Abstract: Systems and method of the present invention provide for one or more server computers configured to receive one or more keywords topically relevant to a content of a web page, request from a search engine a first metric comprising a quantity of times the keywords have appeared in a search query with one or more question keywords during a time period and a second metric comprising a probability of receiving a high rank associated with the one or more keywords and the one or more question keywords, receive, from the search engine, the first metric and the second metric, calculate a keyword effectiveness index from the first metric and the second metric, and generate and transmit to a client computer one or more recommendations to include a high ranked suggested content on the web page according to the keyword effectiveness index.

Abstract: Provided are techniques for assessing object relevance. One or more user usage patterns are retrieved. Object properties of one or more objects are retrieved. The one or more user usage patterns are compared against the object properties of the one or more objects to compute one or more interaction scores that represent a value of how an object interacts with a user based on a current context of the user. Object importance is assigned to each of the one or more objects based on the one or more interaction scores.

Abstract: A system and device are provided for intelligently, or programmatically, assigning weights for one or more criterion utilized to score media content items based on an analysis of a group of media content items. In general, scoring criteria to be used to score media content items for a user are defined. A group of media content items associated with the user is then analyzed with respect to the criteria to provide results such as a number or percentage of media content items from the group of media content items that satisfy each of the scoring criteria. Based on the results of the analysis, a weight is assigned to each of the scoring criteria. Thereafter, media content items are scored as a function of the weights assigned to the scoring criteria.

Abstract: Relay of information from technical documentation by contact center workers to assist clients is limited by industry standard storage formats and query mechanisms. A method is disclosed for processing technical documents and tagging them against a Telecom Hardware domain ontology. The method comprises classical ontological Natural Language Processing (NLP) approaches to extract information from both text segments and tables, identifying text segments, named entities and relations between named entities described by an existing T-Box. A method for scoring candidate object property assertions derived from text before populating the Telecom Hardware ontology is also disclosed.

Abstract: A computer-implemented method of extracting key phrases from a document is disclosed comprising the steps of accessing a repository comprising linked subjects, the repository comprising first and second data structures representing the relationship between said subjects using different representation criteria; pruning the first data structure by removing links between subjects based on a further relationship between said subjects in the second data structure; matching phrases in said document to subjects in the pruned first data structure; further pruning the pruned first data structure by removing unmatched subjects that are not linked to matched subjects; determining a ranking for each matched subject; and selecting key phrases using the determined subject rankings. A computer program for implementing the steps of this method when executed on a computer is also disclosed.

Abstract: Embodiments of the present invention relate to an approach for characteristic-based (e.g., color) selection of items (e.g., clothing) in a networked computing environment (e.g., a cloud computing environment). Specifically, at least one computer storage device will be populated with a first set of items. The first set of items may be associated in the at least one computer storage device with a first set of corresponding characteristics. A computer data structure may then be generated that comprises compatibility scores of the first set of items to one another. A second set of items may then be received in the at least one computer storage device. The second set of items may also be accompanied by a second set of corresponding characteristics. A set of matches between the first set of items and the second set of items may then be generated according to one or more criteria.

Abstract: Co-selected images are labeled based on a topic score that is a measure of relevance of the co-selected image to a first topic to which a reference image belongs. The first topic to which the reference image belongs is identified based on a reference label associated with the reference image. The co-selected images are images that are selected for presentation subsequent to selection of the reference image during a user session. The co-selected images are identified based on selection data for user sessions in which the reference image was selected for presentation. The topic score is generated based on a frequency of selection of the co-selected image. Image search results for a second topic can be filtered to remove images that are labeled as belonging to the first topic or the image search results can be reordered to adjust the presentation positions at which images are referenced based on the topic to which the images belong.

Abstract: In a corpus of scientific articles such as a digital library, documents are connected by citations and one document plays two different roles in the corpus: document itself and a citation of other documents. A Bernoulli Process Topic (BPT) model is provided which models the corpus at two levels: document level and citation level. In the BPT model, each document has two different representations in the latent topic space associated with its roles. Moreover, the multi-level hierarchical structure of the citation network is captured by a generative process involving a Bernoulli process. The distribution parameters of the BPT model are estimated by a variational approximation approach.

Abstract: Provided are techniques for assessing object relevance. One or more user usage patterns are retrieved. Object properties of one or more objects are retrieved. The one or more user usage patterns are compared against the object properties of the one or more objects to compute one or more interaction scores that represent a value of how an object interacts with a user based on a current context of the user. Object importance is assigned to each of the one or more objects based on the one or more interaction scores.

Abstract: Particular embodiments of a social-networking system maintain one or more data stores storing a social graph comprising user nodes, concept nodes, and edges connecting the nodes. Particular embodiments may determine a confidence score with respect to a user node and a concept node, wherein the confidence score is based at least in part on affinity scores associated with the edges along a sequence of nodes between the user node and the concept node in the social graph. The confidence score may be based on an overall probability that a random walk starting at the user node will end at the concept node. This overall probability may be determined by calculating, for each edge in the random walk, the probability of taking that edge during the random walk, based on the affinity score associated with that edge.

Abstract: A system for organizing a plurality of candidates based on the relative similarity of a first candidate with respect to the remaining plurality of candidates is disclosed. The system includes a controller in communication with a storage device configured to receive and accessibly store a generated plurality of candidate images. The controller operable to analyze each of the plurality of candidate images to determined a numeric thumbnail based on a number of identified features in each of a plurality of grid elements of an array and a sum total number of all identified features in the array, calculate a similarity score between one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails; and generate a logical group image order as a function of the highest similarity score between the one of the plurality of determined numeric thumbnails and each of the remaining plurality of determined numeric thumbnails.

Abstract: A computer-implemented method comprises receiving a plurality of data streams into a data stream management system, wherein each data stream is obtained from a data streaming source and a reliance level is associated with each of the data streaming sources. When a continuous query is registered that specifies a reliance level attribute, the query is executed over the plurality of data streams using only those data streams obtained from a data streaming source associated with a suitable reliance level. For example, the reliance level attribute may establish a minimum reliance level, such that data stream having a lesser reliance level are not used. CQL may be enhanced with such an extra attribute which allows end users to specify the desired reliance level when submitting a query.

Abstract: A sensor data system, method and computer program configured to handle sensor data are disclosed. The system includes a reception unit adapted to receive sensor data, a storing unit adapted to store at least some of the received sensor data in an observations database, a recording unit adapted to record usage of the sensor data, and a relevance determination unit adapted to determine the relevance of the sensor data based on the recorded usage. A decision unit is adapted to remove excess sensor data with determined relevance below a limit from the observations database, and to retain relevant sensor data with determined relevance above the limit in the sensor database. Sensor data in an observations database may thereby be limited to a desired size, by removal of excess sensor data from the database.

Abstract: Provided herein are a method, apparatus and computer program product for the management of media files, for summarizing groups of media files, and presenting summarized groups of media files to a user. Example methods may include accessing a plurality of media files, obtaining identification of objects within each media file, and determining the minimum set cover of media files from the plurality of media files, where the minimum set cover of media files includes at least one media file comprising each object identified. The method may include determining a weight of each media file, where determining the weight includes analyzing the metadata of each media file. Example methods may also include identifying a dominant set from the plurality of media files, where the dominant set includes at least one dominant media file, and identifying at least one non-dominant media file from the plurality of media files.

Abstract: A method and system classifies a venue by analyzing venue data from a venue website. The method includes receiving preliminary venue-related data. The method includes scanning the venue website to retrieve venue data, wherein scanning the venue website includes retrieving the venue data from HTML pages, text documents, PDF documents, and images. The method includes retrieving verifiable venue data from the venue data. The verifiable venue data is a subset of the venue data. The method includes analyzing the verifiable venue data by comparing the verifiable venue data to the preliminary venue-related data and determining a probability level for the venue URL from the comparison. If the probability level for the venue URL is equal or greater than a first probability level, the venue website data is further analyzed to extract attributes and attribute counts in a robust and context-sensitive way.

Abstract: An information processing apparatus determines a weight of each physical feature for hierarchical clustering by acquiring training data of multiple pieces of content in triplets with label information indicating a pair specified by a user as having a highest degree of similarity among three contents of the triplet and executing hierarchical clustering using a feature vector of each piece of content of the training data and the weight of each feature to determine the hierarchical structure of the training data. The information processing apparatus updates the weight of each feature so that the degree of agreement between a pair combined first as being the same clusters among three contents of the triplet in a determined hierarchical structure and a pair indicated by label information corresponding to the triplet increases.

Abstract: Systems and methods for cases based analysis are described. In one implementation, a new case-based document having static attributes and dynamic attributes is received. Once the static and the dynamic attributes are received, the static attributes of the received new case-based document is compared with the static attributes of one or more previously processed case-based documents. Based on the comparison, a sub-set of case-based documents is generated. For the generated sub-set, the dynamic attributes of the new case-based document are compared with the dynamic attributes of the sub-set of case-based documents. Based on the comparison, previously processed case-based documents, if any, which are found to be similar to the new case-based document are identified.

Abstract: A method of processing content files may include receiving the content file, employing processing circuitry to determine an identity score of a source of a portion of at least a portion the content file, to determine a word score based for the content file and to determine a metadata score for the content file, determining a composite priority score based on the identity score, the word score and the metadata score, and associating the composite priority score with the content file for electronic provision of the content file together with the composite priority score to a human analyst.

Abstract: A method and apparatus for determining priority of data in a database managed by a computing device are provided. The data comprises a list of events, the computing device comprising a processing unit interconnected with a memory device and a display device. Context data is processing at the processing unit to determine a priority ranking for each of the items, wherein processing the context data to determine a priority ranking comprises at least one of processing attendance data, location, event data, and telephone record data. Respective areas of the display device are controlled to provide visual representations of each of the events, each respective area controlled according to the priority ranking.

Abstract: In a method for managing a plurality of data entities, data pertaining to transactions by a plurality of users with respect to the data entities is collected and a collaborative filtering operation is applied on the data entities to determine similarity levels of the data entities with respect to each other. In addition, for at least one of the data entities, remaining ones of the data entities are ranked according to the determined similarities while discounting for popularities of the data entities. Moreover, identifications of at least another one of the data entities having the highest rankings to the at least one of the data entities are presented to a first user to recommend the at least another one of the data entities for use by the first user.

Abstract: An index generating unit divides each name data of search target data both into words and into characters, calculates start and end scores showing a start and an end of each of the words and start and end scores showing a start and an end of each of the characters, links them to each entry word which constructs the name data as a list (a name ID, a position, and start and end scores), and stores this list in an index storage unit. A searching unit decomposes an input character string into partial character strings, acquires corresponding candidate entries from the index storage unit, and judges the continuity between candidate entries on the basis of lists to add a comparison score according to the continuity to a candidate entry.

Abstract: Embodiments of methods, systems and/or apparatuses relating to data processing in distributed computing environments are disclosed. In particular, methods, systems, and/or apparatuses for determining information similarly and/or performing related statistical techniques which may be implemented or operated in a distributed computing environment are disclosed.

Abstract: System, method and computer program that encompasses one or more client devices cooperating with a program host's on-line data processing center to generate media playlists. Data is transmitted from a program participant's client device to the processing center and is representative of media inventory in a media library on the client device and includes identification data of contained individual media items. Data is further received from a plurality of program participants representative of each respective program participant's media inventory, regardless of the source of the members of the inventory. Co-occurrence of pairs of individual media items in different program participants' media libraries is determined and a similarity rating is assigned between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants' media libraries. From this, a media playlist is generated.

Abstract: An electronic document analysis method receiving N electronic documents pertaining to a case encompassing a set of issues including at least one issue and establishing relevance of at least the N documents to at least one individual issue in the set of issues, the method comprising, for at least one individual issue from among the set of issues, receiving an output of a categorization process applied to each document in training and control subsets of the at least N documents, the output including, for each document in the subsets, one of a relevant-to-the-individual issue indication and a non-relevant-to-the-individual issue indication; building a text classifier simulating the categorization process using the output for all documents in the training subset of documents; and running the text classifier on the at least N documents thereby to obtain a ranking of the extent of relevance of each of the at least N documents to the individual issue.

Abstract: A system and method for providing job recommendations based on user behavior or characteristics are disclosed herein. The job recommendations are configured in accordance with a data set based on relational analysis of previous users' activity, or matches between job postings and the user's resume or user profile information. The presentation of job recommendations is triggered, configured, and provided transparently to the user.

Abstract: Provided is a lifestyle collecting apparatus that collects information for determining a lifestyle of a user, and includes: an object information detecting unit configured to detect object information representing an object around the user; a relevance degree calculating unit configured to calculate a relevance degree of the user to the object, using the object information; an appearance information extracting unit configured to extract appearance information from the object information, and add the relevance degree to the extracted appearance information, the appearance information representing an appearance of the object; and a lifestyle database which stores the appearance information to which the relevance degree has been added, as the information for determining the lifestyle of the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying a plurality of n-grams in a plurality of resources found in a particular site; determining, for each of the plurality of resources, a count of n-grams that originated in the resource; determining, based on counts of n-grams that originated in the resources, a first aggregate count of n-grams that originated in the particular site; determining a second aggregate count of the plurality of n-grams that were identified in the plurality of resources found in the particular site; and determining, based on the first and second aggregate counts, a site originality score for the particular site.

Abstract: Aspects and implementations of the present disclosure are directed to methods and systems of pre-processing a social network structure for fast discovery of cohesive groups. In general, in some implementations, a data processing system identifies a cohesive user group in a social network for delivery of a tailored content item. Generally, the data processing system identifies an affinity criteria; generates a set of user identifiers having characteristics that satisfy the affinity criteria; and generates graphs of users with at least one direct or indirect social network user connection with other user identifiers in the graph. The data processing system returns or stores the graph on computer readable media for later use. A graph may be generated with edges representing connections between user identifiers; edges may be weighted for the number and lengths of connection paths for indirect connections, and for similarities between users.

Abstract: An information search apparatus is provided. The information search apparatus includes: a character string input unit configured to obtain a character string from a client; a character string information search unit configured to obtain information that includes the character string from an index DB; a similarity calculation unit configured to calculate degree of similarity between the character string and searched information; and an output unit configured to output the searched information in descending order of the degree of similarity.

Abstract: A system and method for propagating classification decisions is provided. Text marked within one or more unclassified documents that is determined to be responsive to a predetermined issue is received from a user. The unclassified documents are selected from a corpus. A search query is generated from the responsive text. Same result documents are identified by applying inclusive search parameters to the query, applying the search query to the corpus, and identifying the documents that satisfy the query. Similar result documents are identified by adjusting a breadth of the query by applying less inclusive search parameters and identifying documents from the corpus that satisfy the query. A responsive classification code is automatically assigned to each same result document for classification as responsive documents. The similar documents are provided to the user. A responsive classification decision is received form the user for classification as the responsive documents.

Abstract: The method allows users of mobile devices or desktop/laptops in an organization to perform a search on a collated list of contacts for a particular contact and determine who, within the system/organization, may have that contact in their list. Contact lists from individual mobile devices are collated and stored and are searchable. A rating for the strength of each contact in a user's mobile contact list is made by determining the type of contact that the user uses to communicate with the contact and by the frequency with which the user communicates with the contact. This can be done across the contacts for the entire organization. The organization can also determine the strength of the contact list of someone in the organization or the relative strength of each contact.

Abstract: An apparatus for measuring contents similarity based on feedback information from ranked users includes: a user ranking unit for receiving from a database information on users as contents creators and feedback information on contents and ranking the users based on the received information; and a user grouping unit for classifying the users into a plurality of groups based on the ranking result. The apparatus further includes: a sequence modeling unit for receiving from the database the contents and the feedback information and modeling the number of feedbacks as sequences based on the ranked user groups; and a post similarity calculation unit for measuring similarity between the modeled sequences.

Abstract: An information device is provided that includes a first acquisition unit, a second acquisition unit, a search unit, a first display unit, a determining unit, and a second display unit. The first acquisition unit acquires situation data indicating a situation of the information device. The second acquisition unit acquires object information in accordance with the situation data. The search unit searches a database for related words related to the object information. The first display unit displays the related words to allow any one of the related words to be selected, while the determining unit determines whether any one of the related words is selected. The second display unit displays the object information acquired by the second acquisition unit for the selected related words.

Abstract: One embodiment of the invention sets forth a mechanism for recommending digital items to a user. Each digital item in a set of digital items is scored based on user preferences and other metrics. The digital items are ordered based on scores. The digital items are then evaluated in order of respective rank to determine a subset of digital items that re recommended to the user. The evaluation process is based on different evaluation criteria as well as the presentation style of the recommended digital items.

Abstract: Systems and methods may measure and rank a user's role in propagation of content within a population of users. In one aspect, the systems and methods allow a user to register a piece of content and to refer the registered content to a second user. The second user may refer the registered content to other users. The systems and methods track the propagation of the registered content among the users, and rank a user's relevance in propagating the registered content among the other users.

Abstract: A method and system for delivering highly relevant content, and removing irrelevant content, to a community of users over a conversational network platform. The embodiments of the present disclosure allow user-submitted content to be dynamically organized by “most trending” or “most important” by aggregating and evaluating user votes. User votes may expire according to a specified period of time to allow the system to determine relevancy of the content. An embodiment provides a forum for users to view and contribute content specifically tailored to individual entities, such that every instance of system content (including comments and votes) is related to one specific entity.

Abstract: A computer-implemented method includes receiving (i) a request for ratable content, and (ii) information specifying a geographic location of a computing device; accessing a data repository configured to store items of ratable content, with an item of ratable content associated with a geographic location; obtaining a plurality of items of ratable content related to the geographic location of the computing device; sending, from the obtained items of ratable content, an item of ratable content to the computing device; receiving a request for ratable content associated with a level of granularity relative that is higher than the level of granularity of the sent item of ratable content; sending, to the computing device, another item of ratable content, from the obtained items of ratable content, that is associated with a level of granularity that is higher than the level of granularity of the previously sent item of ratable content.

Abstract: A system including a processor and a memory storing instructions that, when executed, cause the system to: receive a stream of content including a plurality of content items; retrieve a plurality of related content items; identify a topic for at least one of the plurality of the related content items; rank the topics by relevance to the user and one of the plurality of items; associate the topic to the content item in the stream of content where the topic is ranked as being relevant to the content item; generate a marker for the topic; generate an interface including the marker associated with the content item in the stream of content; and provide the interface for display.

Abstract: A method includes analyzing a cluster of conceptually-related portions of text to develop a model and calculating a novelty measurement between a first identified conceptually-related portion of text and the model. The method further includes transmitting a second identified conceptually-related portion of text and a score associated with the novelty measurement from a server to an access device via a signal. Another method includes determining at least two corpora of conceptually-related portions of text. The method also includes calculating a common neighbors similarity measurement between the at least two corpora of conceptually-related portions of text and if the common neighbors similarity measurement exceeds a threshold, merging the at least two corpora of conceptually-related portions of text into a cluster or if the common neighbors similarity measurement does not exceed a threshold, maintaining a non-merge of the at least two corpora of conceptually-related portions of text.

Abstract: A method of location-based data organization is provided. The method includes obtaining a graph that includes nodes, each node connected to at least one other node with an arc. The nodes include a geography nodes associated with geographical locations, and activity nodes. The method also includes dynamically assigning weights to the nodes, and finding, for a first activity node, a suggested set of one or more activity nodes.

Abstract: Method, system, and computer program product for automatic generation of a word-cloud for a content item are provided. The method includes: extracting terms from a content item using statistical selection criteria; weighting a term by a probability that the term is used as a tag; and generating a visual representation of terms with enhanced representation of terms according to the weighting. Weighting a term by a probability that the term is used as a tag may include determining the relative frequency of the term in a folksonomy of tag terms for a domain.

Abstract: This disclosure relates to systems and methods for providing a map-like interface to navigate topics and content.

Abstract: An electronic device may be operable to communicate over a physical medium and to regulate the transmission of a message onto the physical medium. The device may access the medium in accordance with a CSMA scheme, wherein one or more values of one or more CSMA parameters may be determined based on the result of a comparison of a received search token to data stored in the communication device. The message may be a response to a received request message, and the search token may have been received in the request message. A value of the CSMA parameter(s) may be determined based on the result of a comparison of the score and one or more thresholds. The threshold(s) may have been received in the request message. The value(s) of the CSMA parameter(s) may be determined based on one or more initial values contained in the received request message.

Abstract: Provided are an analysis method and system for audience rating and advertisement effects based on viewing behavior recognition including a method of recognizing a viewer on the basis of image recognition through a camera and efficiently collecting data and a method of transmitting collected data on the basis of viewer recognition to an audience rating and advertisement effect measurement server. The present invention includes a viewing behavior measurement device configured to receive a viewer image obtained by imaging one or more viewers who are viewing broadcast content, recognize the one or more viewers from the received viewer image to generate viewing behavior information, and deliver the generated viewing behavior information, and an advertisement effect measurement server configured to analyze an advertisement effect for each viewer on the basis of the received viewing behavior information and generate and deliver an advertisement effect measurement result.

Abstract: A challenge to be met is to make it possible to accurately ascertain a behavior history of a person in various camera environments. Person characteristic data extracted from a plurality of cameras are stored in a person characteristic database. A retrieval request receiving section receives an identifier for identifying a person to be retrieved as a retrieval key. A characteristic retrieval section performs retrieval of persons matching the retrieval key from the person characteristic database in descending order of similarity. A retrieval result grouping section classifies the results of retrieval into units assumed to belong to the same environment. A retrieval result display section displays results of grouping. Since retrieval results are displayed in the form of a list on each unit assumed to belong to the same environment, the person to be retrieved can simply be ascertained in various camera environments despite a limited number of displays provided.

Abstract: An information processing device includes: a creating unit that extracts link information from content, and creates interpage relationship data which includes information between a subject page and linking pages having links from/to the subject page directly or indirectly; a page weight calculating unit that calculates the weight of at least one of the linking pages, based on the interpage relationship data; a tag weight calculating unit that calculates the weight of a tag, based on the weight of the at least one of the linking pages and information about the tag; a tag transmission determining unit that determines which tag is to be transmitted to which page, based on the tag weight; and a page creating unit that creates a new page having the tag added to the subject page, based on the determination result of the tag transmission determining unit.

Abstract: In an embodiment, a method is provided for determining a mood profile of media data. In this method, mood is determined across multiple elements of mood for the media data to create a mood profile associated with the media data. In some embodiments, the mood profile is then used to determine congruencies between one or more pieces of media data.

Abstract: Embodiments of methods for record linkage and comparing attributes are presented herein. Broadly speaking, embodiments of the present invention associate data records using distance measures and weights. More particularly, embodiments of the present invention generate a weight-based comparison of attributes. More specifically, embodiments of the present invention involve deduplication of records in a single database and linkage of records in multiple databases. In some embodiments of the invention, records may be merged into a master database based on the linkage and comparison of attributes. In addition, embodiments of the present invention may calculate a quality measure to be used in comparing attributes and records.

Abstract: A domain classifier develops and maintains relevance data about specific domains based on historical relevance data and source context data. Such data may be used to classify the user's interest in attempting to visit a specific domain and thereby redirect the user to a website expected to be aligned with the user's interest. In various implementations, the historical relevance data is derived from source context data and/or post-visit user behavior collected from previous attempts to visit a specific domain. The source context data collected from the current visit may also be used as source context-factors to influence domain classification. Based on such historical and current source context factors, as well as the domain address provided in the user's navigation request, a domain classifier consults the historical relevance data and provides the user with Web content that is identified as likely to be relevant to the user's interests.

Abstract: A method for evaluating and/or scoring pharmaceutical/life science technology is provided. The method includes importing data of a publication; transforming the data into a structured schema; ingesting the structured schema to determine a context of the data and draw associations between the data and a plurality of profiles; and generating a score based on the associations between the raw data and the profiles. The method may also include generating meta-data based on the determined context of the data and/or one or more quantitative metrics having a temporal component based on the ingested data. Related apparatus, systems, techniques and articles are also described.