Patent application number | Description | Published |
20100070535 | DATA SCHEMA TRANSFORMATION USING DECLARATIVE TRANSFORMATIONS - Embodiments of the present invention relate to systems, methods and computer storage media for transforming data defining a first data schema to data defining a second data schema by way of a declarative transformation. The transformation includes identifying data defining the first data schema. A declarative transformation is generated to transform the data defining the first data schema to data defining the second data schema. The declarative transformation additionally transforms data instantiated in the first data schema into a data structure of the second data schema. The declarative transformation is generated prior to the second data schema being defined. The declarative transformation, in an embodiment, is utilized to generate the second data schema. The data is transformed utilizing a migration code that is derived from the declarative transformation. In an exemplary embodiment, the declarative transformation is expressed in textual form by a person, and/or utilizing a graphical computer application. | 03-18-2010 |
20140149355 | STREAMING RESTORE OF A DATABASE FROM A BACKUP SYSTEM - A distributed data warehouse system may maintain data blocks on behalf of clients in multiple clusters in a data store. Each cluster may include a single leader node and multiple compute nodes, each including multiple disks storing data. The warehouse system may store primary and secondary copies of each data block on different disks or nodes in a cluster. Each node may include a data structure that maintains metadata about each data block stored on the node, including its unique identifier. The warehouse system may back up data blocks in a remote key-value backup storage system with high durability. A streaming restore operation may be used to retrieve data blocks from backup storage using their unique identifiers as keys. The warehouse system may service incoming queries (and may satisfy some queries by retrieving data from backup storage on an as-needed basis) prior to completion of the restore operation. | 05-29-2014 |
20140149356 | AUTOMATIC REPAIR OF CORRUPTED BLOCKS IN A DATABASE - A distributed data warehouse system maintains data blocks on behalf of clients, and stores primary and secondary copies of data blocks on different disks or nodes in a cluster. The data warehouse system may back up data blocks in a key-value backup storage system. In response to a query targeting a data block previously stored in the cluster, the data warehouse system may determine whether a consistent, uncorrupted copy of the data block is available in the cluster (e.g., by applying a consistency check). If not (e.g., if a disk or node failed), the data warehouse system may automatically initiate an operation to restore the data block from the backup storage system, using a unique identifier of the data block to access a backup copy. The target data may be returned in a query response prior to restoring primary and secondary copies of the data block in the cluster. | 05-29-2014 |
Patent application number | Description | Published |
20080250033 | SYSTEM AND METHOD FOR DETERMINING AN EVENT OCCURENCE RATE - Described are a system and method for determined an event occurrence rate. A sample set of content items may be obtained. Each of the content items may be associated with at least one region in a hierarchical data structure. A first impression volume may be determined for the at least one region as a function of a number of impressions registered for the content items associated with the at least one region. A scale factor may be applied to the first impression volume to generate a second impression volume. The scale factor may be selected so that the second impression volume is within a predefined range of a third impression volume. A click-through-rate (CTR) may be estimated as a function of the second impression volume and a number of clicks on the content item. | 10-09-2008 |
20080294577 | Efficient Estimation of Events with Rare Occurrence Rates Using Taxonomies - Methods for predicting the click-through rates of Internet advertisements placed into web pages are disclosed. Specifically, a click-through rate prediction is generating using a hybrid system with two terms. The first term is constructed using a machine learning model that incorporates a limited number of important factors. The second term is constructed using a look-up table that is built using a complex statistical analysis of various web page and advertisement combinations. To construct the second term, the field of multi-level hierarchical modeling is used. Specifically, a tree-structured Markov model is used to process the training data and construct the adjustment factor look-up table. To reduce the complexity of the statistical analysis, Kalman-filters are used to estimate parameters in the traditional multi-level hierarchical models for scalability. | 11-27-2008 |
20090043597 | System and method for matching objects using a cluster-dependent multi-armed bandit - An improved system and method for matching objects using a cluster-dependent multi-armed bandit is provided. The matching may be performed by using a multi-armed bandit where the arms of the bandit may be dependent. In an embodiment, a set of objects segmented into a plurality of clusters of dependent objects may be received, and then a two step policy may be employed by a multi-armed bandit by first running over clusters of arms to select a cluster, and then secondly picking a particular arm inside the selected cluster. The multi-armed bandit may exploit dependencies among the arms to efficiently support exploration of a large number of arms. Various embodiments may include policies for discounted rewards and policies for undiscounted reward. These policies may consider each cluster in isolation during processing, and consequently may dramatically reduce the size of a large state space for finding a solution. | 02-12-2009 |
20090055139 | PREDICTIVE DISCRETE LATENT FACTOR MODELS FOR LARGE SCALE DYADIC DATA - A method for predicting future responses from large sets of dyadic data includes measuring a dyadic response variable associated with a dyad from two different sets of data; measuring a vector of covariates that captures the characteristics of the dyad; determining one or more latent, unmeasured characteristics that are not determined by the vector of covariates and which induce local structures in a dyadic space defined by the two different sets of data; and modeling a predictive response of the measurements as a function of both the vector of covariates and the one or more latent characteristics, wherein modeling includes employing a combination of regression and matrix co-clustering techniques, and wherein the one or more latent characteristics provide a smoothing effect to the function that produces a more accurate and interpretable predictive model of the dyadic space that predicts future dyadic interaction based on the two different sets of data. | 02-26-2009 |
20090063984 | Customized today module - A method and apparatus for customizing content presented to individual users or user segments is provided. There may be three components, a web portal and toolbar component, a modeling component, and a scoring component. The web portal and toolbar component presents content items and collects data. The web portal and toolbar component generates user event data based on the user actions. The user event data is forwarded to the modeling component. The modeling component generates content scoring functions based on user event data and attributes of content items. Content scoring functions may be unique to individual user segments. The content scoring functions based on content features generate probability a content item will be viewed. The scoring component decides which content items are placed in a portal. The scoring component uses the scoring functions generated by the modeling component to rank content items in real time. | 03-05-2009 |
20090070177 | System and Method for Optimally Allocating Overlapping Inventory - The present invention introduces methods for allocating: overlapping inventory. In the system of the present invention overlapping inventory problems are reformulated as a network transport problem. Specifically, different inventory types are represented as inventory network nodes. Similarly, corresponding inventory requests are also represented as request network nodes. The different inventory network nodes corresponding to inventory that can satisfy inventory requests are coupled to the request network nodes associated with those inventory requests. A source node is then coupled to the inventory network nodes and a destination node is coupled to the request network nodes. A flow limit of the available inventory is assigned to the connections between the source node and the inventory network nodes. Finally, inventory requests that must be satisfied are represented as flow minimums between the request network nodes and the destination network node. The transport network problem is then solved to solve the corresponding overlapping inventory allocation problem. | 03-12-2009 |
20100030717 | FRAMEWORK TO EVALUATE CONTENT DISPLAY POLICIES - Content display policies are evaluated using two kinds of methods. In the first kind of method, using information, collected in a “controlled” manner about user characteristics and content characteristics, truth models are generated. A simulator replays users' visits to the portal web page and simulates their interactions with content items on the page based on the truth models. Various metrics are used to compare different content item-selecting algorithms. In the second kind of method, no explicit truth models are built. Events from the controlled serving scheme are replayed in part or whole; content item-selection algorithms learn using the observed user activities. Metrics that measure the overall predictive error are used to compare different content-item selection algorithms. The data collected in a controlled fashion plays a key role in both the methods. | 02-04-2010 |
20110153550 | SYSTEM AND METHOD FOR DETERMINING AN EVENT OCCURRENCE RATE - Described are a system and method for determined an event occurrence rate. A sample set of content items may be obtained. Each of the content items may be associated with at least one region in a hierarchical data structure. A first impression volume may be determined for the at least one region as a function of a number of impressions registered for the content items associated with the at least one region. A scale factor may be applied to the first impression volume to generate a second impression volume. The scale factor may be selected so that the second impression volume is within a predefined range of a third impression volume. A click-through-rate (CTR) may be estimated as a function of the second impression volume and a number of clicks on the content item. | 06-23-2011 |
Patent application number | Description | Published |
20120084155 | PRESENTATION OF CONTENT BASED ON UTILITY - Methods and systems for presenting content such as articles based on utility are provided. In one embodiment, a plurality of articles are determined, each article in the plurality of articles including article content and a corresponding preview icon, the preview icon defining a link to the corresponding article content when presented. For each article in the plurality of articles, a user experience utility value is determined. And for each article in the plurality of articles, an economic utility value is also determined. A ranked order of the articles is determined based upon each article's user experience utility value and economic utility value. And a portion of the preview icons of the articles are presented on a graphical display page in a priority orientation based on the ranked order of the articles. | 04-05-2012 |
20140164136 | BROAD MATCHING ALGORITHM FOR DISPLAY ADVERTISEMENTS - A method of matching advertisements to users is disclosed. A plurality of attributes of a population of users is identified. A selection is received of an attribute of the plurality of attributes to which a target value is to be broadly matched. A correspondence of an advertisement to a user is determined based on a broad matching of the target value to the attribute. The advertisement is matched to the user based at least in part on the determining of the correspondence. | 06-12-2014 |
20140358826 | SYSTEMS AND METHODS FOR CONTENT RESPONSE PREDICTION - Techniques for predicting a user response to content are described. According to various embodiments, a configuration file is accessed, where the configuration file includes a user-specification of raw data accessible via external data sources and raw data encoding rules. In some embodiments, the raw data includes raw member data associated with a particular member and raw content data associated with a particular content item. Thereafter, source modules encode the raw data from the external data sources into feature vectors, based on the raw data encoding rules. An assembler module assembles one or more of the feature vectors into an assembled feature vector, based on user-specified assembly rules included in the configuration file. A prediction module performs a prediction modeling process based on the assembled feature vector and a prediction model, to predict a likelihood of the particular member performing a particular user action on the particular content item. | 12-04-2014 |
20150046278 | SYSTEM AND METHOD FOR POSITIONING SPONSORED CONTENT IN A SOCIAL NETWORK INTERFACE - A system and method optionally includes or utilizes a processor may receive a request for social network content for display in a position of a plurality of sponsored content positions in a newsfeed of a social network interface, each of the plurality of sponsored content positions having a position criterion, at least two of the plurality of sponsored content positions having a different position criterion and identify a sponsored content item of a plurality of sponsored content items stored on a database based, at least in part, on a characteristic of the sponsored content item meeting the position criterion and a bid associated with the sponsored content item. A transmitter may transmit the sponsored content item from the processor to a server for display on a user interface. | 02-12-2015 |
20150046515 | SYSTEM AND METHOD FOR POSITIONING SPONSORED CONTENT IN A SOCIAL NETWORK INTERFACE - A system and method may optional include or utilize a processor configured to receive a request for social network content for display in a sponsored content position in a newsfeed of a social network interface, the position having a position criterion, identify a sponsored content item of multiple sponsored content items stored on a database based, at least in part, on a characteristic of the sponsored content item meeting the position criterion, a bid associated with the sponsored content item, and a scaling factor, wherein each of the sponsored content items correspond to one of multiple item types and at least two of the sponsored content items are of a different item type. The scaling factor for each of the sponsored content items is based on the item type of the corresponding one of the sponsored content items. | 02-12-2015 |
20150088788 | SYSTEMS AND METHODS FOR CONTENT RESPONSE PREDICTION - Techniques for predicting a user response to content are described. According to various embodiments, a configuration file is accessed, where the configuration file includes a user-specification of raw data accessible via external data sources and raw data encoding rules. In some embodiments, the raw data includes raw member data associated with a particular member and raw content data associated with a particular content item. Thereafter, source modules encode the raw data from the external data sources into feature vectors, based on the raw data encoding rules. An assembler module assembles one or more of the feature vectors into an assembled feature vector, based on user-specified assembly rules included in the configuration file. A prediction module performs a prediction modeling process based on the assembled feature vector and a prediction model, to predict a likelihood of the particular member performing a particular user action on the particular content item. | 03-26-2015 |
Patent application number | Description | Published |
20140164064 | SYSTEM AND METHOD FOR SERVING ELECTRONIC CONTENT - A system and methods are provided for serving content in response to content queries or requests. When a request is received, for content to be presented to a specified user, candidate content items are identified, possibly based on matches between attributes of the user and attributes of the items' target audiences. For each item, a history indicating the frequency (e.g., total number) and/or recency with which impressions of the candidate item were previously presented to the user is retrieved and used to determine a modifier value, which is applied to a calculated or generated probable click-through-rate (pCTR) to produce a modified probability that the user would act on the item if it is served to him or her. Each item's estimated value is computed by multiplying a bid associated with the item and the modified probability; the results are ranked and the top-ranked item(s) are served. | 06-12-2014 |
20140207564 | SYSTEM AND METHOD FOR SERVING ELECTRONIC CONTENT - A system and methods are provided for serving content in response to content queries or requests. When a request is received, for content to be presented to a specified user, candidate content items are identified, possibly based on matches between attributes of the user and attributes of the items' target audiences. For each item, a history indicating the frequency (e.g., total number) and/or recency with which impressions of the candidate item were previously presented to the user is retrieved and used to determine a modifier value, which is applied to a calculated or generated probable click-through-rate (pCTR) to produce a modified probability that the user would act on the item if it is served to him or her. Each item's estimated value is computed by multiplying a bid associated with the item and the modified probability; the results are ranked and the top-ranked item(s) are served. | 07-24-2014 |