Abstract: Aspects of the disclosure relate to identifying legitimate websites and removing false positives from domain discovery analysis. Based on a list of known legitimate domains, a computing platform may generate a baseline dataset of feature vectors corresponding to the known legitimate domains. Subsequently, the computing platform may receive information identifying a first domain for analysis and may execute one or more machine learning algorithms to compare the first domain to the baseline dataset. Based on execution of the one or more machine learning algorithms, the computing platform may generate first domain classification information indicating that the first domain is a legitimate domain. In response to determining that the first domain is a legitimate domain, the computing platform may send one or more commands directing a domain identification system to remove the first domain from a list of indeterminate domains maintained by the domain identification system.

Abstract: Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate automated answers to a question using summarized logical forms (SLFs). A myriad of techniques may be utilized to manually or automatically generate one or more summarized logical forms for an answer, where the summarized logical form(s) identifies the main entities/informative portions of the answer. Instead of indexing the whole of the answer as in conventional methods, an answer can be indexed using the summarized logical forms. A subsequent query may be matched to the SLF and the answer may be provided in response to the question. By indexing the answer with its informative portions, the speed and accuracy of identifying the answer is improved.

Abstract: According to an exemplary embodiment of the present disclosure, a method, apparatus for evaluating a review, a device and a computer readable storage medium are provided. The method for evaluating a review includes obtaining a first vectorized representation of a set of text items in a review for a target object. The method further includes extracting a semantic feature of at least two consecutive text items of the set of text items based on the first vectorized representation. The method further includes determining a degree of importance of the at least two consecutive text items in a context of the review, and determining a degree of the review helping a user to evaluate the target object, based on the degree of importance and the semantic feature. In this way, an automatic, efficient, and accurate evaluation of the value of a review may be achieved.

Abstract: A method, system, and computer program product for modifying and improving a network search is provided. The method includes receiving a search string associated with a search request of a user. The search string is transmitted to a search system. In response, initial search results associated with the search string are received and analyzed with respect to previous interactions and user preferences. Modified search results are generated from the initial search results and filter software is executed with respect to the modified search results. Digital tags are applied to portions of the modified search results and the modified search results are presented with respect to instructions associated with the digital tags.

Abstract: Systems and methods for improving attribute data for a point of interest (POI) are provided. A networked system accesses trip data associated with the POI. The networked system generates, using a processor-implemented clustering algorithm, a first spatial cluster and a second spatial cluster using coordinates corresponding to the POI indicated in the trip data. A centroid for the first spatial cluster and a centroid for the second spatial cluster are identified by the networked system. The networked system determines that a difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses a centroid distance threshold. In response to the determining, a database is updated to indicate a new attribute for the POI, the new attribute corresponds to an attribute associated with either the first spatial cluster or the second spatial cluster.

Abstract: A system comprising a memory storing an inverted index of a corpus of documents, and a processor coupled to the memory and configured to receive a search query, after receiving the search query identify a first subset of documents that include the search query by searching, based on the search query, the inverted index of the corpus of documents, wherein the corpus of documents includes the first subset of documents, process the first subset of documents to identify entities related to the search query and relations between the entities and the search query, and generate a knowledge graph based on the entities and the relations.

Abstract: A system and method according to the principles of the invention identifies mobile phone aliases. The system processes mobile location data and call event data to generate mobility profiles. The profiles indicate a mobile's geographic zone history over a specified time. To produce a mobility profile, the system aggregates location data into zones and associates the zones with times of day, week or month. Particular zones for different mobiles can be compared according to weighting algorithms to provide data indicating whether the mobiles belong to the same user.

Abstract: Techniques for phishing protection using cloning detection are described herein. The techniques described herein can include a server which hosts a website detecting that a fetcher is a cloning toolkit or an entity known for using a cloning toolkit. The techniques can also include a server which hosts a downloadable application (such as a mobile application) detecting that a fetcher for the application is a cloning toolkit or an entity known for using a cloning toolkit. The detection can be done in several ways, such as by analyzing data logs for patterns associated with cloning toolkits or entities known for using cloning toolkits. The techniques described herein can also include a part of an end user device (such as a part of a mobile device) detecting a clone (such as a clone website or application) that was cloned by a cloning toolkit. Then, upon detection, security actions can be taken.

Abstract: A method to detect spam SMS messages including unsolicited repeated SMS messages originating from or sent to one or more subscribers of one or more mobile communication networks, comprises: clustering messages in similarity clusters, wherein each similarity cluster comprises SMS messages with identical or similar content; counting an amount of SMS messages in each similarity cluster; monitoring a rate of SMS messages in each similarity cluster; and classifying SMS messages of a similarity cluster as spam when the amount of SMS messages in the similarity cluster exceeds a certain first threshold and the rate of SMS messages for the similarity cluster exceeds a certain second threshold.

Abstract: A method for authenticating a user of a mobile electronic computing device to perform operations on a first electronic computing device includes receiving a request to access the first electronic computing device. In response to the request to access, a first identifier is sent to the mobile electronic computing device. A second identifier is received from a second electronic computing device. The second electronic computing device is different from the mobile electronic computing device. A determination is made as to whether the first identifier matches the second identifier. When the first identifier matches the second identifier, a trust score is calculated for the user. A determination is made as to whether the trust score is equal to or greater than a threshold. When the trust score is equal to or greater than the threshold, the user is authenticated to login to the first electronic computing device.

Abstract: A computer-implemented method for updating generic file-classification definitions may include (1) identifying at least one generic file-classification definition deployed in a software product installed on a client device, (2) classifying at least one data sample encountered by the client device based at least in part on the generic file-classification definition, (3) querying at least one verification server in an attempt to verify the correctness of the classification of the data sample, (4) determining that the classification of the data sample is incorrect based at least in part on the query, and then (5) modifying the generic file-classification definition deployed in the software product based at least in part on the data sample. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a method includes receiving a packet flow associated with a click-through from an end user node destined for an advertiser server; extracting information from the packet flow; analyzing the extracted information to determine one or more characteristics of the packet flow; and classifying the packet flow based on the determined one or more characteristics; modifying the packet flow to include classification information to provide classification information indicating a quality level of the click-through. The packet flow may include a hypertext transfer protocol GET request. Modifying the packet flow may include adding a tag with classification information that indicates a likelihood of fraudulent click behavior associated with the packet flow.

Abstract: The present disclosure relates to apparatus, systems, and methods for providing a location information analytics mechanism. The location information analytics mechanism is configured to analyze location information to extract contextual information (e.g., profile) about a mobile device or a user of a mobile device, collectively referred to as a target entity. The location information analytics mechanism can include analyzing location data points associated with a target entity to determine features associated with the target entity, and using the features to predict attributes associated with the target entity. The set of predicted attributes can form a profile of the target entity.

Abstract: Methods and systems of the present invention allow for improving website performance. An exemplary method may comprise the steps of calculating a website quality score for a website (which may indicate the website's effectiveness), identifying changes to the website's attributes that would improve the website's quality score, and modifying the website to include such changes.

Abstract: An embodiment for providing a secure virtual browsing environment includes creating a virtual browsing environment with a virtualized operating system sharing an operating system kernel of a supporting operating system and executing the browser application within the virtual browsing environment. Another embodiment includes receiving a website selection within a browser application, determining if the website selection corresponds to a secure bookmark, and creating a second virtual browsing environment and executing the browser application within the second virtual browsing environment to access the website selection when the website selection corresponds to a website specified as a secure bookmark.

Abstract: A processor engine for affecting a website's position on at least one Internet search engine's page ranking comprises at least one processor. The at least one processor is arranged to: load (425) at least one search term into a program (425) running on the at least one processor; load (445) a target list comprising at least one website that is to be promoted; and create (420) an Internet connection. The at least one processor is further arranged to request a search of the at least one search term on the at least one Internet search engine; identify at least one website search hit that matches at least one website on the target list; and access the identified at least one website a plurality of times, affecting the at least one website's position on the Internet search engine's page ranking.

Abstract: A computer-implemented method and system for managing keyword bidding prices are disclosed. An example system embodiment includes an automatic keyword bidding module, operably coupled with a processor and a memory, operable to determine a revenue per click value associated with a keyword, obtain bidding information associated with the keyword, obtain automatic bid controls associated with the keyword, and automatically generate a bid value for the keyword based on the revenue per click value, the bidding information, and the automatic bid controls.

Abstract: A computer-implemented method of determining the relevance, to a user, of documents accessible over a computer network involves analyzing information relating to a first document, identifying a second document corresponding to the first document using a computer, obtaining information that indicates the relevance of a second document, determining the relevance of the first document using the information indicating relevance of the second document. The first document may be a mobile document, while the second may be a non-mobile document.

Abstract: A method for selecting a command file is described. One or more command files coupled with a first device are accessed. Each command file of the one or more command files comprises one or more command file attributes. One or more device attributes associated with a second device are accessed. The one or more command file attributes and the one or more device attributes are compared to determine a correlation between the one or more command files and the second device. Based on the comparing, generating a ranked portion of the one or more command files according to the correlation.

Abstract: Defeating click-through cloaking includes retrieving a search results page to set a browser variable, inserting a link to a page into the search results page and clicking through to the page using the inserted link. Investigating cloaking includes providing script associated with a suspected spam URL, modifying the script to de-obfuscate the script and executing the modified script to reveal cloaking logic associated with the script.

Abstract: A processor engine for affecting a website's position on at least one Internet search engine's page ranking comprises at least one processor. The at least one processor is arranged to: load (425) at least one search term into a program (425) running on the at least one processor; load (445) a target list comprising at least one website that is to be promoted; and create (420) an Internet connection. The at least one processor is further arranged to request a search of the at least one search term on the at least one Internet search engine; identify at least one website search hit that matches at least one website on the target list; and access the identified at least one website a plurality of times, affecting the at least one website's position on the Internet search engine's page ranking.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for providing an adaptive knowledge platform. In one or more aspects, a system can include a knowledge management component to acquire, classify and disseminate information of a dataset; a human-computer interaction component to visualize multiple perspectives of the dataset and to model user interactions with the multiple perspectives; and an adaptivity component to modify one or more of the multiple perspectives of the dataset based on a user-interaction model.

Abstract: Query generation for searchable content is provided. In some embodiments, query generation for searchable content includes receiving searchable content (e.g., the searchable content can include a unique identifier for the searchable content, such as a Uniform Resource Locator (URL) for a web site, and the web site can include one or more web pages); and generating a set of queries, the set of queries including one or more queries (e.g., the set of queries can include ranked queries) that are relevant to the searchable content.

Abstract: The disclosed embodiments provide a reputation system. The reputation system includes a scoring apparatus that provides a matrix of reputation scores for a set of items and a set of dimensions of the items in the reputation system, wherein the matrix comprises unknown values for a subset of the reputation scores. The reputation system also includes an inference apparatus that calculates a factorization of the matrix and uses the factorization to update the matrix with a set of inferred values for the set of reputation scores. Finally, the reputation system includes a ranking apparatus that uses the updated matrix to obtain a ranking of the items by one or more of the dimensions.

Abstract: This disclosure describes systems and associated processes for generating recommendations for users based on usage, among other things. These systems and processes are described in the context of an interactive computing system that enables users to download applications for mobile devices (such as phones) or for other computing devices. Users' interactions with applications once they are downloaded can be observed and tracked, with such usage data being collected and provided to the interactive computing system. The interactive computing system can include a recommendation system or service that processes the usage data from a plurality of users to detect usage patterns. Using these usage patterns, among possibly other data, the recommendation system can recommend applications to users for download.

Abstract: A method, apparatus, and correspondingly configured computer program, in which a querying device inputs a user an identification of desired content and sends a query request for the desired content to surrounding memory devices. The query request is adapted to cause compatible receiving memory devices to perform a search based on the request. The memory devices are configured to listen to query requests and responsively perform searches based on the queries. Any memory device that finds content according to the query request responds to the query device which, after sending the query request, monitors for the compatible receiving memory devices for information that the queried content is found. Responsive to receiving the information from a given memory device, the querying device establishes a connection with the given memory device and obtains the content.

Abstract: Methods and systems for identifying and presenting information are described. Search results are received from a search engine. An entity associated with a networked site is selected using a selection criterion. A determination is made as to whether the listing includes a link to the networked site or includes the link to the networked site at a list position that fails to satisfy a first criterion. After determining that the link to the site associated with the entity is not included in the search result listing, or that the link to the site associated with the entity is not at a position in the search result listing that satisfies the first criterion, the search listing is modified by causing the link to the site associated with the entity to appear in a first position in the search listing. The modified search listing is displayed on a user terminal.

Abstract: There is a method and a system for concentration detection. The method for concentration detection includes the steps of extracting temporal features from brain signals; classifying the extracted temporal features using a classifier to give a score x1; extracting spectral-spatial features from brain signals; selecting spectral-spatial features containing discriminative information between concentration and non-concentration states from the set of extracted spectral-spatial features; classifying the selected spectral-spatial features using a classifier to give a score x2; combining the scores x1 and x2 to give a single score; and determining if the subject is in a concentration state based on the single score.

Abstract: Artificial identities or information sources are created and used for—among other things—the purpose of manipulating the output of information retrieval, recommendation systems, or any information gathering and classifying technique based on relationships between information sources. Fictitious information sources or information designed to be recognized as untrustworthy by an information trust ranking system are created. By linking otherwise trustworthy information sources to fictitious information or information, they also appear less trustworthy. Target information or information sources are made to rank much lower in the output of systems designed to prioritize trustworthy information sources. Other applications include creating information or associations to make targeted information or information sources rank higher and reliable by information retrieval or recommendation systems.

Abstract: Systems and methods promoting an authoritative version (AVR) of copyrighted media content over one or more non-authoritative versions of the copyrighted media content relative to relevancy of the copyrighted media content to a search query are presented.

Abstract: A method performed by one or more processing devices includes obtaining search results responsive to a search query submitted by a user; determining a maturity score for the user, where the maturity score represents a measure of development of a particular user attribute; determining, based on the maturity score, utility scores for the search results, where a utility score represents a measure of utility of a particular type of content to a particular type of user as defined by the measure of development of the particular user attribute; and adjusting rankings of the search results based on the utility scores.

Abstract: Adjusting search results ranking is disclosed, including: receiving a search query comprising one or more keywords submitted by a user; determining intermediate ranked results comprising a plurality of sets of product information matching the one or more keywords; determining a trust level value associated with the user with respect to a first seller of a plurality of sellers associated with the intermediate ranked results, wherein the trust level value is determined based at least in part on one or more historical user product information evaluation records associated with the first seller submitted by the user; and adjusting ranking associated with the intermediate ranked results based at least in part on the determined trust level value associated with the user with respect to the first seller to determine final ranked results.

Abstract: In this invention, systems and methods for providing keywords for advertising are provided. After a user searches for another user in a social network, the webpage or blog of the queried user is retrieved, and keywords are extracted from this webpage. The keywords may be extracted from the user's profile on the social network (e.g., favorite sports, music artists, etc.), or keywords may be extracted from the text of the webpage (e.g., comments that comprise the blog entries). Once extracted, these keywords may then be used by an advertising system to provide targeted advertisements to the user.

Abstract: A processor engine for affecting at least one authorized website's position on at least one Internet search engine's page ranking is described. The processor engine comprises at least one processor arranged to: identify a target list comprising at least one authorized website that is to be promoted; open a web browser; access an internet search engine on the first web browser; load at least a part of at least one search term into the internet search engine running on the web browser; associate at least the part of the at least one search term with the at least one authorized website on the target list; close the web browser, and repeat a plurality of times, the operations of open, access, load, associate, and close, thereby affecting the at least one authorized website's position on the internet search engine's page ranking.

Abstract: The present disclosure includes, among other things, systems, methods and program products for modifying search result rankings based on populations.

Abstract: A method, system, and apparatus for presenting information on a user in a social network is disclosed. In some embodiments, this includes analyzing a user profile for character traits, wherein the user profile is populated with information provided by third party users, determining a number of times the user has populated other users' profiles, determining a number of times the third party users have populated the user profile, calculating a user reputation score based on the analysis, the number of times the user has populated other users' profiles, and the number of times the third party users have populated the user profile, and storing the user reputation score in a storage device.

Abstract: Systems and methods sort location dependent information based on selecting multiple groups of information according to location, ordering the groups based on location, and ordering the information within the groups based on at least one or more other criteria. The size(s) of the areas used to select the groups may be predetermined, or dynamically determined (e.g., based on clustering of information along distance to a location of interest).

Abstract: Query generation for searchable content is provided. In some embodiments, query generation for searchable content includes receiving searchable content (e.g., the searchable content can include a unique identifier for the searchable content, such as a Uniform Resource Locator (URL) for a web site, and the web site can include one or more web pages); and generating a set of queries, the set of queries including one or more queries (e.g., the set of queries can include ranked queries) that are relevant to the searchable content.

Abstract: A system and method for providing a natural language interface to a database or the Internet. The method provides a response from a database to a natural language query. The method comprises receiving a user query, extracting key data from the user query, submitting the extracted key data to a data base search engine to retrieve a top n pages from the data base, processing of the top n pages through a natural language dialog engine and providing a response based on processing the top n pages.

Abstract: A method can include detecting an incoming voice mail message and accessing information associated with the incoming voice mail message. The information associated with the incoming voice message may then be compared with some other information, which may comprise one or more of these attributes associated with each message: a caller ID; a time stamp; a user extension; a message length; a caller identification; message content; and whether a user has tagged each message as spam.

Abstract: Methods and systems for selecting advertisements to present to a user of a computing device are provided. An advertisement system selects advertisements to display to a user based on the serving area of candidate advertisements. The advertisement system selects those candidate advertisements whose serving area encompasses the user's current location. The advertisement system may also select candidate advertisements to present to a user based on a map area currently being displayed to the user. The advertisement system may filter the candidate advertisements based on the provider location being within the map area that is currently being displayed to the user.

Abstract: An exemplary method for protecting web browsers from spam includes providing a multi-layer model that includes a doorway layer, a redirection domain layer, an aggregator layer, a syndicator layer and an advertiser layer; identifying domains as being associated with at least one of the layers; and, based at least in part on the identifying, taking one or more corrective actions to protect web browsers from search spam. An exemplary method for identifying a bottleneck layer in a multi-layer spam model includes providing a multi-layer spam model, collecting spam advertisements, associating a block of IP addresses with the collected spam advertisements and identifying a bottleneck layer based on the block of IP addresses. Other methods, systems, etc., are also disclosed.

Abstract: A system and method are provided that detect spam business listing data. In one aspect, a plurality of clusters containing previously captured spam business data is formed. The attributes of new incoming business data may be compared to the attributes of the clustered spam business data. If the incoming business data is associated with any one of the plurality of clusters, the incoming business data may be deemed spam.

Abstract: The method and system of the present invention provides an improved technique for integrated asset management. Information is aggregated from a variety of sources into a centralized computerized database. Thereafter, asset transition events are scheduled. Information from the centralized computerized database is used in the performance of the asset transition events and information relating to the asset transition events is added to the centralized computerized database. Subsequent changes to the asset are also recorded into the centralized computerized database. As a result, a plethora of information is available within said database for the purpose of managing future asset transition events.

Abstract: A spam score is assigned to a business listing when the listing is received at a search entity. A noise function is added to the spam score such that the spam score is varied. In the event that the spam score is greater than a first threshold, the listing is identified as fraudulent and the listing is not included in (or is removed from) the group of searchable business listings. In the event that the spam score is greater than a second threshold that is less than the first threshold, the listing may be flagged for inspection. The addition of the noise to the spam scores prevents potential spammers from reverse engineering the spam detecting algorithm such that more listings that are submitted to the search entity may be identified as fraudulent and not included in the group of searchable listings.

Abstract: Techniques for extracting information from a database are provided. A database such as the Web is searched for occurrences of tuples of information. The occurrences of the tuples of information that were found in the database are analyzed to identify a pattern in which the tuples of information were stored. Additional tuples of information can then be extracted from the database utilizing the pattern. This process can be repeated with the additional tuples of information, if desired.

Abstract: A method of and apparatus for constructing a user profile using a content tag, a method of recommending digital content by using a user profile including a tag included in the digital content and a preference value for the tag. According to the methods and apparatus, a user profile is generated by using a content tag, and thus the taste of the user according to digital content consumption can be expressed in more varied ways. Also, by suggesting a method of generating a tag from web content, construction of a user profile for digital content having no tag is enabled. Furthermore, a tag extracted from digital content used by a user is included in a profile and it can be used for a variety of purposes, such as expansion of a comparison scope, use of preference keywords, providing of content links, and expansion of search scope.

Abstract: Implementations and techniques for determining a relative importance among ordered lists are generally discussed.

Abstract: Methods, systems, and apparatus, including computer program products, for generating visual media search results are provided. A first search query in a first language and a second search query in a different second language are received. The first search query is a translation of the second search query into the second language. A quality of results statistic for the second search query is obtained. A final search query is created using the first search query, the second search query, and the quality of results statistic. The final search query is sent to a search engine and a final group of visual media search results responsive to the final search query are received from the search engine, where visual media search results in the final group that are responsive to the second visual media search query are assigned a ranking based in part on the quality of result statistic.

Abstract: This specification describes technologies relating to providing search results. One aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving a network resource, the network resource including text content; generating a language model score for the resource including applying a language model to the text content of the resource; generating a query stuffing score for the reference, the query stuffing score being a function of term frequency in the resource content and a query index; calculating a gibberish score for the resource using the language model score and the query stuffing score; and using the calculated gibberish score to determine whether to modify a ranking score of the resource.