY”, which is a continuation of U.S. application No. 11/382,260 filed on May 8, 2006 and entitled “AUTHORIZED MOBILE CONTENT SEARCH RESULTS”, which is a continuation of U.S. application No. 11/382,257 filed on May 8, 2006 and entitled “MOBILE SEARCH SUGGESTIONS”, which is a continuation of U.S. application No. 11/382,249 filed on May 8, 2006 and entitled “MOBILE PAY-PER-CALL CAMPAIGN CREATION”, which is a continuation of U.S. application No. 11/382,246 filed on May 8, 2006 and entitled “CREATION OF A MOBILE SEARCH SUGGESTION DICTIONARY”, which is a continuation of U.S. application No. 11/382,243 filed on May 8, 2006 and entitled “MOBILE CONTENT SPIDERING AND COMPATIBILITY DETERMINATION”, which is a continuation of U.S. application No. 11/382,237 filed on May 8, 2006 and entitled “IMPLICIT SEARCHING FOR MOBILE CONTENT,” which is a continuation of U.S. application No. 11/382,226 filed on May 8, 2006 and entitled “MOBILE SEARCH SUBSTRING QUERY COMPLETION”, which is a continuation-in-part of U.S. application No. 11/414,740 filed on Apr. 27, 2006 and entitled “EXPECTED VALUE AND PRIORITIZATION OF MOBILE CONTENT,” which is a continuation of U.S. application No. 11/414,168 filed on Apr. 27, 2006 and entitled “DYNAMIC BIDDING AND EXPECTED VALUE,” which is a continuation of U.S. application No. 11/413,273 filed on Apr. 27, 2006 and entitled “CALCULATION AND PRESENTATION OF MOBILE CONTENT EXPECTED VALUE,” which is a non-provisional of U.S. application No. 60/785,242 filed on Mar. 22, 2006 and entitled “AUTOMATED SYNDICATION OF MOBILE CONTENT” and which is a continuation-in-part of U.S. application No. 11/387,147 filed on Mar. 21, 2006 and entitled “INTERACTION ANALYSIS AND PRIORITIZATION OF MOBILE CONTENT,” which is continuation-in-part of U.S. application No. 11/355,915 filed on Feb. 16, 2006 and entitled “PRESENTATION OF SPONSORED CONTENT BASED ON MOBILE TRANSACTION EVENT,” which is a continuation of U.S. application No. 11/347,842 filed on Feb. 3, 2006 and entitled “MULTIMODAL SEARCH QUERY,” which is a continuation of U.S. application No. 11/347,825 filed on Feb. 3, 2006 and entitled “SEARCH QUERY ADDRESS REDIRECTION ON A MOBILE COMMUNICATION FACILITY,” which is a continuation of U.S. application No. 11/347,826 filed on Feb. 3, 2006 and entitled “PREVENTING MOBILE COMMUNICATION FACILITY CLICK FRAUD,” which is a continuation of U.S. application No. 11/337,112 filed on Jan. 19, 2006 and entitled “USER TRANSACTION HISTORY INFLUENCED SEARCH RESULTS,” which is a continuation of U.S. application No. 11/337,180 filed on Jan. 19, 2006 and entitled “USER CHARACTERISTIC INFLUENCED SEARCH RESULTS,” which is a continuation of U.S. application No. 11/336,432 filed on Jan. 19, 2006 and entitled “USER HISTORY INFLUENCED SEARCH RESULTS,” which is a continuation of U.S. application No. 11/337,234 filed on Jan. 19, 2006 and entitled “MOBILE COMMUNICATION FACILITY CHARACTERISTIC INFLUENCED SEARCH RESULTS,” which is a continuation of U.S. application No. 11/337,233 filed on Jan. 19, 2006 and entitled “LOCATION INFLUENCED SEARCH RESULTS,” which is a continuation of U.S. application No. 11/335,904 filed on Jan. 19, 2006 and entitled “PRESENTING SPONSORED CONTENT ON A MOBILE COMMUNICATION FACILITY,” which is a continuation of U.S. application No. 11/335,900 filed on Jan. 18, 2006 and entitled “MOBILE ADVERTISEMENT SYNDICATION,” which is a continuation-in-part of U.S. application No. 11/281,902 filed on Nov. 16, 2005 and entitled “MANAGING SPONSORED CONTENT BASED ON USER CHARACTERISTICS,” which is a continuation of U.S. application No. 11/282,120 filed on Nov. 16, 2005 and entitled “MANAGING SPONSORED CONTENT BASED ON USAGE HISTORY”, which is a continuation of U.S. application No. 11/274,884 filed on Nov. 14, 2005 and entitled “MANAGING SPONSORED CONTENT BASED ON TRANSACTION HISTORY”, which is a continuation of U.S. application No. 11/274,905 filed on Nov. 14, 2005 and entitled “MANAGING SPONSORED CONTENT BASED ON GEOGRAPHIC REGION”, which is a continuation of U.S. application No. 11/274,933 filed on Nov. 14, 2005 and entitled “PRESENTATION OF SPONSORED CONTENT ON MOBILE COMMUNICATION FACILITIES”, which is a continuation of U.S. application No. 11/271,164 filed on Nov. 11, 2005 and entitled “MANAGING SPONSORED CONTENT BASED ON DEVICE CHARACTERISTICS”, which is a continuation of U.S. application No. 11/268,671 filed on Nov. 5, 2005 and entitled “MANAGING PAYMENT FOR SPONSORED CONTENT PRESENTED TO MOBILE COMMUNICATION FACILITIES”, and which is a continuation of U.S. application No. 11/267,940 filed on Nov. 5, 2005 and entitled “MANAGING SPONSORED CONTENT FOR DELIVERY TO MOBILE COMMUNICATION FACILITIES,” which is a non-provisional of U.S. application No. 60/731,991 filed on Nov. 1, 2005 and entitled “MOBILE SEARCH”, U.S. application No. 60/720,193 filed on Sep. 23, 2005 and entitled “MANAGING WEB INTERACTIONS ON A MOBILE COMMUNICATION FACILITY”, and U.S. application No. 60/717,151 filed on Sep. 14, 2005 and entitled “SEARCH CAPABILITIES FOR MOBILE COMMUNICATIONS DEVICES”.
BACKGROUND OF THE INVENTION1. Field of the Invention
This disclosure relates to the field of mobile communications and more particularly to improved methods and systems directed to targeting advertising to mobile and non-mobile communication facilities accessed by the same user.
2. Description of Related Art
Web-based search engines, readily available information, and entertainment mediums have proven to be one of the most significant uses of computer networks such as the Internet. As online use increases, users seek more and more ways to access the Internet. Users have progressed from desktop and laptop computers to cellular phones and smartphones for work and personal use in an online context. Now, users are accessing the Internet not only from a single device, but from their televisions and gaming devices, and most recently, from tablet devices. Internet-based advertising techniques are currently unable to optimally target and deliver content, such as advertisements, for a mobile communication facility (e.g., smartphone, tablet device, etc.) because the prior art techniques are specifically designed for the Internet in a non-mobile device context. These prior art techniques fail to take advantage of unique data assets derived from telecommunications and fixed mobile convergence networks. As it becomes commonplace for a user to interchangeably access the Internet via his smartphone, tablet, PC, and television, there is no efficient way to optimally target that same user across all the devices he may use. Therefore, a need exists for a system associated with telecommunications networks and fixed mobile convergence applications that is enabled to select and target advertising content readable by a plurality of mobile and non-mobile communication facilities and Internet platforms that is available from across a number of advertising inventories.
SUMMARY OF THE INVENTIONTo overcome the deficiencies of the prior art, what is needed, and has not heretofore been developed, is a system associated with telecommunications networks and fixed mobile convergence applications that is enabled to select and target advertising content readable by a plurality of mobile and non-mobile communication facilities and that is available from across a number of advertising inventories.
The present invention includes a system for determining interests of users of mobile and non-mobile communication devices based on data received from a plurality of data providers, wherein the system is configured to perform the steps of: (a) obtaining multiple datasets, wherein each dataset comprises at least one user and at least one corresponding attribute for the at least one user; (b) creating a first cluster comprising a first user from at least one dataset and the at least one corresponding attribute for the first user; (c) creating a second cluster comprising a second user from the at least one dataset and the at least one corresponding attribute for the second user; (d) merging the first cluster with the second cluster; and (e) assigning values to previously unknown attributes based on probabilistic estimations.
In one embodiment, a system for determining interests of users of mobile and non-mobile communication devices based on data received from a plurality of data providers may include one or more computers having computer readable mediums having stored thereon instructions which, when executed by one or more processors of the one or more computers, causes the system to perform the steps of: (a) receiving a first dataset from a first data provider, wherein the first dataset includes a first and second user and a respective first plurality of attributes corresponding to the first and second users; (b) receiving a second dataset from a second data provider, wherein the second dataset includes the first and second user and a respective second plurality of attributes corresponding to the first and second users, wherein at least some of the plurality of first attributes is different from the second plurality of attributes, wherein respective attributes of the pluralities of the first and second attributes include corresponding indications of likes and dislikes thereof, and wherein respective attributes of the pluralities of first and second attributes lack a corresponding indication of the likes or dislikes thereof; (c) creating a third dataset by combining the first and second datasets, wherein the third dataset includes: (i) the first and second users; (ii) the first and second plurality of attributes; (iii) the respective attributes of the pluralities of the first and second attributes including the corresponding indications of likes and dislikes thereof; and (iv) the respective attributes of the pluralities of the first and second attributes lacking a corresponding indication of the likes or dislikes thereof; (d) for at least one attribute of the first plurality of attributes lacking a corresponding indication of the likes or dislikes thereof for the first user, determining an indication of a liking for the attribute by determining that: (i) a first set of a plurality of attributes for the first user has an indication of a liking by the first user of each attribute of the plurality of attributes; and (ii) a second set of a plurality of attributes for the second user has an indication of a liking by the second user of each attribute of the plurality of attributes, wherein the first set of the plurality of attributes is contextually similar to the second set of the plurality of attributes; (e) selecting an advertisement contextually relevant to the attribute of the first plurality of attributes that previously lacked a corresponding indication of the like or dislike thereof by the first user; and (f) transmitting the selected advertisement to a communications device of the first user for display thereon. The communications device may be one of a cellular phone, a tablet, a portable media player, a laptop or notebook computer, a television, a game console, a cable box, and a personal computer, however, this list is not to be construed as being limiting.
These and other features and characteristics of the present invention, as well as the methods of operation and functions of the related elements of structures and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures.
A first system developed to overcome the deficiency in the prior art is bridging. A bridge is a system of linking two different Internet platforms so that both platforms may coexist harmoniously on a single device or from device to device. A bridge brings an audience to advertising agencies and networks via mobile, PC-online and off-line data.
A bridge leads platform convergence, which includes mobile, PC, and television, with mobile at the epicenter. The invention's strategy is to bridge technology for these three platforms to create an unparalleled interactive experience for mobile users. To accomplish this, an advertising network may offer complete campaign management including: concept, creation, delivery, billing, technology, performance analysis, and customer service to publishers and application and game developers.
A bridge may be established by a hybrid smartphone application. A hybrid application is a mobile website embedded into a downloadable application. It is a combination of web page and application that uses HTML5 and native functions of the smartphone to allow the application and web page to exist side by side, using the best features of a web page and application together. This may permit media brands to have a greater interaction with their customers while delivering an engaging user experience.
The web page exists within the application through a web widget. The widget renders web pages within the application. The web page with application does not share the same cookie pool as its web page outside the application.
A major component of bridging is online game play. Game developers are seeking a transition between web pages and social media sites that offer games to smartphones, as well as a transition of the game experience between different makes of smartphones. A bridge transitions a game in JavaScript to HTML5-based applications for various mobile and social media platforms.
A second major component of bridging is shopping and commerce. To reach consumers from their televisions or print media to their mobile devices, shoppers may scan a bar code presented on a television or print advertisement, which then redirects them to a web page or application download. Consumers may also “clip” coupons with a text message when they see a short code (a truncated phone number) in television, print, on-package, online and mobile advertisements. Then, texting the code instantly loads the coupons onto consumers' loyalty cards from participating merchants. The coupons are automatically redeemed when shoppers swipe their loyalty cards at checkout.
Bridging may also transition between location data, social media, and shopping incentives. For example,
Companion advertisements have many possibilities. The check-ins themselves provide geocode information, so that if there is no current advertisement for a specific location, the advertising network may find a nearby one. For example, if the check-in was at an independently run restaurant that has no current coupon, the advertising network might offer a coupon for the closest Starbucks.
Bridging is valuable to an advertising network because it allows the network to reach audiences more effectively. An advertising network may aggregate mobile “endemic data.” For example, an advertising network receives interest data from publishers in its network. The advertising network may also aggregate data from web pages and applications that are outside its network as another vantage point on the users it encounters. Wherever possible, these relationships may span PC-online and mobile. If a log-in is available, the advertising network will seek to gain access to match keys and make additional links between PC-online and mobile. The data that the advertising network amasses will be made available to its advertisers so that the advertisements may better reach the target audience.
Another system developed to overcome the deficiency in the prior art is smart traffic. An advertising network may direct their advertising via “smart traffic.” Smart traffic is the determination of which advertiser to give the impression based on available budgets and available space. This is a targeted form of inventory optimization, in which an advertising network maximizes the value of a perishable good.
An advertising network may use multivariate click and conversion history to optimize its yield optimization. This process is to improve the current yield optimization algorithm. To determine an accurate calculation of click through or conversion rates, an advertising network must first be able to categorize impressions. This is so that it can improve the targeting of the impression to improve the probability that an advertisement is clicked and an action is taken. Second, it needs a practical way to match impressions with ads. Since each impression is a combination of multiple features describing the category of the impression, all relevant combinations will need to be matched with corresponding advertisements. As the number of impression features increases, so does the number of matches to calculate click through rate. An advertising network may develop a hybrid of static offline metrics with real time online information. The algorithm uses a maximum of 4 GB of memory for real time calculations.
Another system developed to overcome the deficiency in the prior art is collaborative filtering. An advertising network may use collaborative filtering. Collaborative filtering is the process of filtering for information or patterns using techniques involving collaboration among multiple agents, viewpoints, and data sources. Applications of collaborative filtering typically involve very large data sets. Collaborative filtering is a method of making automatic predictions, the filtering, about the interests of a user by collecting preferences or taste information from many users, the collaborating. The assumption of the collaborative filtering approach is that those who agreed in the past tend to agree again in the future. For example, a collaborative filtering for television tastes could make predictions about which television show a user should like given a partial list of that user's likes or dislikes. These predictions are specific to the user, but use information gleaned from many users. This differs from a simpler approach of giving an average score for each item of interest, such as based on a number of votes.
Another system developed to overcome the deficiency in the prior art is advertisement affinity. An advertising network may identify users who interact with one advertisement to determine who will interact with another type of advertisement. Affinity targeting is simply a way of targeting advertisements. It is a method of maximizing clicks, and profits of online advertisement affinity focuses on the attitude of website visitors toward online advertising. It further suggests that if a user likes a certain web page more than others, he will not only devote more time on that site but also be more receptive to its advertisements. A network may measure the connection between user attitude towards websites and their online advertisements. High-affinity visitors are expected to exhibit the following characteristics: users spend more time at the page; users are more positive toward the page and its content; and users are more positive toward advertisements on the site.
What makes a user take a liking to a certain website depends on many things, but if users become loyal to an affiliate site, the conversion rate most definitely will increase. Visitors will not click on banners and ad-links just because they like the web page, but when people normally are restricted and skeptic toward an advertisement, a web page's loyal visitors will more receptive to the advertisement and its message.
A publisher of a web page may use similar data in conjunction with an advertising network. If a user has already shown interest in what a publisher has to offer, should an advertising network show the user a way back to the publisher's page, the user is more likely to follow through. This results in increased click through rates. The system may flow like this example: 1) Publisher, “P” has an active publisher account with Advertising Network, “A.” 2) P has created an advertiser account with A and has set up a campaign with the intention of pulling users into its web page (or application), via advertisements such as “Visit (name of page)!” or “Play (name of application)!” 3) User “U” is browsing or playing P's web page or application, and is served advertisements from A. A notes that an interaction has taken place between U and P. 4) U jumps to another publisher's website or application, which also has an active account with A. A identifies that U has switched publishers, recalls the U/P interaction, and then serves advertisements per P's campaign to U.
No special integration is required on behalf of the publisher with the advertising network. The existing account is sufficient. The advertising network may either explicitly permit the publisher to turn on this feature per campaign, allowing the advertising network to charge an additional fee. The advertising network may alternatively turn on this feature per campaign implicitly to increase click through rates to gain revenue.
Another system developed to overcome the deficiency in the prior art is probabilistic attachment of attributes. Probabilistic attachment of attributes involves clustering users based on attributes gathered from various data providers and assigning values to unidentified attributes based on probability. Users are identified through selected attributes and grouped into clusters for better advertisement targeting. The attributes can be selected from, but not limited to, first party data such as handset, location, browsing behavior, etc. and/or third party data such as demographics, purchase behavior, and/or interests such as outdoor activities or electronics, etc. Once the users are in a cluster, additional attributes can be gathered or selected from first or third party data to further identify the users' habits and behaviors through probability. Specifically, a user may have unknown values for a particular attribute, the system will then provide a value for the user on the particular attribute based on highly correlated and similar users.
More specifically, this invention is broken down into two phases. The first phase is clustering and the second phase is dataset merging. In clustering, all users in each dataset are used to generate clusters using a multi-attribute method. High level analysis of quality of the clusters is performed by calculating inter-cluster distances for all pairwise combinations of clusters, and intra-cluster distances & densities for each cluster by sampling. Clusters may be merged based on pairwise comparison of inter-cluster distances and pairwise comparison of user level correlations. All users in unmerged clusters are considered to look alike with higher probability of match than users in merged clusters. The attributes for the users in each cluster may be recommended to other users in the same cluster. In dataset merging, when merging datasets with some users being common between datasets, clusters are developed independently for each cluster. Users that are common users between datasets are identified. All clusters with common users are identified. Common users get the combined set—union of attributes from the corresponding datasets. The union of attributes is propagated to all users in the corresponding clusters in the merged datasets. The probability of match for the propagated data is lower than the union of attributes for common users. Users in clusters that do not have any users that are common between datasets are merged with the most closely correlated cluster. The propagation of attributes for these users has the least amount of confidence. Correlation of the same cluster with just the common users and all users is used to generate the probability value for the propagated users.
When server 605 collects table 602 and table 604, it will use one of table 602 and table 604 as a base table to construct table 606. In this example, server 605 chooses to use table 602 as the base table, however, server 605 could have used table 604 as the base table. The choice is arbitrary. Since server 605 uses table 602 as the base table, the information in table 606 that came from table 602 would not be altered. However, table 606 has populated the originally blank spaces in table 604 with estimates. Additionally, although the users here are identified through their first names in tables 602, 604 and 606, they can be identified through other methods including, but not limited to, profile ID, carrier ID, hardware ID, manufacturer ID, hashed code ID, hashed email ID, etc. The IDs can also be encrypted so that the no personal information will be revealed.
With respect to Kevin, Kevin's interest in cosmetics has been populated with an “O_LA” because server 605 has identified that the most similar user, Sam, has an “O” in cosmetic. Sam is identified as the most similar user because by examining the interests in both table 602 and table 604, Sam is almost identical in all interests except for football. Even if John had an “X” in fishing, Kevin's interest in cosmetics would still be “O_LA” because Sam is still the most similar user. However, if John had an “X” in fishing and “O” in travel, then Kevin's interest in cosmetics would remain blank. The fact that cosmetics is a different genre of interest from sports like, basketball, football, fishing and baseball is not a consideration for server 605 in making the probabilistic estimates. This is because server 605 will conduct live campaigns in the future to verify whether such probabilistic estimates are in fact correct.
With respect to John, John's interest in travel has been populated with an “O_LA” because server 605 has also identified that the most similar user, Sam, has an “O” in travel. Although John and Sam's interests are not similar to a degree like that of Kevin and Sam's, as long as the degree of similarity is within an acceptable threshold, server 605 will assign “O_LA” or “X_LA” to the particular interest. Alternatively, if the degree of similarity is below the acceptable threshold, server 605 would simply leave the interest blank.
Targeted advertising may then be implemented by selecting advertisements relating to the newly identified interests and transmitting the advertisement(s) to any of the one or more communication devices associated with the user. The advertisement(s) may be displayed in the context of web pages, applications, and other mediums, as is known in the art. It is to be understood that the various attributes obtained from data provides may include other items instead of or in addition to just interests (e.g., hobbies). For example, attributes that may be correlated may be demographics, including online behaviors (e.g., viewing habits, browsing habits, transaction/shopping habits, etc.) and other personally identifiable data, as listed in the prior-filed applications listed above and incorporated herein by reference. Furthermore, similarities between the attributes may be contextual, contemporaneous, logically, numerically, etc. based.
Since the newly identified interests are calculated based on probability, verification may be needed to ensure the newly attached interests are in fact true. One way of doing so is through A/B testing in live campaigns. Live campaigns determine whether the user is receptive of the advertisements pushed based on newly assigned interests. This live campaign can be conducted throughout a predetermined period of time or any dynamic testing environment. In
Another system developed to overcome the deficiency in the prior art is bumping. An advertising network may use bumping devices to reach users. Tapping two smartphones together may transfer information, music, and even money. Smartphones may recognize tapping motions and map them. When a bump is recognized, a signal is sent to cloud servers that match it with another bump that occurred at the exact same place and time. It decides those two bumps are a match, and exchanges information between them.
Users may need to log into secure account settings to use a bump feature. Upon a successful bump, an advertising network may access additional data about a user to add to the user's hashed identification.
Another system developed to overcome the deficiency in the prior art is user prediction. An advertising network may predict a user's web page or application destinations. By identifying a user's repetitive behavior, a network may prepare in advance to send targeted or customized advertisements to a user.
Another system developed to overcome the deficiency in the prior art is photo metadata. An advertising network may use photo metadata to develop profiles and customize advertisements. Photos, taken from a user's photos available online, may be added to an advertisement for a specific user. Regardless of the format, these files can store not only image data but also information about the images. Metadata is, literally, data about data. When included in image files, this information is photo metadata.
Metadata is actually part of the image file, effectively a bundle of image data and information about that image. Digital photo files can include descriptive, technical, and administrative classes of metadata of several types. These can list an image's creator, copyright holder, source and description. They may also explain rights released and available to an image; how and when an image was created; and its size, color characteristics and more. Embedding and preserving photo metadata can prevent and solve many issues confronting photographers and others who work with digital images.
Thus, an appropriately configured system may perform the steps of (a) receiving at least one photo taken by a user via a mobile communication facility; (b) extrapolating at least one photo metadata from the at least one photo; (c) determining that a pre-existing universal profile has not been created for the user; (d) creating a user profile for the user; (e) storing the at least one extrapolated photo metadata in the user profile; and (f) providing advertisements to the user based on the at least one extrapolated photo metadata.
Another system developed to overcome the deficiency in the prior art is real time streaming. An advertising network may use real time stream processing to produce profiles. A profile is updated in real time in accordance with the action the user just took, whether it was surfing web pages, completing a purchase, or uploading a picture. The profile is refreshed in real time to include the new information to better target advertisements upon the user's next action.
Another system developed to overcome the deficiency in the prior art is advertisements caching. An advertising network may cache advertisements. It may preload advertisements, then fire the data at a later time, often based on a user's predicted destination. The delivery of an advertisement to a browser from local cache or a proxy server's cache. When a user requests a page that contains a cached advertisement, the advertisement is obtained from the cache and displayed.
Another system developed to overcome the deficiency in the prior art is sequential targeting. An advertiser may want to sequentially target a particular user on a plurality of screens. For example, an advertiser may have five advertisements that relate to the same product or service that should be viewed in a particular order. The advertising network may fire advertisements 1, 2, and 3 to a user while on his mobile device, then fire advertisements 4 and 5 when the user is on his PC. This method ensures the user will see all five advertisements without repetition.
As advertisements appear across a plurality of devices, there is a growing need for improved methods of paying for these advertisements. A smart pricing strategy for advertisers encompasses a smart pricing system that presents a platform for bidding in real time, wherein the platform offers competitive bidding for advertising space on a multitude of devices. The devices include, but are not limited to, smartphones, mobile phones, tablet devices, PCs, gaming devices, and televisions.
To achieve the smartest pricing, an advertiser gives a maximum it is willing to spend, and the advertising network makes sure to spend the maximum while simultaneously garnering the greatest click-though rate possible. As mentioned above, this spending is typically performed on a bidding platform. To manually override the platform is known as dumb pricing.
Similarly, smart pricing may optimize an advertiser's spending across multiple devices depending on the advertiser's audience. The smart pricing strategy may target 5% of the advertisements to mobile phones, while 95% to tablet devices.
The goal of any advertising or smart pricing is to achieve a conversion. A conversion is the action intended by the site owner, typically a user making a purchase. Should a Retargeting is a form of online targeted advertising by which online advertising is delivered to consumers based on previous Internet actions that did not previously result in a conversion. However, when a conversion does result, an advertising network may use alternative or post sale actions to create additional conversions. A third party may take the conversion data to create new events or incentives around a completed purchase.
Similarly, incentives may be used to opt into advertising or targeting through bridges. For example, a user opts in on his phone in exchange for a free reward. When the user access a web page from a PC, his opt in status will travel with him from mobile web to PC web.
In various embodiments, information from third party may be provided by a loyalty program or reward card. Supermarket and pharmacy shoppers, as well as other retail shoppers, may be provided incentives to participate and provide personal information that may be used by the system, including but not limited to cash back incentives, discounts, coupons, loyalty programs, or some other type of incentive. For example, the use of reward card may indicate the frequency of a shopper's visits to a particular retailer. Furthermore, the reward card number or bar code may be presented directly from a mobile communication facility.
If a reward card is presented via a mobile communication facility, it may be part of a mobile wallet. A mobile wallet's capabilities include a tap-to-pay feature; the ability to link credit and debit cards; storage of all loyalty or rewards cards and identification numbers; integration with third party applications; and secure elements on the SIM card rather than the phone itself. A user also has a PIN code option to protect all purchases on the mobile communication facility.
A mobile wallet may also support coupon storage. Coupons may be deposited with or without action by the user of the mobile communication facility. A coupon may also be added via a URL. An advertisement may insert a coupon, either by linking directly to it and allowing the or by using a special link that assures the web browser opens to present the URL.
A user may create a mobile wallet within an application. For example, applications such as Key Ring allow a user to scan and store existing loyalty cards, enroll in new loyalty programs, and access exclusive coupons and discounts. The user's shopping habits as recorded through use of the mobile wallet may be used to target advertisements.
The methods and systems described herein may be deployed in part or in whole through a machine that executes computer software program codes, and/or instructions on one or more processors. The one or more processors may be part of a server, client, network infrastructure, mobile computing platform, stationary computing platform, cloud computing, or other computing platform. The processor(s) may be communicatively connected to the Internet or any other distributed communications network via a wired or wireless interface. The processor(s) may be any kind of computational or processing device capable of executing program instructions, codes, binary instructions and the like. The processor(s) may be or include a signal processor, digital processor, embedded processor, microprocessor or any variant such as a co-processor (math co-processor, graphic co-processor, communication co-processor and the like) and the like that may directly or indirectly facilitate execution of program code or program instructions stored thereon. In addition, the processor(s) may enable execution of multiple programs, threads, and codes. The threads may be executed simultaneously to enhance the performance of the processor(s) and to facilitate simultaneous operations of the application. The processor(s) may include memory that stores methods, codes, instructions and programs as described herein and elsewhere. The processor(s) may access a storage medium through an interface that may store methods, codes, and instructions as described herein and elsewhere. The storage medium associated with the processor(s) for storing methods, programs, codes, program instructions or other type of instructions capable of being executed by the computing or processing device may include but may not be limited to one or more of a CD-ROM, DVD, memory, hard disk, flash drive, RAM, ROM, cache and the like.
The methods and/or processes described above, and steps thereof, may be realized in hardware, software or any combination of hardware and software suitable for a particular application. The hardware may include a general purpose computer and/or dedicated computing device or specific computing device or particular aspect or component of a specific computing device. The processes may be realized in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable device, along with internal and/or external memory. The processes may also, or instead, be embodied in an application specific integrated circuit, a programmable gate array, programmable array logic, or any other device or combination of devices that may be configured to process electronic signals. It will further be appreciated that one or more of the processes may be realized as a computer executable code capable of being executed on a machine readable medium.
The computer executable code may be created using a structured programming language such as C, an object-oriented programming language such as C++, or any other high-level or low-level programming language (including assembly languages, hardware description languages, and database programming languages and technologies) that may be stored, compiled or interpreted to run on one of the above devices, as well as heterogeneous combinations of processors, processor architectures, or combinations of different hardware and software, or any other machine capable of executing program instructions.
Thus, in one aspect, each method described above and combinations thereof may be embodied in computer executable code that, when executing on one or more computing devices, performs the steps thereof In another aspect, the methods may be embodied in systems that perform the steps thereof, and may be distributed across devices in a number of ways, or all of the functionality may be integrated into a dedicated, standalone device or other hardware. In another aspect, the means for performing the steps associated with the processes described above may include any of the hardware and/or software described above. All such permutations and combinations are intended to fall within the scope of the present disclosure.
Further, although process steps, method steps, algorithms or the like may be described in a sequential order, such processes, methods and algorithms may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described in this patent application does not, in and of itself, indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously despite being described or implied as occurring non-simultaneously (e.g., because one step is described after the other step). Moreover, the illustration of a process by its depiction in a drawing does not imply that the illustrated process is exclusive of other variations and modifications thereto, does not imply that the illustrated process or any of its steps are necessary to the invention, and does not imply that the illustrated process is preferred.
It will be readily apparent that the various methods and algorithms described herein may be implemented by, e.g., appropriately programmed general purpose computers and computing devices. Typically a processor (e.g., a microprocessor) will receive instructions from a memory or like device, and execute those instructions, thereby performing a process defined by those instructions. Further, programs that implement such methods and algorithms may be stored and transmitted using a variety of known media. When a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the present invention need not include the device itself.
The term “computer-readable medium” as used herein refers to any medium that participates in providing data (e.g., instructions) that may be read by a computer, a processor or a like device. Such a medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks and other persistent memory. Volatile media include dynamic random access memory (DRAM), which typically constitutes the main memory. Transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise a system bus coupled to the processor. Transmission media may include or convey acoustic waves, light waves and electromagnetic emissions, such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, a PROM, an EPROM, a FLASH-EEPROM, any other memory chip or cartridge, a carrier wave as described hereinafter, or any other medium from which a computer can read. Various forms of computer readable media may be involved in carrying sequences of instructions to a processor. For example, sequences of instruction (i) may be delivered from RAM to a processor, (ii) may be carried over a wireless transmission medium, and/or (iii) may be formatted according to numerous formats, standards or protocols, such as Bluetooth, TDMA, CDMA, 3G, LTE, WiMax. A non-transitory computer-readable medium includes all computer-readable medium as is currently known or will be known in the art, including register memory, processor cache, and RAM (and all iterations and variants thereof), with the sole exception being a transitory, propagating signal.
Where databases are described, it will be understood by one of ordinary skill in the art that (i) alternative database structures to those described may be readily employed, and (ii) other memory structures besides databases may be readily employed. Any schematic illustrations and accompanying descriptions of any sample databases presented herein are illustrative arrangements for stored representations of information. Any number of other arrangements may be employed besides those suggested by the tables shown. Similarly, any illustrated entries of the databases represent exemplary information only; those skilled in the art will understand that the number and content of the entries can be different from those illustrated herein. Further, despite any depiction of the databases as tables, other formats (including relational databases, object-based models and/or distributed databases) could be used to store and manipulate the data types described herein. Likewise, object methods or behaviors of a database can be used to implement the processes of the present invention. In addition, the described databases may, in a known manner, be stored locally or remotely from a device that accesses data in such a database.
Numerous embodiments are described in this patent application, and are presented for illustrative purposes only. The described embodiments are not intended to be limiting in any sense. The invention is widely applicable to numerous embodiments, as is readily apparent from the disclosure herein. Those skilled in the art will recognize that the present invention may be practiced with various modifications and alterations. Although particular features of the present invention may be described with reference to one or more particular embodiments or figures, it should be understood that such features are not limited to usage in the one or more particular embodiments or figures with reference to which they are described.
In the foregoing description, reference is made to the accompanying drawings that form a part of the present disclosure, and in which are shown, by way of illustration, specific embodiments of the invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention, and it is to be understood that other embodiments may be utilized and that structural, logical, software, electrical and other changes may be made without departing from the scope of the present invention. The present disclosure is, therefore, not to be taken in a limiting sense. The present disclosure is neither a literal description of all embodiments of the invention nor a listing of features of the invention that must be present in all embodiments.
Although the invention has been described in detail for the purpose of illustration based on what is currently considered to be the most practical and preferred embodiments, it is to be understood that such detail is solely for that purpose and that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present invention contemplates that, to the extent possible, one or more features of any embodiment can be combined with one or more features of any other embodiment.
Claims
1. A system for determining interests of users of mobile and non-mobile communication devices based on data received from a plurality of data providers, the system including one or more computers having computer readable mediums having stored thereon instructions which, when executed by one or more processors of the one or more computers, causes the system to perform the steps of:
- (a) receiving a first dataset from a first data provider, wherein the first dataset includes a first and second user and a respective first plurality of attributes corresponding to the first and second users;
- (b) receiving a second dataset from a second data provider, wherein the second dataset includes the first and second user and a respective second plurality of attributes corresponding to the first and second users, wherein at least some of the plurality of first attributes is different from the second plurality of attributes, wherein respective attributes of the pluralities of the first and second attributes include corresponding indications of likes and dislikes thereof, and wherein respective attributes of the pluralities of first and second attributes lack a corresponding indication of the likes or dislikes thereof;
- (c) creating a third dataset by combining the first and second datasets, wherein the third dataset includes: (i) the first and second users; (ii) the first and second plurality of attributes; (iii) the respective attributes of the pluralities of the first and second attributes including the corresponding indications of likes and dislikes thereof; and (iv) the respective attributes of the pluralities of the first and second attributes lacking a corresponding indication of the likes or dislikes thereof;
- (d) for at least one attribute of the first plurality of attributes lacking a corresponding indication of the likes or dislikes thereof for the first user, determining an indication of a liking for the attribute by determining that: (i) a first set of a plurality of attributes for the first user has an indication of a liking by the first user of each attribute of the plurality of attributes; and (ii) a second set of a plurality of attributes for the second user has an indication of a liking by the second user of each attribute of the plurality of attributes, wherein the first set of the plurality of attributes is contextually similar to the second set of the plurality of attributes;
- (e) selecting an advertisement contextually relevant to the attribute of the first plurality of attributes that previously lacked a corresponding indication of the like or dislike thereof by the first user; and
- (f) transmitting the selected advertisement to a communications device of the first user for display thereon.
2. The system of claim 1, wherein the communications device is one of:
- (a) a cellular phone;
- (b) a tablet;
- (c) a portable media player;
- (d) a laptop or notebook computer.
- (e) a television;
- (f) a game console;
- (g) a cable box; and
- (h) a personal computer.
Type: Application
Filed: Nov 4, 2012
Publication Date: May 16, 2013
Inventor: Jumptap, Inc. (Boston, MA)
Application Number: 13/668,300
International Classification: G06Q 30/02 (20120101);
